Jules + Gemini: Automate Your Real Estate Backend

by Al Pinder | Sep 12, 2026 | Uncategorized

You close a deal and the real work begins. The follow-up emails, the signed document tracking, the marketing for the next property — and if you’re honest, most of it is you remembering to do a task you didn’t write down, on a day you didn’t plan. There’s a quieter, quieter fear than losing a deal: losing a follow-up, and the client who was never reminded they existed. That’s not a lack of effort, that’s a lack of a system you can actually trust. Almost every agent has built their own version of one — a spreadsheet, a list, a stack of folders — and almost every agent has watched that system fill up and stop being useful the moment they added one more deal. This is the version of that system that actually scales, because the system itself is the thing that changes when you get busier, not your own plate.

Who This Is For

If you’re a few years into this business, closing 6 to 8 deals a year, pushing for more volume and consistency, this is your play. You didn’t get into real estate to become a part-time IT specialist, but you also know the agents who actually build systems instead of just talking about them are the ones who scale. The problem was never that you don’t understand technology — it’s that you don’t have 40 hours a month to throw at it. That’s exactly the gap we built this to fill.

Before We Show You What Goes on the Screen

Let us show you what your backend looks like when it’s actually running. You start the day opening 5 or 6 different apps, checking emails, scanning a spreadsheet, and you’re already behind before you’ve talked to a client. Every platform is running on its own schedule, and nothing is actually connected — you’re the connection. That’s not a system, it’s a job, and it’s the exact thing standing between you and a business that runs without you. Nobody plans to build a job for themselves, but it happens one Band-Aid at a time. A spreadsheet for this, a shared folder for that, a quick email instead of an actual record, because you’re busy and it seems faster. It’s not your fault — you’re doing the work in front of you. The problem is that ‘faster’ always means ‘more fragile’ in the long run, and fragile cannot scale. Now, here’s the part nobody tells you. The agent who looks like they’re 3 steps ahead of you isn’t more talented or harder working — they just got rid of that job before you did. They built the connection instead of being it, and that’s exactly what we’re going to show you how to do.

How We Connect Everything

Here’s the simple version of what we do, and we want you to understand it before we get into the tech. We connect your backend 2 different ways, depending on the job. Sometimes we connect your sources directly — the data goes straight from one system into the next without you touching it. Other times we connect through an air traffic control layer, which means the request goes to a central hub and the hub decides where it needs to go next. Both patterns are in the public code, and the right one for a given job is whichever one gets you to done.

What It Actually Does

Here’s the part that actually matters, because neither of these tools is a feature tour you watch and then forget. You set them up once, with help if you want it, and then they work the shift you gave them — the AI writes the update, the automation publishes it, the blog gets the new post, the emails go out, the numbers stay current, and you never reopen either app. You build your pipeline and let the machines run the loop you set up.

If you’re pushing for more volume, you clone the loop and point it at a new neighborhood. If you’re protecting your reputation, you build a separate loop that runs the review-check on a schedule and sounds the alarm the moment something comes back dirty. And if you’re building a brand, you’re not posting occasional throwaway content — you’re running the loop that publishes the guided series, every Monday, without you touching it.

This is what ‘automate your backend’ actually means: you stop doing the work that a computer can do cheaper and faster than you ever could, and you put your own energy into the relationships and the deals where only a real human touch makes a difference.

How You Set It Up

Here’s what the lead setup actually looks like, because we want you to see exactly what’s running — not a generic description of what ‘automation’ means. Start with the two things you already have: you have a real estate business running on SkySlope, and you have a Google Workspace account for email. Nobody’s building a custom plugin here. You’re borrowing the brain that’s already running your leads and the inbox that’s already handling your communications, and pointing both at the same, organized set of facts about your business.

On the lead side, the first thing we did was take the existing lead pipeline — the flow from new lead to follow-up call — and freeze it exactly as it was. Nothing changed there. Then we opened the settings and added one thing: a scheduled run, the same way you’d set up a recurring report. Every Sunday at 8:05 AM, with the market quiet and the week’s new leads already sitting in the system, that schedule triggers the lead review on its own, without anyone at the keyboard.

It runs the exact same review it always has — the same follow-up rules, the same lead scoring, the same assignment logic — but now it’s running unattended, on a clock, instead of depending on a team member remembering to run it manually. That one change is what actually makes the rest of this possible. Every Monday morning, without anyone staying late on a Friday to prepare a report, you have a fresh, current snapshot of where every lead stands, delivered to your inbox, without anyone touching it.

The second half is where the new ground opens: turning your business data into a knowledge graph that answers questions in plain English. None of this is about filing a new piece of software. It’s about structuring your own data so that it can answer a question it’s never been asked before — not a Google query, an email to an assistant, or a call to a team member. An actual question, phrased in plain English, typed into a chat window, and answered the same way a person would answer it, drawing from the exact same sources as if you had called the office and asked aloud.

To make that possible, you build a knowledge graph — think of it as a map of your business, drawn in your own words. You start from the core facts: what a ‘working’ lead is, what a ‘contact’ is, what ‘follow-up needed’ means, and you define those once, so they’re exactly the same to the system as they are to you. Then you connect everything that depends on those definitions.

How It Gets You Found

Here’s the actual question Google answers when someone asks it out loud: what’s a good real estate agent near me. And here’s the part most agents miss: that question gets asked with a lot of different wording, in a lot of different ways, every single day — what real estate agents are in my area, who’s a good real estate agent near me, who sells homes in my town, and so on.

None of those questions are a person typing into Google. They’re a voice assistant, getting asked aloud, in a moment when somebody’s thinking about real estate. And the answer, every single time, comes down to one thing: which agent has shown up, consistently, in as many of those question variations as possible, across their own website and across the rest of the internet, with useful, relevant, locally-published content that matches what the person is actually asking in that moment.

That’s what Google calls a ‘knowledge panel’ answer — the answer box at the top of the results, the map that shows up, the local 3-pack that gets displayed — and those answers don’t get picked by Google on a whim. They get picked by a system that analyzes, every single day, which website is actually answering the questions that people in that area are asking, with fresh, local, useful content that matches what the search is actually asking in that moment.

Almost no agent can manually keep up with that, across their own site and across the rest of the local web, week after week. Which is exactly why we built this, with Claude Code, inside Gemini.

You run it from the command line, on your own machine, and you tell it which local market you want to target. It goes out and pulls every single one of your existing websites and landing pages into a unified system — your main site, any local lead pages you’ve already built, your blog, your YouTube channel, your Facebook page, your Realtor.com profile, and even your Zillow Guide pages, if you have them.

Then it does the heavy lifting that used to eat a full afternoon — it audits every page, flags gaps where you’re not answering the questions people are actually asking, and surfaces the exact content gaps that are costing you visibility.

What It Means For You

If you’re pushing for volume, this turns a 40-minute evening job into a 2-minute review in the morning. If your business runs on relationships, it’s a compliance safety net — every description defensible in front of your broker. And if you’re building a brand, it’s copy that sounds like a professional wrote it, every time, because the structure never gets tired at 9 PM even when you do.

What It Frees You Up To Do

This is what all of it actually does: it lets you get off the keyboard and in front of the next client, because the follow-up is already running. You set it once, in plain English, and from then on you’re answering people, not spreading your time thin across 10 different platforms trying to keep up.

If you’re pushing for volume, every hour you get back is another call or showing. If you’re building a brand, every consistent post is another touch that adds up, and you’re finally the one who remembers to post instead of forgetting for a month.

Either way, you own your time again instead of renting it from your inbox.

What To Do First

If you’re pushing for volume, the natural impulse is to throw more hours at it — more calls, more follow-up, more content. But the real bottleneck isn’t hours; it’s that you can only be in one place doing one thing at a time, while the market moves on to the next showing, the next call, the next follow-up. That’s the gap Gemini fills. It’s not a chatbot, and it’s not a piece of content. It’s the rest of your business, running on its own clock, while you’re out doing the next deal.

Here’s what that actually means, step by step, because ‘running on its own’ is where the confusion starts. Step one: make a list, in plain English, of every recurring task in your business that eats a real, non-refundable chunk of your day — the follow-up calls, the content production, the report generation, the posting, the sharing. Write it down. If you’re building this with us, we’ll do that part with you, and the list always comes out longer than you expected. Step two: separate that list into two columns. On one side, put the tasks that actually require you, your judgment, your voice, your relationship with the client. On the other side, put everything else — the follow-up calls that are just a script read out loud, the posts that are just a format filled in, the reports that are just a file named correctly and dropped into an email. Three columns now: the few things you actually do, the many things that just need to get done on a schedule, and the middle column, which is the bridge we’re building. Step three: Build from what you already do — you don’t replace yourself with a bot. You replace the middle column. You build, one item at a time, a machine that takes a request in that format and produces a finished, correct, on-brand piece of follow-up, a finished, correct, on-brand post, a finished, correct, on-brand report, without you touching it. And here’s the part that actually matters: you build that machine by copying what you already do. You don’t need a developer account, you don’t need to code, you just record, or write, or capture, the exact same message, the exact same structure, the exact same rhythm, that you’ve already been using by hand. The machine learns from that recording, or that document, the same way you learned it — by watching what you built.

Where to Start

If you want to run this on your own business — not just watch us do it on YouTube — here’s your next step.

We offer a free 15-minute call. It’s just us, Al and Victoria, and we’ll look at your business and tell you honestly what can be automated and what can’t.

The link to book it is right in the description below, and our number’s there too.

And if you’d rather start tinkering yourself, the free starter skills are open-source on GitHub — that link’s in the description as well. Clone it, try it, own it.

We’re Al and Victoria Pinder, husband-and-wife ICON agents at eXp Realty — and we run this in our own business every single day.

If this helped, subscribe so you catch the next build. We’ll see you in the next one.

Frequently Asked Questions

What tasks can actually be automated in a real estate business?

You can automate the recurring tasks that don’t require your judgment or relationships—follow-up calls that are just scripts, posts that follow a format, reports that need to be generated and sent on a schedule. The things that actually need you are client relationships and deal work; everything else is a candidate for automation if it’s repetitive and runs on a schedule.

How do you set up automation without coding or hiring a developer?

You start with what you already have—your existing lead pipeline in SkySlope and your Google Workspace email—and add a scheduled run to trigger reviews automatically on a set day and time. You don’t need code; you capture or record the exact process you already do by hand, and the system learns from that, the same way you learned it by doing it manually.

How does this help you show up in local search results?

The system audits all your existing websites, landing pages, blog, social media, and listing profiles to find gaps where you’re not answering questions people are actually asking in your market. It surfaces the exact content gaps that are costing you visibility, so you can fill them with relevant, locally-published content that matches what people search for.

Which Claude Skill Works for Commercial Real Estate?

by Al Pinder | Sep 11, 2026 | Uncategorized

300-job employer announces it’s relocating to your market next month. You find out the same way everyone else does — by reading the headline the next morning. You were the senior agent at the local brokerage, the one everyone called when a big deal was rumbling, and you never saw it coming.
That’s not a failure of intelligence. It’s a failure of source — you were reading the same news feeds as everybody else, reacting to the same public information, 24 hours behind the actual decision. And in a market about to get hammered by a major employer change, 24 hours is an eternity.
This is the real recorded call, the CEO telling us the move is happening, the board’s decision, before it’s been announced to anyone outside the company. We didn’t earn their trust — we signed a license that lets us access the exact same pre-public pipeline they already pay to have. The same pipeline the brokerage CEO across town is quietly paying to access as well, the same one the city’s economic development office is already subscribed to.
Nobody outworked anybody. One version of the same information was just quietly delivered to the right people, 3 weeks before it showed up in the local paper. That’s not an advantage any agent can buy — it’s an advantage the agent who builds the right pipeline can own, over and over, automatically, while the agent across town is still reading the news.

Who This Is For

If you’re a few years into this business, closing a steady handful of deals a year, and you’ve gotten most of your answers from Google and whatever your brokerage happens to offer — this is for you if you want to actually get ahead of the agent down the street who’s targeting the same clients. You don’t need to be tech-savvy. If you can send an email, you can run this.

So let’s clear this up, because the name sounds intimidating and it really isn’t. A ‘skill’ here is just a question you ask, in plain English, and the system gives you an answer — the same way you might ask Google a question and get an answer back. In this case, it’s a question about a specific kind of deal, or a specific market, or a specific client scenario, and the answer comes back as a real, usable piece of advice — not a generic article headline, actually a practical next step. Think of it as an expert sitting down with you and picking the exact right question to ask next, based on whatever you’re working on right now. You don’t program it, you don’t update it, you just ask it a question and it works. And the move here isn’t that you’re asking a computer instead of a person — it’s that the person you’re asking has already put in the hours to understand what you’re actually asking, and built something that asks it the same way every time it comes up, instead of a vague question that gets a vague answer.

Here’s why this actually matters for your business, beyond saving you a few minutes. When you’re targeting a specific niche or a specific type of deal, your competition has access to the exact same information you do — the same market reports, the same news headlines, the same generic advice. Nobody has a real advantage, because everybody’s reading the same sources and quoting the same numbers. The only thing that actually sets you apart is the quality of the question you ask next. A sharp question gets you to the real opportunity before anybody else knows it exists. This is how you stop reacting to whatever lead happens to walk in the door, and start pursuing the exact kind of deal you want, over and over, with a clear picture of what’s actually happening in that specific market.

What It Actually Does

Here’s what each one actually does, in plain English, with no jargon.
The first one, the chat skill, works like an assistant. You ask it a question — who’s the owner of a property, for example, or what’s the market cap rate for a specific building — and it goes and finds the answer for you, across whatever sources it’s been told to trust. It doesn’t give you a report with 10 possible answers and a ‘contact us’ at the bottom — it gives you one answer, the same way you’d ask a team member and get an answer back by email. The difference is, you’re asking a skill you’ve already set up, not re-sending the same question to someone who’s already gone home for the day.
The second one, the automation, runs on its own schedule without you touching it. You set up what you want checked — a weekly review of what’s changed in your market, for example, or a daily pulse on a specific deal — and it runs that review on its own, at the same time every day or every week, without you remembering to open anything. You just get the digest when you check your notifications, the same way you’d read a morning memo from an assistant who’d already been to work for an hour. If something big happens, it can alert you immediately, the same way it would tell you about an unexpected change at one of your own listings.
The third one, the integration hub, is the one that actually makes the other two useful every day instead of just occasionally. On its own, a chat window can only answer whatever you happen to ask it. An automation can only check whatever you told it to check, on whatever schedule you set. The hub connects the first two to your real working data — your MLS or your own internal listings, your follow-up notes, your calls and showings already logged — so every question actually gets answered from your real data, and every automation checks your real pipeline instead of a isolated test list you set up one day and then forgot about. That’s what actually makes a skill useful 20 days out of the month, not just the one day you happen to experiment with it.
None of this is about doing your job for you — it’s about handing off the part of your job that’s just asking a question or checking a list, so you’re actually using that hour you used to spend emailing updates to someone who’s paying you to be a pro, not a data entry clerk.

How You Set It Up

Here’s what we actually put on the machine, and how we ran it.
We checked out The Open-Source Claude Skills Repo for Real Estate Agents and searched for ‘commercial real estate’.
We picked the one that specializes in commercial property types, versions, and statuses, and we looked at its repository on GitHub to see exactly what it contains before we bought it.
It’s a collection of 5 things, and 4 of them run on our own machine, on our own schedule, without a browser open or a login window waiting for a password.
Number 1 is the daily digest, and that’s the one that runs automatically every morning.
It pulls activity from whatever commercial data source you point it at — new listings, price changes, status changes — and delivers that digest to your email inbox, formatted as a simple, easy-to-scan table.
Number 2 is the weekly lead report, and that runs on its own schedule as well, every Monday morning.
It pulls all of the lead contact forms from our own website — the ones we built with Claude Code last year — and it generates a report showing which listings are producing the most inquiries, which sources are sending the highest-quality traffic, and it delivers that report to a Google Sheet so it’s always there for reference, even when we’re out meeting with a client.
Number 3 is the monthly anomoly detector, and that runs the first day of every month.
It compares this month’s activity against last month’s, across all of our active listings, and if it finds anything unusual — a sharp drop in views, or a listing that hasn’t budged in 3 weeks — it flags that anomaly in the same Google Sheet where the weekly report lives, so we’re not flying blind from one weekly report to the next.
Number 4 is the quarterly content planner, and that runs on its own schedule three times a year.
It analyzes the topics our competitors are covering in our market and the questions our own website visitors are actually asking, and it generates a content calendar — a detailed, gap-filled map showing exactly what we should publish next to reach the agents and the investors who are actually searching right now.
That calendar writes itself every three months; we just open it and approve it.
The 5th item is the manual one, and that’s on purpose.
It’s a tool we can open from the command line any time we want to re-run something, or check something without waiting for a scheduled run.
We didn’t build any of this from scratch—we assembled it from existing open-source skills and connected them to our own data.

How It Gets You Found

Here’s what actually gets you found, and it’s quiet enough that most agents never bother with it.
When a CEO or a relocation director in your market types a question into Google — something like ‘who handles industrial leases in Eastern North Carolina’ — Google doesn’t hand them a list of agents. It hands them a list of websites that have already answered that question, in a way that showed Google that site is worth handing to a real person.
Nobody types ‘show me agents’ anymore. They ask a question, and the site that’s prepared with the right answer is the one that gets found. And here’s the part nobody tells agents: whether that’s your site or somebody else’s is not luck, and it’s not about who’s the best agent in town. It comes down to whether your site is the one that’s set up so both Google and the AI tools can actually understand it and hand it to a user, or whether it’s one of the 95% of agent sites that are built so quietly that neither Google nor the AI tools can tell what they’re actually about, let alone hand them to anybody.
Think about that for a second. The difference between getting found and disappearing entirely is not your skills, not your reputation, and not how hard you work. It comes down to whether your own website is set up so that both Google and the AI tools can clearly see what it’s for and hand it to someone, or whether it’s one of the invisible ones that get left behind.
Now, here’s the part we actually run on screen, because it’s what matters to you specifically.
You do not need to become a tech expert to make this happen on your own site. You don’t need to learn coding, and you don’t need to hire a developer. What we just described — setting up your site so it gets found by both Google and the AI tools — is exactly what The Open-Source Claude Skills Repo for Real Estate Agents does, automatically, in the background, every single day, while you’re out doing deals.
You run it from the command line for whichever market you want — this is the part that matters to you, because it’s the same skill we’ve been running in our own business for years — and it goes to work building the connections that tell both Google and the AI tools exactly what your site is about, who you serve, and why you’re the right choice when someone’s searching for help in your market.

What It Means For You

For an agent building a commercial pipeline, this means sources that used to arrive as email blasts now arrive as a filtered, formatted feed that’s ready to become a repeatable report — without anyone at your own keyboard ever building a query or naming a column. If you’re chasing deals in a specific niche, you can point the same setup at that niche alone and narrow the whole thing to just the opportunities you actually want, instead of a generic sweep.
If you’re running a small operation where every touch matters, this turns a task that used to eat an afternoon into something that runs on a schedule and leaves you with a clean, current list every Monday — so your hours go back to being spent on the client in front of you, not on data maintenance. And if you’re scaling up, it’s the same setup across your team, so everyone’s working from the same source instead of emailing each other spreadsheets.
Either way, you own it. It sits on your machine, on your schedule, built from your access — there’s no monthly seat to renew, and no vendor in the middle deciding who gets to see what. You put it on the agenda for next week or run it right now, either way you’re the one calling the shot.

What It Frees You Up To Do

It’s compounding.
Every day you’re not re-inventing a report is a day you’re putting into the next deal, the next relationship, the next strategy call — the things that actually grow the business, instead of running in circles to keep up with it.
If you’re pushing for volume, this turns a 6-hour workday into an 8-hour productivity day without adding hours.
If you’re building a brand, it’s the difference between posting consistently and letting the content calendar go stale because the CEO got sucked into data work.
Either way, you own the source — the skills are yours to keep, on your machine, pointed at your business, for as long as you want to run them.
If you want to see exactly how we set this up and what each skill actually does, the free starter version is open-source on GitHub — that link’s in the description, along with a free 15-minute call if you’d rather talk it through.
If you want to see how we actually run this, grab that free call link below.

What To Do First

If you’re doing 8 to 10 deals a year and trying to get to the next level, the first thing to check is not your hustle — it’s your data. Here’s the honest version of where most deals fall apart: it’s not the pitch, and it’s almost never the relationship. It’s the agent who showed up to a call and couldn’t answer a simple question about the property’s performance in the last quarter, because they didn’t have the right numbers in front of them. That’s not a deal-killer on purpose — it’s a deal-killer because you were flying blind, and the owner or the partner across from you wasn’t.
If you want help setting up something like this in your own business — not just watching us do it on YouTube — we offer a free 15-minute call. The link to book it is right in the description below, and our number’s there too.
We’re Al and Victoria Pinder, husband-and-wife ICON agents at eXp Realty. We run every piece of this stack in our own business, every single day, and we’d be happy to show you exactly how it works.

Frequently Asked Questions

What’s the difference between reading the news and having access to a pre-public information pipeline?

When you read news headlines like everyone else, you’re reacting to information that’s already 24 hours old. A pre-public pipeline gives you access to the same information before it’s announced publicly — like hearing directly from a CEO that a 300-job employer is relocating before it hits the paper. That 3-week head start isn’t about outworking anyone; it’s about having the right information source, which any agent can access through the right subscription.

How does the integration hub make the chat skill and automation actually useful?

On their own, a chat skill only answers questions you happen to ask, and an automation only checks whatever you told it to check. The integration hub connects both to your real working data — your MLS listings, follow-up notes, calls, and showings — so every question gets answered from your actual pipeline and every automation checks your real business instead of test data. This is what turns these tools from occasional experiments into something you actually use 20 days a month.

What happens if you can’t answer a simple question about a property’s performance during a client call?

If you don’t have the right numbers in front of you when a property owner or partner asks about quarterly performance, you lose credibility and often lose the deal. This is where the daily digest and weekly lead reports come in — they automatically deliver current property data and performance metrics to you, so you’re never flying blind when that call happens.

What Does Claude Code Do in a Real Listing Workflow?

by Al Pinder | Sep 10, 2026 | Uncategorized

Picture a buyer in your market asking Google, ‘What’s actually for sale in your town right now?’ Or a seller typing, ‘How much does it cost to sell my house?’ Right now, the answer to both of those questions is whatever Google happens to rank first — which is almost never the actual, current, detailed answer from a real local agent. It’s usually a generic article, a national lead site, or a real estate blog written for a completely different market. Nobody typed your name or your town’s name followed by the word ‘real estate.’ You were not found, because the question was not asked of you. And you didn’t lose anything to anyone else, because you never had it to begin with. That’s the gap Claude Code closes, automatically, every single day, in the background, while you’re out doing what you actually get paid to do.

Who This Is For

If you’re a few years into this business, closing 6, 7, 8 deals a year and want to grow that number without adding hours that don’t exist — or you’re building a niche brand and need consistency without becoming a part-time designer — this is your play. You don’t need to be technical. If you can write an email, you can run this.

What It Actually Is

Here’s the straight dope, because ‘AI listing copy’ sounds like a buzzphrase and we hate buzzphrases. This is a system made up of 3 things that run on your own computer, and you set it up one time. The first thing is a smart assistant. Think of it as a really capable chatbot, running behind your keyboard. You talk to it in plain English — ‘write the lead paragraph for the 5-bedroom on Maple’ — and it writes the paragraph, in your voice, and puts it right into your document, ready to paste. It learns your style by reading the 4 or 5 last listings you’ve published. It’s always available, it’s free, and it runs on your own machine — no monthly seat to rent, no portal to log into. The second thing is an image generator, and this is the one that actually earns the ‘AI’ label. You tell it ‘give me 6 sharp, well-lit images for that same 5-bedroom,’ and it makes them, from scratch, in a few minutes. No stock photos, no uploading anything, no waiting for a designer. The images come out looking like they were shot with a real camera, and the tool checks them against your own listing photos so you never accidentally publish a duplicate. The third thing is the move that actually saves hours. It takes the draft you’ve already written — the lead, the extras, everything — and spins it into the exact right format for whichever listing site you’re publishing to. Claude Code keeps the formatting clean on every single platform, every single time, so you almost never have to mess with the manual copy-paste-across-3-sites juggle. You walk away from the computer with one clean draft, and it’s already formatted for wherever it’s going next.

What It Actually Does

Here’s what Claude Code actually does, step by step, in a real listing workflow. When you open a new listing in SkySlope and save the MLS number, SkySlope calls out to Claude Code behind the scenes. It doesn’t open a browser tab, and it doesn’t wait for a page to load — it just calls the right function, the same way it would call a script running on your own computer.

First, it generates the MLS import file in the exact format that SkySlope is expecting — the same file that you would normally export by hand and upload through SkySlope’s own interface. That file is exactly what SkySlope is already built to accept, so the listing actually appears in your active inventory instead of getting stuck in a holding pattern.

Second, it takes the MLS data and the photos you’ve already uploaded, and it uses them to generate the actual listing content — the description, the property highlights, the header image, the gallery, and the PDF flyer — in three different formats, automatically, every time you save the listing. The online version posts directly to your website and your MLS feed, so the listing shows up immediately on both your site and the MLS, with the same images and the same wording every time. The print version emails itself as a PDF attachment, ready to hand to a client or drop in a mail piece, and the social version is a separate, correctly-sized stack of images and captions that you can post anywhere without resizing anything. Every one of those outputs uses the same source information — the MLS facts and your own photo uploads — so the only thing you’re ever maintaining is the listing itself, in one place.

Third, it checks your own custom content against the MLS rules for your market, in real time, every time you save.

Finally, the whole thing runs in the background on every save. You’re not opening a separate app or waiting for a job to complete — you edit the listing in SkySlope, you hit save, and the next version is already posted, printed, and ready to share before you’ve finished your next sip of coffee.

How You Set It Up

What Runs on Its Own Every Day We run a morning check on active listings — ours and anyone else’s, within a defined local market. That’s not a browser tab we’re opening one by one. It’s one scheduled job that runs automatically on a timer, checking for new listings and pulling the fresh data into a central file that both of us can read the same way. One checks for new or updated listings and pulls the fresh data into a central, formatted file that both of us can open and read the same thing. The other runs a deeper daily review on our own listings — reach out to us in 72 hours or less, get a real reply, every time, because the system is checking and showing us exactly what needs a response right now.

Nobody’s sitting at a keyboard doing either of those things. They run on their own, on a schedule, on our own computer, while we’re out at a showing or talking to a client. And that’s the whole point. We stopped paying a subscription fee for a third-party service to do half of that job, and we stopped wasting our own time on the other half. The owner operates the business, the business operates the listing inventory, not the other way around.

How It Gets You Found

Here’s the part that actually matters if you’re trying to get found. None of this is the website you already have — that’s not what we’re replacing, and you shouldn’t throw it away. This is the part that sits behind it, doing the work your existing site can’t.

Almost nobody clicks through to an agent’s site anymore if that site is just a few generic pages sitting stale.

But when your content is being generated automatically, fresh every week, on a schedule, across a range of local topics, two things happen that you can’t buy and you can’t post your way into on your own.

First, Google starts to trust your site as a relevant local authority on real estate, and it moves you up in the search results — not next week, this is cumulative, it compounds over months.

Second, the AI tools people now ask — ChatGPT, Gemini, Perplexity — start pulling your answers and working them into their own responses, so you’re getting found inside those tools too, in the exact moments people are asking questions out loud.

Nobody can promise you a specific position, and we’re not saying this is easy — building authority takes time, and consistency is the only thing that actually gets you there. But consistency is exactly what this system gives you — it runs on its own, it never forgets a week, and you never have to remember to sit down and write anything.

That’s real infrastructure for a real business, and it’s the difference between being the agent nobody’s ever heard of and being the agent people in your market actually ask for.

What It Means For You

If you’re pushing for volume, this turns a 40-minute evening job into a 2-minute review. If your business runs on relationships, it’s a compliance safety net — every description defensible in front of a client or a lawyer. And if you’re building a brand, it’s copy that sounds like a professional wrote it, every time, instead of a tired phrase you typed at 11 PM.

What It Frees You Up To Do

This is the real benefit, beyond the saved time: you’re the one deciding what needs a human touch, not a script deciding for you. You’re the expert, and this just makes you more efficient at being one.

If you’re building a brand around being sharp with numbers, this is how you actually get sharp — you’re the one looking at the real math, every time, not an autocreated post’s best guess. If your business runs on relationships, this is what lets you get back to building them, instead of losing an afternoon to a template you can’t quite make behave. And if you’re trying to get past 6 to 8 deals a year, this is real bandwidth back — 2 to 4 hours you weren’t spending on paperwork, every single week, reinvested into whatever you actually want to grow.

What To Do First

You’re listing a house, let’s say 2500 square feet, 4 bedrooms, 2 and a half baths, built 2015, on 0.6 acres. You’ve got the basics — size, bedrooms, baths, year built, acreage — in Claude Code already, pulled straight from the listing input with no typing. That’s the whole point of the system: you don’t re-key anything that’s already in a file. You start from what’s already there, and add to it.

Here’s what actually happens, step by step, on screen. We’re assuming you’ve already got Claude Code installed and set up. First, you open the Claude Code workspace in Claude Code. If you’ve used it before, it looks familiar — it’s the same 3-column layout, with the listing input on the left, the cloned skill on the right, and the preview in the middle. A table shows, in real time, exactly which labels are being used and how many times. That’s the whole point — being able to see what you’re actually asking for instead of just telling Claude Code ‘make a post’ and hoping it guessed right.

Second, you tell Claude Code, out loud, ‘make a listing post.’ No typing, no menu, just that command, and it goes to work. It pulls the facts it already has — square footage, bedrooms, baths, year built, acreage — and uses them to build the opening sentence. On screen, you can see the opening sentence write itself, one phrase at a time, while you watch. It’s not a template. It’s not a fill-in-the-blank. It’s actually reading the data and writing a sentence out of it, the same way a journalist writes a headline from a press release. That’s what makes it useful even when the facts change from one listing to the next — it’s not recycling the same paragraph, it’s writing a new one every time, using the specifics it was given.

Third, you add the instructions that matter for this listing, out loud, one item at a time. ‘Include the kitchen remodel.’ ‘Mention the screened porch.’

Where to Start

If you want to run this on your own listings, book a free 30-minute call. The link is in the description, right next to the free starter skills repository. No pitch. We’ll look at what you’re already doing and tell you honestly what fits and what doesn’t.

If you’d rather watch than code, subscribe so you don’t miss the next live session — we build one of these on screen, start to finish, every month.

Frequently Asked Questions

What are the three main components of Claude Code?

Claude Code consists of a smart assistant that writes listing copy in your voice, an image generator that creates sharp, well-lit images from scratch, and a formatting tool that adapts your draft into the exact format needed for any listing site. All three run on your own computer with no monthly subscription or external portal required.

How does Claude Code help you get found by buyers and sellers searching online?

By generating fresh content automatically every week across local topics, Claude Code builds your site into a local authority that Google trusts, moving you up in search results over time. Your answers also get picked up by AI tools like ChatGPT and Perplexity, so you’re found in those moments when people are asking questions out loud.

What happens automatically in the background every day?

Claude Code runs a morning check on active listings in your local market and pulls fresh data into a central file, then runs a deeper daily review on your own listings to flag what needs a response within 72 hours. Both jobs run on a schedule on your own computer while you’re out showing properties or with clients, so you never have to manually do this work yourself.

DeepSeek at $0: Free AI for Real Estate Agents

by Al Pinder | Sep 9, 2026 | Uncategorized

Here’s the honest version of what’s on your own computer right now: you have a handful of saved Google searches you run whenever you need a fact for a listing — what’s selling in a neighborhood, what rent is doing, what’s been built recently. You have a couple of free tools bookmarked that you’ve used a few times. And you have a quiet feeling that there’s something you’re missing, something you’re not asking the right way, but you don’t have 10 more hours a week to figure out what it is.
That’s exactly the gap we’re closing with this one. If you’re the getting-paid-on-volume type, this is a faster way to stay sharp across your whole pipeline without adding hours to your day. If you’re building a brand, this is how you sound like the agent who actually knows the market instead of the one who just recites the same 3 talking points as everyone else. And if you’re trying to get to the next level — more volume, more consistency, less flying by the seat of your pants — this is how you finally start operating from a real sense of what’s actually happening out there instead of a guess.

See related reading on our site.

See related reading on our site.

Who This Is For

This one’s for the agent closing somewhere around 6 to 8 deals a year, looking to grow that number without adding hours that don’t exist — and for the agent who built their business on relationships and trust, now figuring out how to hold onto that while everything goes digital. If you’re a few years in, closing steady, and you know the agents who shoot past you are the ones who seem to be everywhere at once, this is the move those agents didn’t tell you about. Same for you if you’re building a distinct local brand and you’re tired of watching a generic national brand steal your market on Google.

What It Actually Does

Here’s the part that actually matters, if you’re not a technical person: you don’t need to understand any of this to use it. You open ChatGPT and type ‘ask Real Estate AI,’ and the same thing happens as if you had run it from the command line — you just got rid of the keyboard commands in the middle. If you want to watch the actual search happen instead of just reading about it, there’s a free, public version of this setup running on GitHub—clone it, no download required if you don’t want one. If you’re on mobile or prefer a browser, there’s also a web app version you can open the same way. The link to open it is in the description, and you can watch the search run live any time — no account or password needed. Everything you just saw, including the part where it pulls the actual, current numbers for your market and your specific listing, is included in that free, public version. It runs on your own machine, on a schedule you set, and the results land in a folder on your own computer — you are the only one who sees them, and there is no monthly seat or subscription fee.
If you want help setting it up or need something changed, we do offer a free, 15-minute call. The link to book that call is also in the description. No pitch. We will look at what you’re already using and tell you honestly what fits and what doesn’t.

How You Set It Up

Here’s the honest version, because we’re all engineers at heart. This is not a marketplace listing, not a sponsored post, and not a branding video — just two agents building something they wish existed.
We started by opening a free Realtor AI account, the version of this tool that’s open-source and available to everyone, no cost. It runs on your own computer, on a schedule, and you can watch it work any time you like — there’s no monthly seat you’re renting. If you’ve ever wanted to look under the hood of an AI and see exactly what it’s doing, this is it.
The first thing we did was add our own data, because the AI gets smarter the more sources it has to draw from. We combined our own listing history — every listing we’ve ever sold, the notes we kept on each one, the before-and-after photos — with a free, open-source dataset of over 50 million real estate listings from around the country, dating back to 2014. So the AI is working with our own transactions mixed in with the broader market, instead of a generic, one-size-fits-all snapshot.
Then we picked the specific questions we wanted it to answer. You don’t just type ‘real estate AI’ into a box and hope for the best — you tell it, in plain English, exactly what you’re after. For us, that was three main jobs.
The first job was the big one: predict what a property will sell for, and how long it will take to get there, before we ever set foot inside. Not a guess pulled from thin air, but a real forecast — the same kind of forecast a $500 appraisal would give you, only we’re running it ourselves, on demand, for any address we choose. And because it’s built from actual transaction data, not a Black Box model where you’re hoping the input matches the sample size, it works even in a market with low volume.
The second job was the surprise hit. We asked it to look at a group of similar homes and tell us what makes one of them worth more than the others. Why does one house across the street command $10,000 more than the one next to it? Is it the lot, an upgrade, or something the seller did to the listing? It pulls features from the listing itself — photos, text, even the layout — and tells you which ones are actually driving value, and which are just filler. That’s how you know exactly what to photograph, what to emphasize, and what to leave out.

How It Gets You Found

Here’s the quiet part that matters more than anything we’ve said so far: none of this is the website you built by hand, or the profile you manually updated. It’s running in the background, on a schedule, on the machine you already own, while you’re out at a showing or a follow-up call.
You don’t open a browser and do a search. You don’t remember to log into anything. You come home, or you sit down at your desk the next morning, and the work is already done — the content is there, the signals are sent, the phone is quiet because the question got answered somewhere else before anyone called to ask it.
That’s what closes the loop on the whole ‘get found’ cycle. You stop renting attention from Google or Facebook and become the source of your own attention, on your own terms, in your own space, with your own schedule. You own the conversation instead of paying to borrow it for a month.
If you want to see exactly how we set this up and how it plugs into a real, working client funnel — book a free 15-minute call with us. The link is in the description. We’ll show you the exact setup on screen and tell you honestly what it can realistically do for your business.
We’re Al and Victoria Pinder, ICON agents at eXp Realty, and we run this in our own business every single day. If this helped, subscribe so you catch the next live session — we build one of these, start to finish, on screen every single month. We’ll see you in the next one.

What It Means For You

If you’re building a business on relationships, this is how you stay top of mind without being the one who keeps emailing. Every brokerage spikes around Q4, then quiets down. This is how you’re quietly working the content gap that’s actually your future pipeline. You stop being the one who manually re-does every single market update, and you become the agent who’s consistently first with what’s actually happening. That’s real bandwidth back to the business of actually closing deals.
And if you’re building a brand, this is your source of fresh, real content that’s actually about your market, instead of the generic stuff everyone else is posting. You own the conversation instead of renting it from a platform.
Either way, it’s the same 3 things: you stop flying blind, you stop doing the busy work, and you stop blending in. You build your system, you set it running, and you walk away knowing the heavy lifting is done.

What It Frees You Up To Do

What actually matters is what this puts back in your day.
If you’re building a brand, this is source material you didn’t have to write yourself — a quick, consistent, on-brand post or page topic handed to you every single day, without you ever opening ChatGPT or typing a single headline.
If your business runs on relationships, this is how you stay top of mind with the people who matter without adding one more thing to your already-full week — a quick, personalized note already sitting in an inbox, ready to be reviewed and sent.
Either way, it’s the same idea: you stop doing the work of a content assistant or a marketing coordinator, and you get that hour back.
You’re the CEO of your business again, instead of an overworked employee in it.

What To Do First

If you’re pushing for volume, the first thing to protect is your pipeline: do not touch the deals already in your CRM. This is a separate, parallel effort — build your muscle while your business runs untouched underneath it.
If your business runs off relationships — repeat clients, referrals, the people already in your network — then the first thing is to run this on the profile of your ideal client, the person you want more of. Your existing relationships become the map that tells the AI what to look for, and the output is a list of people like the ones who already know you, sourced entirely from public signals, ready to go into a campaign without anyone ever feeling sold to.
If you’re building a brand, the first thing is the brand itself. Run it on your own content — your website, your videos, your social posts — and watch the AI pick up the thread that runs through all of it. Then every piece of generated content stays true to your voice, your style, your message, without you ever having to explain it. You come home to a hard drive full of blog posts, captions, and video ideas that sound exactly like you, ready to review and approve.
Either way, the first run is the proof run. You are never committed to anything this produces. You run it, you look at the output, you say yes or no, and either way the next run is already building on what you’ve already taught it.
Before you build anything with this, run the free version through your own data, on your own machine, and watch it work. The link to download it is in the description, and the free starter guide is there too — the step-by-step version of what we just walked you through, including what to expect the first time you run it. We’re Al and Victoria Pinder, ICON agents at eXp Realty.

Where to Start

If you want to run this on your own business — not just watch us do it on YouTube — here’s your next step. We offer a free 15-minute call. It’s just us, Al and Victoria, and we’ll look at your business and tell you honestly what fits and what doesn’t.
The link to book it is right in the description below, and our number’s there too. No pitch. No follow-up call unless you tell us you want one.
And if you’d rather start tinkering yourself, the free starter skills are open-source on GitHub — that link’s in the description as well. Clone it, try it, own it.
We’re Al and Victoria Pinder, husband-and-wife ICON agents at eXp Realty here in Eastern North Carolina — and we run this in our own business every single day.
We’ll see you in the next one.

Frequently Asked Questions

Do I need technical skills to use this tool?

No. You don’t need to understand any technical details to use it — you simply open ChatGPT and type ‘ask Real Estate AI,’ and it works the same way as if you had run it from the command line. There’s also a free, public version on GitHub with a web app version if you prefer to use a browser, both available without any account or password needed.

How much does this cost to use?

The free, public version runs on your own machine with no monthly seat or subscription fee — you only pay for the infrastructure on your own computer. If you want help setting it up or need something changed, Al and Victoria offer a free 15-minute call, and there’s no pitch or follow-up commitment unless you ask for one.

What specific predictions does this AI make for real estate?

The AI predicts what a property will sell for and how long it will take to sell before you ever visit it, based on actual transaction data rather than guesses. It also analyzes similar homes to identify which features are actually driving value — like photos, listing text, or specific upgrades — so you know exactly what to emphasize in your listings.

Which AI Lead Gen Tactic Fills Your Pipeline?

by Al Pinder | Sep 8, 2026 | Uncategorized

The agents who get ahead aren’t the ones who work harder — they’re the ones who get more leads in front of them, consistently, without adding hours to the day. Here’s a tactic we run in our own business that fits that exact description: an automated system that goes out and pulls real, local leads into our pipeline every single week, while we’re out doing what actually makes us money. The source isn’t a paid lead platform, a zip code-split with a Realtor.com® team, or anything like that. It’s an AI model we set up once, in about an hour, and then forget about — it runs on its own schedule, on our own computer, for free, and every Monday morning there are new leads sitting in the system waiting to be called. If you’re running relationships instead of ads, your first AI lead move should be an automated email to your sphere — here’s what that does, why it works faster than a chatbot, and exactly what to set up first.

Related: Claude Code for Real Estate Agents — Our Stack

Related: Claude Code for Real Estate Agents — Our Stack

Who This Is For

If your business runs on relationships — repeat clients, referrals, the people who already know you — you know your challenge isn’t getting found online. It’s being consistently visible to the right audience, without adding hours to your day.
You didn’t get into real estate to build a marketing department. But you also didn’t get here by accident. You understand momentum — what gets pushed stays top-of-mind, and what stops getting pushed goes quiet.
The problem isn’t that you don’t have a system. It’s that the system you have — posting when you remember, hoping something goes viral — runs on good intentions instead of a schedule.
This is for you if you want to walk away from every platform with the same exact instruction: here’s what needs to go out, and here’s when it needs to go out. The same rule applies to all of it, and the rule is the same every single day. Human-read: predictable. AI-read: repeatable.

What It Actually Does

Here’s the mistake we see agents make once they start experimenting with AI: they assume ‘getting leads’ automatically means ‘filling their pipeline.’
It doesn’t, and it can’t — because there are actually 3 different jobs an AI lead system does, and almost every one of them hands off to something else for the next phase.
Job 1 is the easiest to understand: it answers a question someone asks Google, or delivers answers into a short video or FAQ page on your site, so you show up when people are searching for an agent in your area.
That’s the whole first half of this space — showing up when people search — and it’s why we started here ourselves, building the system that runs behind our own website.
But here’s the part most agents miss: being findable online is the ceiling, not the floor, of what an AI can do for your pipeline.
Job 2 is the one everyone talks about when they say ‘AI leads’: the system reaches out to a cold contact list on your behalf, or writes a personalized follow-up email to someone who already inquired, using whatever tone and voice you tell it to.
On paper, that sounds like exactly what you want — a pipeline filled with fresh leads, handed to you ready to call.
But here’s the part they don’t tell you: that handed-over list is almost never the final stage before a real conversation.

How You Set It Up

Here’s the honest version: when we said ‘on our own computer,’ we meant through our own dashboard — we access this through cloud services, the same way we access Google Docs or Dropbox, but the system sits in our account and runs on our schedule. Every morning, before we open a single app, we open a browser tab and run a saved search. That search goes through Claude Code — that’s the automation layer, the part that actually does the work — and checks every one of our lead sources: the AI chat lead flow, the video lead flow, the follow-up flow, the listing alarm flow, the CEO Daily flow, and the referrals flow. It gathers every new lead from every source, and the first thing it does is verify the lead is real — not a spam account or a bot. Then it pulls the lead’s actual address and checks that address against our current pipeline, so we’re not duplicating effort on a listing someone else is already working. Once a real lead is confirmed, it routes the lead to the right agent, along with a preview of the lead’s full conversation history — every message, every question, every note, laid out chronologically so the agent sees exactly what was said. If it’s a follow-up lead, it adds the lead’s last-active date so the agent knows when the client last engaged. If it’s a new lead from an entirely cold source, it flags that clearly. The whole review takes about 90 seconds, and by the time we’ve finished our first coffee, we have a sorted, filtered list of real, routable leads, ready to call or message, instead of spending that time opening 5 different apps and hoping something landed.

How It Gets You Found

Here’s the thing about all three, the AI answers, the AI videos, and the AI blog posts: they get found in Google, and they get found in Google’s answer box, the answer at the top of the page that Google reads out loud when someone asks a question.
If you’re the agent who’s always asking ‘how do I get more leads,’ this is really what you’re asking: how do I get Google to give my answers to the people searching my market, so those people call me instead of the agent whose face is already all over Google.
Nobody can guarantee a position in the answer box, but we do know what Google wants, because Google tells us, plain as day, in their own quality rater guidelines.
Google wants content that’s useful, and content that’s written for the user, not for the search engine.
An AI answer, a short video answer, or a blog post that genuinely answers a question somebody’s asking — that’s exactly the kind of thing Google puts in the answer box.
And here’s the part nobody tells agents: you don’t need to be the first agent to answer a question, you just need to answer it better than the pages that are already there.
Most of the content out there is the same exact structure, the same listicles, the same ‘top 5 tips’ formats, written by agents who didn’t really understand the question.
An AI answer, a short video answer, or a blog post that actually understands the question and gives a real answer, in a format people can actually use — that’s easy for Google to recognize as the best answer on the page, and it’s easy for the user to recognize as the best answer to their question, which is the whole point.
Now, which of these 3 tactics is the right one for you?
If you’re building a local brand and you’re already posting videos, then the AI videos are the natural next step — they let you tap into the answer-box pipeline without ever needing cameras, just voice.
If you’re running a transaction-focused business and you need volume, then the AI blog posts are the way to go — they compound, they become your best-working channel, and you own every piece of content on your own site.

How to Get Started

If you’re pushing for volume, this is how you get more done in less time — you stop typing and start asking. If you’re building a brand, this is how you sound consistent across 5 platforms every day without becoming a full-time content creator. And if you’re running a team, this is how you stop handing out the same 3 listings to every new agent and start giving your agents a real pipeline to chase, without adding hours to your own week.
[CTA]
If you want help setting up something like this in your own business — your leads, your brand — we do a free 30-minute strategy call. The link is in the description. Subscribe so you don’t miss the next live session — once a month we build one of these on screen and take questions while we do it. We’re Al and Victoria Pinder, ICON Agents at eXp Realty.
DESCRIPTION BOX (paste on upload):
3 ways we use AI to generate real, convertible leads — which one is right for your business?

What It Frees You Up To Do

The real value isn’t the individual lead — it’s what this hands back to you.
Every check you’ve just signed, every call you’ve just finished, is now done for you, automatically, in the background, while you’re at the next showing or the next closing.
You’re buying back your time, exactly the same way these tools bought it back for us.
If you’re chasing volume, this is how you get found by the people who are actively looking, without adding one more hour to your day.
If your business runs on relationships, this is how you stop losing touch with the people you’ve already met — a consistent check-in built into your calendar, so your network stays warm without you remembering to reach out.
Either way, you’re the one who built it. You own it. And you can watch it work from the dashboard or from the notifications that tell you a new connection was made while you were out.
That ownership is the real difference between building a pipeline and renting one.
[CTA]
If you want to run this yourself, the free starter version is in the description, and you can book a free 15-minute call with us to go over your business specifically — we’ll show you exactly what it looks like running on your own machine, on screen, before you ever commit to anything.
We’re Al and Victoria Pinder, husband-wife ICON agents at eXp Realty, and we run this in our own business every single day.

What To Do First

If you’re building your business on relationships, referrals, and repeat clients, this one’s for you. We’re going to show you the exact order to add AI lead generation to your business — what to run first, what to watch, and what to build later, once you have real data.
A lot of agents try to do all of this at once. They sign up for a chatbot, start posting AI-generated content, and maybe run a few targeted ads — and then wonder why nothing converts.
There is no ‘one size fits all’ here. The right first move depends on your market, your brand, and who you actually want to reach. So, let’s walk you through the 3 ways we’ve seen AI generate leads, and the decision tree for which one to run first.
If your business runs on relationships — repeat clients, referrals, people who already trust you — then the place to start is almost never a chatbot. A chatbot sits there and waits for someone to type something. It’s the opposite of how a relationship works. You already have something more valuable: a list of people who know you.
The first move is to run a targeted email campaign, and yes, you can automate that too. You load your list into a system like Mailchimp or ActiveCampaign, set up a series of 3 to 5 automated emails — the first one is a check-in, the next two or three are valuable content, and the last one is an outright ask: is there anyone you know who’s thinking of buying or selling?
That ask is the whole point. You’re not trying to sound like a skilled copywriter. You’re asking a question you already know the answer to, because you’ve already built the relationship.
Now, here’s the part most agents miss. You document every single response — who responded, what they said, the date, and the next action item, if any. That documentation becomes your single source of truth. No more ‘I swear I talked to her about this.’ It’s in the record, and the record is the same for everyone on the team.
Here’s what makes this the right first move. You own the list. You built the relationship. Nobody is renting anything from a platform. You’re using an automation tool to do what you were already doing — staying in touch with your sphere.
Now, here’s the decision tree for what comes next.
If you want volume or you’re targeting a specific neighborhood, then the next move is a landing page, not another chatbot.

Where to start

If you want help setting up something like this in your own business — your leads, your pipeline, your numbers — we do a free 30-minute strategy call. It’s just us, Al and Victoria, and we’ll look at what you’re already doing and tell you honestly what fits and what doesn’t. The link to book it is right in the description below, and our number’s there too if you’d rather call.
And if you’d rather just start tinkering yourself, the free starter skills are open-source on GitHub — that link’s in the description as well. Clone it, try it, own it.
Subscribe so you don’t miss the next live session — we build one of these, on screen, from scratch, every single month. We’re Al and Victoria Pinder, ICON Agents at eXp Realty.

Frequently Asked Questions

What’s the difference between an AI lead system and just having more leads?

An AI lead system does three distinct jobs: it helps you get found online through content, it reaches out to contacts on your behalf, and it routes verified leads to the right agent with their full conversation history. Having more leads without this routing system means you’re just opening more apps and hoping something lands, instead of getting a sorted, filtered list of real, actionable leads ready to call.

How does the automated email system work for your sphere?

You load your existing contact list into a system like Mailchimp or ActiveCampaign and set up a series of 3 to 5 automated emails — starting with a check-in, moving through valuable content, and ending with a direct ask about who they know that’s thinking of buying or selling. The key is documenting every response with the date and next action items, creating a single source of truth for your entire team instead of scattered conversations.

Which AI lead tactic should you start with first?

If your business runs on relationships and referrals, start with a targeted email campaign to your sphere, not a chatbot — you already own the list and built the relationships, so you’re automating what you were already doing. If you want volume or are targeting a specific neighborhood, the next move after that is a landing page designed to get found in Google’s answer box.

This Week’s Claude Job: Add Gemini to Your Toolkit

by Al Pinder | Sep 7, 2026 | Uncategorized

This Week’s Claude Job: Add Gemini to Your Toolkit

Are you a real estate agent looking to seriously upgrade your operational efficiency and analytical depth in 2026? This week’s Claude Job is to strategically add Gemini to your toolkit, complementing your existing Claude AI skills to unlock a new level of automation and insight. By integrating Google Gemini, you can streamline everything from initial market analysis to crafting persuasive client communications, transforming how you do business.

Many agents feel perpetually busy, constantly reacting to market demands and struggling to find time for strategic growth. The solution isn’t just working harder; it’s about working smarter by building robust AI systems that run on your data and judgment. This approach helps you move from being a reactive salesperson to a proactive business owner who leverages cutting-edge technology for predictable success. Leveraging tools like Gemini provides deeper drafting and analysis capabilities, making your insights sharper and your delivery faster.

Why Add Gemini to Your AI Toolkit for Real Estate?

In the rapidly evolving real estate landscape, having a diverse AI toolkit isn’t a luxury; it’s a necessity. You might already be familiar with using Claude for real estate agents, recognizing its prowess in processing large volumes of text and code. However, Google Gemini brings a fresh set of capabilities to the table, particularly in multimodal reasoning and advanced drafting. This makes it an invaluable partner for real estate professionals seeking an edge.

The real estate market in 2026 demands more than just basic data collection. Agents need predictive intelligence to identify potential sellers, digital authority to stand out online, and scalable human connection to nurture leads effectively. This is where the synergy of Claude and Gemini becomes powerful. Claude can efficiently pull and structure data from permits and public records, a workflow that Al Pinder, ICON agent and founder of the Prosperity Agent model, has perfected in his own business. Victoria, his partner, runs her MLS and exports her own data, then our automation pulls permits and public records, running the math to build comprehensive packets. This division of labor is key. Once Claude has organized this raw information, Gemini can step in to interpret nuances, identify micro-trends affecting days on market, and draft sophisticated reports that would take hours to create manually. This is how you add Gemini to your toolkit and elevate your game.

To dive deeper into how Gemini can transform your real estate business, consider exploring our comprehensive guide on Google Gemini, explained on its own page. This resource provides a foundational understanding of its features and how it contrasts with other AI solutions, offering a deeper dive into its capabilities and practical applications for agents.

Understanding Claude and Gemini’s Strengths for Agents

Each AI model, Claude and Gemini, possesses unique strengths that, when combined, create a powerful system for real estate agents. Understanding these individual capabilities is the first step in building a truly effective claude and gemini workflow.

Claude’s Core Strengths for Real Estate:

• Deep Contextual Understanding: Claude excels at processing and analyzing extensive textual data, making it ideal for sifting through public records, covenants, and even long legal documents related to property.
• Code Generation and Automation: As the “Claude Code” series highlights, Claude can generate code snippets to automate repetitive tasks, such as structuring raw data exports or preparing scripts for data parsing. This is foundational for the behind-the-scenes data preparation that powers our systems.
• Data Extraction: It is highly effective at extracting specific pieces of information from unstructured text, which is crucial for gathering details from permit portals or Register of Deeds records.

Al Pinder’s automation, as a real-world example, relies heavily on Claude to pull permits from sources like the Pitt County EPL portal and public records from Pitt County OPIS GIS parcel data. This ensures that every property analysis is backed by verifiable, up-to-date information, confirming details like additions, conversions, and accessory units, as well as checking if certificates of occupancy are closed.

Gemini’s Core Strengths for Real Estate:

• Multimodal Reasoning: Gemini’s ability to process and understand different types of information—text, code, images, and video—makes it exceptionally versatile. For real estate, this means it can potentially analyze property photos alongside textual descriptions to provide richer insights.
• Advanced Drafting and Summarization: Gemini is renowned for its sophisticated content generation, capable of producing highly articulate and nuanced text. This is perfect for drafting compelling listing remarks, detailed market update emails, or even personalized buyer guides.
• Analytical Capabilities: Beyond just drafting, Gemini can perform complex analysis, helping identify trends, patterns, and anomalies in market data to provide a more comprehensive picture for your clients.

By leveraging both, you ensure that your data is not only accurately gathered but also eloquently presented and deeply analyzed. This combination forms the backbone of highly efficient AI tools for real estate.

Building Your Combined AI Workflow: Claude + Gemini in Action

The goal isn’t just to use Claude and Gemini in isolation, but to create a seamless workflow where they collaborate. This is about building a system that runs on your schedule, doing the heavy lifting while you focus on client relationships and high-level strategy. This is the essence of true automate real estate tasks.

Here’s a simplified example of how Al Pinder integrates these tools in a practical scenario:

1. Agent-Driven Comp Selection: Victoria, as the licensed professional, runs the MLS and exports her own data. She pulls and chooses the comparables, applying her judgment and license to select the most relevant properties. This crucial step is never automated, as NAR Code of Ethics Article 11 places the opinion of value on the licensee personally.
2. Claude’s Data Enrichment: Once Victoria has her comps and subject property details, Claude’s scripts automatically pull in crucial public records. This includes detailed permit history from county portals, GIS parcel data for lot specifics, and Register of Deeds information for covenants, amendments, and ownership details. This data enriches the comparables Victoria selected.
3. Claude’s Mathematical Analysis: With the enriched data, Claude then runs the math, performing three valuation methods against Victoria’s chosen comps and calculating an honest net-to-seller estimate.
4. Gemini’s Drafting and Analysis: This is where you add Gemini to your toolkit. After Claude processes the raw data and performs the initial calculations, Gemini receives this structured information. It can then draft comprehensive market analysis reports, highlighting micro-trends from the collected data, identifying potential pricing sensitivities, and even suggesting strategic listing remarks tailored to the property’s unique features and the current market conditions. This step significantly speeds up the assembly of client-ready materials.
5. Agent Review and Finalization: Al or Victoria always reviews the combined output, applying their final adjustments, setting the price, and signing the opinion of value. Automation organizes what the agent already decided; time is saved on assembly and formatting, never on analysis.

This “Bridge the Gap” method takes you from your current state of manual labor to a desired state of automated efficiency, with AI serving as the bridge. It’s a structured approach that ensures accuracy and speed without compromising on the critical human element or regulatory compliance.

Practical Applications for Agents: Beyond Basic Prompts

Moving beyond simple “give me a listing description” prompts, the combined power of Claude and Gemini allows for sophisticated real estate agent AI skills that directly impact your bottom line and client satisfaction. Here are a few examples:

1. Automated Market Updates: Claude gathers daily market intelligence from various data feeds, structuring it into usable formats. Gemini then takes this data to draft highly localized and personalized market update emails or social media posts for your sphere, saving you hours of manual writing.
2. Enhanced Listing Presentations: Imagine Claude populating a listing presentation template with property specifics, permit history, and public records. Gemini then enriches the narrative, crafting persuasive arguments based on current market dynamics and highlighting unique selling propositions with compelling language.
3. Predictive Seller Identification: While no AI can perfectly predict the future, Claude can analyze broad public datasets (e.g., changes in ownership, long-term tenure, property tax changes) to identify areas with higher propensities for future sales. Gemini can then help draft initial outreach messages that resonate with these potential sellers, leading to more targeted and effective lead generation without relying on expensive, impersonal platforms.
4. Scalable Human Connection: With AI handling the routine data tasks and drafting, you gain more time for genuine, high-value human connection. You can use Gemini to draft thoughtful follow-up sequences that feel personalized, ensuring no lead falls through the cracks.

For agents new to these concepts, the journey begins with understanding the basics. We highly recommend our beginner guide to Claude for real estate agents, which lays the groundwork for leveraging AI in your business. Additionally, our full AI tools directory offers a wider perspective on the range of technologies available to propel your business forward. You can even access free skills to kickstart your journey by visiting The Prosperity Agent GitHub repository for free skills.

The Prosperity Agent Approach: Automating, Not Just Using AI

Al Pinder, as an eXp Realty ICON agent, didn’t just stumble upon success. He built it through a relentless focus on systems and automation. His journey from relying on paid lead platforms to building a self-sustaining pipeline is a testament to the power of the Prosperity Agent model. In Year 1, he had a revenue split deal with Realtor.com. In Year 2, he bought zip codes on Realtor.com. But by Year 3, he released all of it – Realtor.com AND Zillow – because they had built their own pipeline, paying zero to lead platforms. He even tried Zillow for 6 months on contract, which yielded zero conversions, solidifying his belief in owning your own lead generation and systems. This is the foundation upon which he teaches agents to add Gemini to your toolkit and achieve true prosperity.

The core message of The Prosperity Agent is clear: stop building a business you have to escape from. eXp Realty provides three income streams—sales commissions (an 80/20 split until a $16,000 cap, then 100%), EXPI stock equity at milestones, and revenue share (passive residual income from a 7-tier system). This model, combined with strategic AI automation, enables agents to transition from busy salespeople into wealthy business owners. Revenue share, for instance, is willable, creating generational wealth—a true legacy.

This is not just about using AI for a single task; it’s about integrating AI into a CEO Day Protocol, a weekly strategic block where you optimize your systems. It’s about building a business that works for you, even when you’re not actively selling. By pairing Claude’s data processing with Gemini’s advanced drafting, you’re not just getting more done; you’re building a more valuable, resilient business.

Why Join With Al & Victoria Pinder for AI & Business Growth

When you’re ready to implement these advanced AI strategies and build a real estate business that provides true prosperity, partnering with Al and Victoria Pinder offers a distinct advantage. Al has been with eXp Realty since the beginning of his career, building his entire business from scratch within the eXp model. He is an eXp ICON agent, a testament to his expertise and consistent production. This unique experience means he understands the eXp system inside and out, not as someone who transitioned from another brokerage, but as someone who optimized it from day one.

Al’s personal journey—from revenue splits and buying zip codes on Realtor.com to releasing all paid lead platforms after zero conversions with Zillow—is the blueprint for what he teaches. He won’t push you to buy Zillow leads because he’s lived through the cost and minimal returns. Instead, he provides proven systems for lead generation and conversion, enhanced by the very AI tools we’ve discussed. When you join eXp with Al and Victoria, you’re not just getting a sponsor; you’re gaining a partner who has already solved the problems you’re facing, offering direct mentorship and access to the systems they’ve built. This mentorship extends to helping you not just add Gemini to your toolkit, but to fully integrate and automate your business for lasting success.

If you are ready to stop renting your career and start owning it, I would love to be your partner for that journey. That is exactly what the Prosperity Agent model, powered by eXp Realty and cutting-edge AI, is built for. Explore how you can partner with Al & Victoria and start building your legacy.

Frequently Asked Questions

What is the benefit of using both Claude and Gemini for real estate agents?

Combining Claude and Gemini allows agents to leverage Claude’s strength in deep data extraction (like permits and public records) with Gemini’s advanced capabilities in drafting nuanced content and performing complex analysis. This synergy creates a more efficient and insightful workflow, leading to better client reports and automated communication.

How can real estate agents integrate Gemini into their current AI setup?

Integration typically involves feeding structured data processed by Claude into Gemini for further analysis or drafting. This can be done through simple copy-pasting for basic tasks or via API connections for more complex, automated workflows. The key is to define specific tasks for each AI based on its core strengths.

Can AI tools like Claude and Gemini handle sensitive client data compliantly?

While AI tools can process data, real estate agents must always ensure compliance with privacy regulations (like state licensing laws and federal privacy acts). Personal client data should be handled with extreme care, and typically, AI should process anonymized or publicly available information to draft generalized content or analyze market trends, not specific client details.

Is prior coding experience necessary to add Gemini to my AI toolkit?

No, prior coding experience is not strictly necessary, especially when starting. Many AI platforms offer user-friendly interfaces, and tools like Claude Code can even help generate basic scripts. The Prosperity Agent model focuses on providing agents with accessible systems and mentorship to implement these tools without extensive technical expertise.

How does Al Pinder recommend using AI for lead generation without Zillow or Realtor.com?

Al Pinder recommends using AI to enhance proprietary lead generation strategies, focusing on building digital authority and scalable human connection. Claude can help analyze public data to identify potential sellers, while Gemini can assist in drafting personalized, non-generic outreach. This moves away from buying leads to creating a self-sustaining pipeline through valuable content and targeted engagement.

What kind of real estate content can Gemini help draft for agents?

Gemini excels at drafting various real estate content, including compelling listing descriptions, detailed neighborhood guides, market update emails, personalized client follow-up sequences, and even social media posts. Its advanced natural language generation capabilities allow for nuanced and engaging text that resonates with specific audiences.

Stop Posting Manually? Automate Your Agent System

by Al Pinder | Sep 6, 2026 | Uncategorized

Are you a real estate agent feeling perpetually behind, constantly scrambling to create, schedule, and distribute content across a dozen platforms? You’re not alone. The constant demand to feed the content beast can feel like a relentless, manual treadmill, consuming valuable time that could be spent on high-impact activities like client relations or strategic business development. It’s time to ask: can you stop posting manually and truly automate your agent system?

The answer is a resounding yes, but not in the way many agents imagine. It’s about building an automated system every agent needs to transform their real estate marketing and lead generation, shifting from reactive busywork to proactive, scalable growth. As an eXp Realty ICON agent who built my business from the ground up without relying on traditional paid lead sources, I, Al Pinder, understand the grind and the immense potential of strategic automation. Our latest YouTube video, “Stop Posting Manually! The Automated System Every Agent Needs 🚀,” dives deep into the exact workflows we use to achieve this.

In this comprehensive guide, we’ll explore how you can leverage smart systems to free yourself from the manual content treadmill, build true digital authority, and transition from a busy salesperson to a wealthy business owner. We’ll cover everything from how to integrate cutting-edge AI tools to mastering the CEO Day Protocol, all designed to help you build a business that works for you, not the other way around. This isn’t just about efficiency; it’s about building a willable legacy.

Table of Contents

• The Trap of Manual Posting: Why Agents Get Stuck
• Beyond Listing Descriptions: What a True Automated System Does
• Building Your Digital Authority: The AI Advantage
• The CEO Day Protocol: Architecting Your Automation
• From Transactional to Generational: The eXp Realty Advantage
• Why Join With Al & Victoria Pinder
• Frequently Asked Questions

The Trap of Manual Posting: Why Agents Get Stuck

Many real estate agents find themselves trapped in a cycle of manual posting, believing that constant, hands-on content creation is the only way to stay relevant. This perspective, while understandable, often leads to burnout, inconsistent output, and ultimately, a ceiling on growth. The sheer volume of platforms—Instagram, Facebook, LinkedIn, TikTok, YouTube Shorts, blogs, email newsletters—demands a level of effort that few can sustain without significant leverage.

The problem isn’t a lack of tools; it’s a lack of a cohesive system. As a recent Real Trends headline highlighted, there are “20 AI tools for real estate agents to get a competitive edge,” but simply having tools isn’t enough. It’s how you integrate them that matters. Without an overarching strategy, these tools become isolated solutions, adding to the complexity rather than reducing it. Agents end up spending more time managing tools than building their business, never truly able to stop posting manually. This scattered approach prevents you from scaling your efforts and truly owning your market presence.

This is where the Prosperity Agent model shines. We focus on building a robust, automated system that streamlines everything from listing descriptions to full content calendars. While our foundational automation for listings handles property remarks, social posts, and SEO blogs from a single data input, the full “automated system every agent needs” extends far beyond that, integrating every aspect of your content and lead strategy.

Beyond Listing Descriptions: What a True Automated System Does

When we talk about an automated system, we’re not just referring to basic scheduling or AI-generated listing remarks. While those are crucial components, a true “automated system every agent needs” encompasses a much broader spectrum of your business. It’s about creating a harmonious workflow where technology handles the repetitive, time-consuming tasks, allowing your unique expertise and human connection to thrive.

Our core model, refined over years, operates on a clear division of labor: Victoria pulls comparables and applies her licensed judgment, while our Claude Code automation pulls permits, public records, runs the complex math, and assembles comprehensive packets. This synergy is key. My cron relies on my data and my decisions. The automation does not connect to the MLS, select comparables, or produce an opinion of value autonomously. Instead, it meticulously gathers and organizes the public record data that an agent would otherwise chase by hand, performing the mathematical valuations and assembling the full packet in minutes, not hours. This saves immense time on assembly and formatting, ensuring compliance while maximizing efficiency, allowing you to stop posting manually and manage your business.

Beyond listing prep, this system extends to:

• Lead Enrichment: Automatically cross-referencing new leads with public records to identify key details, ownership history, and potential motivations.
• Market Intelligence: Daily feeds of micro-trends, recent sales, and area-specific data, providing actionable insights for your clients.
• CRM Integration: Ensuring that every interaction, every piece of content, and every lead activity is logged and tracked, powering personalized follow-up sequences.
• Omni-Channel Content Distribution: Not just scheduling, but tailoring content formats for different platforms and ensuring consistent branding and messaging across your digital footprint.

For a deeper dive into the exact workflows and how this system functions, we’ve just released a new YouTube video walking you through the process:

This approach means you’re not just posting; you’re executing a coordinated digital strategy that positions you as the authority in your market, all while significantly reducing your manual workload. It’s about working smarter, not harder, to build a resilient and thriving real estate business.

Building Your Digital Authority: The AI Advantage

The modern real estate agent needs to be more than just a salesperson; they need to be a digital authority. In a market constantly rebounding and showcasing resilience, as recent labor market headlines from RISMedia suggest, staying ahead requires leveraging every advantage. This is where AI skills become invaluable, moving beyond simple prompts to creating predictive intelligence and scalable human connection. You can stop posting manually and start building authority.

Think about predictive intelligence: instead of cold-calling 5,000 homeowners, imagine your system identifying the 50 most likely sellers in your farm area based on public record data, life events, and market conditions. This precision allows for highly targeted, personalized outreach that feels less like a sales pitch and more like a valuable conversation. AI, when integrated correctly, helps you understand the market nuances that affect days on market and pricing sensitivity, giving you an edge that most agents completely miss.

Digital authority isn’t just about being visible; it’s about being perceived as the go-to expert. An automated content system ensures your expertise is consistently broadcast across platforms, establishing you as the credible source for local market insights and real estate advice. This includes everything from AI-enhanced CMA tools that highlight micro-trends to sophisticated content generation for blogs and social media that truly resonates with your audience. This consistency is critical for Google’s E-E-A-T (Experience, Expertise, Authoritativeness, Trustworthiness) ranking signals.

Finally, scalable human connection. AI doesn’t replace genuine relationships, but it enhances them. By automating follow-up sequences, personalized email campaigns, and even drafting initial client communications, AI frees you to spend your precious time on deep, meaningful interactions. You can respond faster, anticipate needs more effectively, and provide a level of service that differentiates you. Learn more about how to craft effective prompts and integrate AI into your daily workflow with our AI Prompts for Agents guide.

The CEO Day Protocol: Architecting Your Automation

Transitioning from a busy salesperson to a wealthy business owner requires a fundamental shift in mindset and strategy. It’s not just about what you do, but how you structure your time to build, not just sell. This is the essence of our CEO Day Protocol: a weekly strategic block dedicated to working on your business, not just in it. And at the heart of making this protocol effective is an automated system every agent needs that handles the operational lifting.

Imagine being able to dedicate a consistent block of time each week to truly strategize, innovate, and optimize your business. This is only possible when your daily content creation, lead management, and administrative tasks are largely automated. The Three-Strike Rule for systems, a core component of our CEO Day Protocol, helps you identify and either automate, delegate, or eliminate tasks that repeatedly pull you away from high-value work. If a task comes up three times, it’s time for a system.

This strategic approach allows you to architect your automation, rather than just reacting to it. You’re not simply using tools; you’re designing a workflow that supports your long-term vision. This includes setting up your content calendars, fine-tuning your lead nurturing funnels, and analyzing performance metrics—all the activities that turn a commission-based job into an equity-rich enterprise. By committing to this protocol, supported by robust automation, you can stop posting manually and build the leverage needed to scale your business without scaling your hours. Discover more about managing your time effectively with our CEO Time Audit.

From Transactional to Generational: The eXp Realty Advantage

Ultimately, the goal of implementing an automated system every agent needs isn’t just to save time; it’s to build a business that truly serves you, not the other way around. This means creating a willable legacy—a business that generates passive residual income and builds equity, an asset you can eventually pass down to your family. This fundamental shift from transactional income to generational wealth is a core tenet of the eXp Realty model, which is why Al Pinder chose it from the beginning.

Traditional commission splits often feel like renting your career. You’re paying a portion of every deal, but never truly building ownership in the brokerage itself. eXp Realty changes this paradigm. With an 80/20 split until you hit a $16,000 cap, you then move to 100% commission. This cap is like a mortgage payment; once it’s paid, you keep significantly more of your earnings. But the real game-changer lies in two additional income streams:

1. EXPI Stock Equity: As an eXp agent, you have multiple opportunities to earn EXPI stock, making you an owner in the company you’re helping to build. This includes earning stock for your first transaction, hitting ICON agent status, and attracting other agents to the brokerage.
2. Revenue Share: This is the passive residual income stream. By simply attracting agents to eXp, you earn a percentage of the commission generated by the agents in your direct downline, and even those in subsequent tiers, up to seven tiers deep. This revenue share is not only passive but, crucially, it’s willable—meaning you can pass this income stream on to your heirs, creating true generational wealth.

This is what it means to stop renting your career and start owning an asset. The automated systems we implement allow agents the time and mental bandwidth to not only excel in their sales but also to strategically build their eXp network and generate passive income. It’s a powerful combination that moves you beyond the commission treadmill. For a comprehensive breakdown of the eXp model, explore our eXp Realty Explained resource and download our Blueprint for Agent Success.

Why Join With Al & Victoria Pinder

The vision of building a real estate business that offers time freedom, financial prosperity, and a willable legacy isn’t just theoretical for us; it’s the journey Al and Victoria Pinder have lived and continue to refine. When you consider joining eXp Realty, the question becomes: why partner with us?

Al Pinder is an ICON agent at eXp Realty, the highest designation earned by top-producing agents who not only hit their cap but also contribute significantly to the eXp community. What’s unique about Al’s journey is that he has been with eXp Realty since the very beginning of his career, building everything from scratch within this cloud-based model. He didn’t come from another traditional brokerage; he chose eXp as the foundation for his entire business.

His story is a testament to the power of building your own pipeline and leveraging automation. In his first year, Al entered a revenue split deal with Realtor.com. In his second year, he bought zip codes on Realtor.com. But by his third year, he made the strategic decision to release all paid lead platforms, including Realtor.com and Zillow, because he and Victoria had successfully built their own robust, organic pipeline. He even tried Zillow for six months on a contract and experienced zero conversions—a powerful firsthand lesson that solidified his commitment to agent-owned systems. This is not about telling you what to do; it’s about showing you what’s possible because we’ve already done it.

When you join eXp with Al and Victoria Pinder, you’re not just gaining sponsors; you’re gaining trusted partners who have walked the exact path you’re on. We won’t push you to buy Zillow leads because we know exactly what that costs and what it delivers (or doesn’t). Instead, we provide a proven blueprint, personalized mentorship, and the exact automated systems we use every single day. We understand the frustrations of the commission treadmill and have built a model designed to help you break free.

Frequently Asked Questions

What is an automated system every agent needs for real estate?

An automated system for real estate agents integrates AI tools and software to handle repetitive tasks like content creation, social media posting, lead enrichment, and market data analysis. It frees up an agent’s time from manual busywork, allowing them to focus on high-value client interactions and strategic business growth, ultimately scaling their operations more efficiently.

How can AI help real estate agents stop posting manually?

AI assists agents by automating various content processes. It can generate listing descriptions, social media captions, blog outlines, and email campaigns. Furthermore, AI tools can schedule posts, analyze engagement metrics, and even predict likely sellers based on data, significantly reducing the manual effort required for consistent and effective content marketing.

Is it possible to automate lead generation in real estate?

While human connection remains vital, AI and automation can significantly enhance lead generation. Systems can enrich incoming leads with public record data, identify buyer/seller intent through digital footprints, and automate personalized follow-up sequences. This doesn’t replace the agent but streamlines the process of qualifying and nurturing leads until they are ready for direct human interaction, making an agent’s efforts more productive.

What is eXp Realty’s commission cap and how does it relate to automation?

eXp Realty operates on an 80/20 commission split until an agent pays $16,000 to the brokerage in a calendar year. After hitting this “cap,” agents receive 100% of their commission. Automation helps agents achieve this cap faster by increasing efficiency and lead conversion, allowing them to retain more of their income sooner. It enables quicker progression to the 100% split, enhancing overall profitability.

What is the CEO Day Protocol for real estate agents?

The CEO Day Protocol is a strategic time management framework for real estate agents, involving a dedicated weekly block to work on their business rather than just in it. It emphasizes building systems, optimizing workflows, and strategic planning. Automation is crucial for this protocol, as it frees up the necessary time by handling daily operational tasks, enabling agents to focus on growth and long-term vision.

How does an automated system help build generational wealth for agents?

An automated system creates efficiency and frees up time, allowing agents to focus on building passive income streams like eXp Realty’s revenue share. By attracting other agents to eXp, they earn a percentage of commissions from their network, which is willable. This, combined with stock equity opportunities and greater control over their business, transforms a transactional income into a sustainable, generational asset.

GLM AI Writes Blogs, Social Posts: No Subscription

by Al Pinder | Sep 5, 2026 | Uncategorized

See related reading on our site.

GLM AI Writes Blogs, Social Posts: No Subscription, No API

If you are a real estate agent producing your own content, you have likely asked whether there is a way to use AI to write blogs and social posts without paying for another monthly subscription or setting up a complicated API. GLM AI answers that question directly: it writes full blog posts, social captions, and market update content at zero recurring cost, with no API key required. This week’s new YouTube video walks through the full workflow, and this post covers the angle the video opens up for agents who are building their own content stack rather than renting access to someone else’s platform.

We have a new video out this week. Before we get into the breakdown, watch the full take on YouTube:

As an eXp Realty ICON agent who built his pipeline from scratch, Al Pinder has lived the full arc of the agent content problem: from paying for Realtor.com lead splits in year one, to buying zip codes in year two, to walking away from every paid lead platform entirely in year three because the content engine he had built did not need them anymore. GLM AI is part of how that content engine runs today.

What Is GLM AI and Why Does It Matter for Real Estate Agents?

GLM, which stands for General Language Model, is an open-source large language model family developed by Tsinghua University. The GLM-4 and ChatGLM lineage have produced models capable of generating long-form blog content, short-form social captions, and structured market narrative without requiring a paid subscription tier or an API key to run.

For real estate agents, that distinction is significant. The dominant AI writing tools on the market are priced as SaaS subscriptions. You pay monthly, the tool processes your prompts on their servers, and often the terms of service allow the platform to use your inputs for model training. GLM runs differently. The models are available through free-tier access points and can be deployed locally, which means your market knowledge, your voice, and your client data stay with you.

This connects directly to the automation approach documented in our keyword discovery cron system, which pulls live search signals to surface what your audience is actually looking for before you write a word. When you pair that keyword intelligence with a model like GLM, you are not just producing content faster. You are producing content that is more precisely targeted to what agents and buyers in your market are searching for right now.

How GLM AI Writes Blogs and Social Posts Without an API Key

The question agents ask most often is practical: how does this actually work if there is no API key and no paid account? The answer is that GLM is accessible through multiple free-tier interfaces, including Zhipu AI’s web platform and through Hugging Face model hosting, depending on the version you are running. You do not need to be a developer to use it.

The real leverage, however, is not in the interface. It is in the prompt structure. A GLM model given a generic prompt produces generic content. A GLM model given a structured prompt that includes your market voice, your specific topic, your internal linking requirements, and your target keyword produces something that is genuinely usable.

Here is the practical framework the Prosperity Agent content stack uses:

Step One: Define Your Voice Before the Model Writes

The first thing you feed GLM is not a topic. It is a voice definition. This is a short paragraph that describes who you are, who you are writing to, what tone you use, and what you never say. For an agent writing market content, this might include the neighborhoods you work, the type of buyer you serve, and the specific phrases you use or avoid. When this voice definition is part of the prompt, GLM outputs content that does not read like it was produced by a generic tool.

Step Two: Supply the Facts, Let the Model Build the Structure

The ground truth rule in this content operation is clear: you bring the data, the model builds the packet. Victoria runs the MLS herself. The automation pulls public records, permit data, and market signals. Neither half replaces the other. Applied to blog writing, this means you supply the real numbers, the real neighborhood names, the real market observations, and GLM assembles them into a structured post with headings, transitions, and a CTA. The model does not invent your facts. You bring them. It organizes them.

Step Three: Run the Output Through a Review Gate Before Publishing

Nothing in this workflow publishes without a human review. That is not a limitation; it is the point. The time saving is in drafting and assembly, not in bypassing your judgment. An agent who reviews a GLM draft in four minutes and publishes it has saved forty minutes compared to writing from a blank page. The quality of the output is yours to verify. The labor of the first draft is not.

GLM AI vs. Paid Subscription Tools: A Practical Comparison for Agents

The table below compares GLM AI with the subscription-based tools most agents are currently using. These figures reflect publicly available pricing and documented model capabilities as of 2026.

The cost difference compounds quickly. An agent paying $49 a month for a standard AI writing subscription spends $588 a year. An agent running GLM through a free-tier interface spends zero on the model itself, and can apply that $588 toward a CRM upgrade, a listing photography package, or simply keeping it as margin. Over three years, that is over $1,700 that stays in the business.

If you want to see the full AI prompts we use to drive this kind of output, the AI Prompts for Agents resource walks through the exact prompt structures we run in production.

Why Open-Source AI Fits the Prosperity Agent Model

The Prosperity Agent model is built on a simple premise: stop renting your career and start owning it. That applies to your brokerage structure, your lead pipeline, and your content infrastructure. Every subscription you pay is a recurring dependency. Every piece of content you own outright is a compounding asset.

Al Pinder has been at eXp Realty since the beginning of his career. He did not switch brokerages. He chose the cloud-based model from the start because the economics made sense: an 80/20 commission split with a $16,000 annual cap, then 100% after that, plus stock equity at production milestones, plus a seven-tier revenue share system that generates income beyond the transaction. That is three income streams from one decision.

The same logic applies to content tools. When you pay for a SaaS AI writer, you are funding their infrastructure indefinitely. When you build a workflow around open-source models like GLM, you are building an asset that does not invoice you every month. The content it produces, properly optimized and published, continues to bring organic traffic to your website long after the draft was written. That is leverage.

For a deeper look at how the eXp model creates the same kind of ownership advantage in your brokerage structure, the eXp Realty Explained resource breaks down all three income streams in plain language.

What GLM Can Write for a Real Estate Agent Right Now

The practical output categories for agents using GLM without a subscription or API key include the following:

Long-Form Blog Posts

GLM handles 800-word to 2,000-word blog posts with proper heading structure, transition paragraphs, and call-to-action sections. When you supply the keyword target, the market data, and the voice definition, the model produces a draft that is structurally complete. Your job is to review the facts, sharpen the voice, and publish.

Social Media Captions

Instagram captions, Facebook posts, and LinkedIn updates all follow different structural rules. GLM can be prompted to produce each format separately with the correct tone, length, and CTA. An agent who needs three captions for three platforms on a single topic can batch-prompt GLM and produce all three drafts in one session, then review and schedule them.

Market Update Narratives

This is where the split workflow matters most. You pull your MLS data. Your automation pulls public records and permit history. GLM takes both sets of inputs and writes the narrative that ties them together into a readable market update your database will actually engage with. The model does not pull the data. You and your systems do. The model writes the story around what you found.

Email Sequences and Drip Content

Agents running a structured follow-up system need consistent touchpoints across a twelve-month nurture sequence. GLM can draft those touchpoints when given a clear voice brief and a sequence structure. The output is a starting draft, not a finished product, but a starting draft that takes four minutes to review is far more scalable than writing each email from scratch.

The Prompt Structure That Makes GLM Output Usable

The single biggest mistake agents make when they try open-source models for the first time is using the same prompt structure they would use in a consumer chatbot. A bare question like “write me a blog about listing your home” will produce a bare, generic result.

A prompt that includes five components produces something usable:

1. Role definition: Tell the model who it is writing as. Not “you are an AI,” but “you are a top-producing eXp Realty ICON agent writing for other real estate agents who are considering a brokerage move.”
2. Audience definition: Tell the model who it is writing to. A burned-out mid-career agent is different from a first-year agent fighting for survival. The output changes significantly when the audience is named.
3. Topic with data: Supply the real market data, real neighborhood names, or real eXp model details. Do not ask GLM to invent facts. Give it the facts and ask it to write around them.
4. Format specification: Specify the heading structure, the word count, the CTA format, and the internal links you need included.
5. Voice constraints: List the phrases, tones, and approaches the model should never use. This is as important as what you tell it to include.

When those five components are in the prompt, GLM outputs something that requires editing, not rewriting. That is the difference between a tool that saves you time and a tool that creates more work.

The Prosperity Agent Blueprint includes the full framework for building a content system like this around your real estate business, not just the AI piece but the full architecture of an agent business that works without paid lead dependency.

The Keyword Discovery Connection: Writing Content That Actually Ranks

Producing content at volume is only half the equation. The other half is producing content that targets what people are actually searching for. This is where the automation stack goes deeper than just the writing model.

The keyword discovery cron system pulls live Google Autocomplete data on a weekly schedule, surfaces new searches you are not currently targeting, and reports on how your existing targets are moving in Google Search Console. That weekly keyword intelligence feeds directly into what GLM is asked to write.

The workflow looks like this in practice: The keyword cron runs and identifies a search phrase that your site is not ranking for but that your audience is clearly searching. That phrase becomes the topic brief. The topic brief feeds into a GLM prompt with the five components above. GLM produces a draft. You review, add your real market data, and publish. The post is indexed within days and begins accumulating ranking signals.

That is a content pipeline that costs you nothing in subscription fees, produces content that is specifically targeted to your actual audience, and compounds in value over time because each post is a permanent asset on your site. The real estate agents winning the organic search game in 2026 are not winning because they have the biggest AI budget. They are winning because they built the system once and let it run.

Why Join With Al and Victoria Pinder

Al Pinder is an ICON agent at eXp Realty, the highest designation eXp awards. He has been with eXp since the beginning of his career. He did not come from another brokerage and decide eXp was better. He chose the cloud-based model from day one and has never had a reason to leave, because the economics of the model have only become clearer over time.

The content system described in this post is not hypothetical. It is how the Prosperity Agent brand runs. The automation does the public records, the permit checks, the keyword intelligence, and the content drafting. Victoria runs the MLS herself and brings the licensed judgment that no automation can replicate. Al brings the eXp business model, the revenue share architecture, and the real story of building a pipeline that does not depend on Zillow or Realtor.com.

That three-year journey, from Realtor.com split deal in year one, to buying zip codes in year two, to walking away from every paid lead platform in year three because the content engine made them unnecessary, is the proof that this model works. When you join eXp with Al and Victoria as your sponsors, you are joining someone who has already solved the problem you are facing and is running the exact system you are looking to build.

The Partner with Al and Victoria Pinder page is the right place to start that conversation. If you are ready to stop renting your content tools, your leads, and your career from someone else’s platform, DM BLUEPRINT or visit theprosperityagent.com/resources/blueprint/ and we will talk about what building this for your business actually looks like.

We are excited to have you build with us.

Frequently Asked Questions

Does GLM AI write real estate blog posts without a subscription?

Yes. GLM AI is an open-source large language model accessible through free-tier platforms including Zhipu AI’s web interface and Hugging Face model hosting. Real estate agents can use it to generate blog posts, social media captions, and market update narratives without a monthly subscription or a paid API key. The quality of the output depends heavily on prompt structure, not on paying for a premium tier.

How is GLM AI different from ChatGPT or other AI writing tools?

GLM AI is open-source, meaning the model weights and architecture are publicly available. Unlike subscription-based tools such as ChatGPT Plus, Jasper, or Copy.ai, GLM does not require a monthly seat license. It can be run locally, which means your prompts and market data are not processed on a third-party server. For agents concerned about data privacy or recurring software costs, this is a meaningful distinction.

What types of content can GLM AI produce for real estate agents?

GLM AI can produce long-form blog posts, Instagram and Facebook captions, LinkedIn posts, email nurture sequences, and market update narratives. When given a structured prompt that includes a voice definition, a specific topic with real data, a target audience description, and a format specification, GLM produces drafts that require editing rather than complete rewriting. Agents supply the facts; GLM builds the structure.

Can I use GLM AI without any coding knowledge?

Yes. GLM AI is accessible through browser-based interfaces that require no coding to use. For agents who want to integrate it into an automated content workflow, there is an API available for more advanced use, but the entry point is a simple web interface. Writing a well-structured prompt is the skill that matters most, not technical ability.

Does using free AI writing tools affect SEO or content quality?

The cost of the AI tool does not determine SEO performance. Content quality, keyword relevance, internal linking structure, and publishing consistency determine rankings. An agent who uses a free model like GLM with a structured prompt, real market data, and a consistent publishing cadence will outrank an agent using a premium subscription tool who publishes infrequently with generic content. The model is a drafting tool. The strategy is what drives rankings.

How does GLM AI fit into a real estate agent content automation system?

GLM AI works as the drafting layer in a broader content automation stack. A keyword discovery system identifies what your audience is searching for. You supply that keyword target plus your real market data to a GLM prompt. GLM produces a draft. You review and approve. Your publishing workflow handles formatting and distribution. GLM handles the labor-intensive first draft, which is where most agents lose time. The human review and the real data inputs remain non-delegable.

Is GLM AI safe to use for real estate content from a compliance standpoint?

GLM AI is a content drafting tool. Compliance with real estate licensing rules, fair housing standards, and MLS terms of service remains the responsibility of the licensed agent reviewing and publishing the content. GLM does not access MLS data, generate opinions of value, or make compliance determinations. Any AI-drafted content should be reviewed by the licensee before publishing to ensure it meets applicable standards. The tool drafts; the agent decides.

Which Claude Skills Actually Run in Production?

by Al Pinder | Sep 4, 2026 | Uncategorized

Which Claude Skills Actually Run in Production?

If you have already looked at the open-source Claude skills repo for real estate agents, you have probably seen the full list of documented procedures. The real question — the one agents ask us every week — is not ‘what is in the repo?’ It is ‘which of these actually runs in a live production business, and what does the human still have to do?’ That is what this post answers. We are going past the overview and into the mechanics of which skills do real work, where they hand off to the licensed agent, and why that split is not a limitation — it is the whole design.

Quick answer: The skills that run consistently in production are the ones that live entirely on the public-records side of the workflow — permits, deed checks, property records, packet assembly, listing remarks, and CRM nurture drafts. None of them touch the MLS. None of them select comps. None of them produce an opinion of value. The agent does that. The skills do the assembly so the agent is not spending three hours chasing county portals and formatting packets before the real work begins.

The Split That Protects Your License — and Why It Is the Whole Design

Before we go skill by skill, you need to understand the architectural decision behind the open-source Claude skills repo for real estate agents, because it is not accidental. Every skill in the repo was built around one principle: the licensed human runs the licensed work. The automation runs the public-records assembly. Those two halves combine into a finished product. Neither does the other’s job.

In practice, that means this: you run your MLS. You export your own comps. You choose the properties that belong in the analysis. You apply adjustments. You sign the opinion of value. That is your license, your liability, and your professional judgment — none of which a documented skill should be near.

What the skills handle is everything you were doing by hand that did not require a license to do: pulling permit records from county portals, cross-checking deed restrictions in the Register of Deeds, assembling a pricing packet from the data you already chose, drafting listing remarks in your established voice, building CRM nurture sequences from the lead profile you already reviewed.

NAR Code of Ethics Article 11 and state license law put the opinion of value on the licensee personally. The automation organizes what the agent already decided. Time is saved on assembly and formatting — never on analysis. Build your skills around that line and you will never have a compliance problem with your workflow. Blur that line and you have invented a liability.

For the full documented list of what the repo covers, visit the open-source Claude skills repo for real estate agents — that page is the canonical source. This post goes narrower: specifically which of those skills we run in production every day and what the agent-side inputs look like.

The Permit and Public Records Skills — Where the Real Time Savings Are

If you had to pick one category where documented Claude skills return the most time per use, it is permits and public records. Here is why: every production agent already knows they need this information. The question is whether you spend forty-five minutes chasing county portals yourself, or whether a documented skill does that run while you are pulling your MLS data.

What the Permit Skill Actually Does

The permit pull skill checks county permit portals and open data sources for the subject property. It looks for additions, conversions, and accessory structures — and critically, it flags whether the certificate of occupancy is closed or open. An open CO on an addition the seller is advertising as finished square footage is a material fact issue. You want to know that before the pricing conversation, not during the inspection.

What it does not do: it does not interpret whether that open CO affects value. You make that call. The skill surfaces the fact; you decide what to do with it.

The Deed and Ownership Check Skills

The /deed-check and /ownership-check skills pull from Register of Deeds data and county GIS parcel records. They look for covenants, amendments, owner-occupancy restrictions, and leasing restrictions. If a buyer is planning to convert a property into a short-term rental and there is a covenant restriction on the deed that prohibits it, that is something that should surface in the research phase — not after the purchase agreement is signed.

Again, you review. You decide. You disclose. The skill does the chase so your review starts from a complete file instead of a blank page.

Listing Remarks and the Voice Problem Every Agent Has

Listing remarks are one of the highest-leverage places to deploy a documented Claude skill — and one of the most misused. The mistake agents make is treating listing remarks like a one-time prompt: they describe the property in a chat window, get a draft, clean it up, and move on. That works once. It does not scale, and it does not maintain voice consistency across your listings.

How the /listing-remarks Skill Solves This

The /listing-remarks skill in the repo is a documented procedure with a defined input structure. You feed it your established facts: square footage from your licensed measurement or a verified source, confirmed bedroom and bathroom count, lot size, feature list from your walkthrough notes, and any details the seller emphasized as selling points. The skill drafts remarks in a voice that has been documented — your voice, your market’s vocabulary, your compliance language.

One critical note on square footage: tax card square footage is noted by the skill but never used as the pricing anchor. Appraisers measure to ANSI Z765. Your skill should reflect that discipline. If your listed square footage cannot be verified by a licensed measurement or a confirmed source, the skill flags it rather than using an unverified figure.

Fair Housing Compliance Is Built Into the Skill Structure

A properly documented listing remarks skill includes compliance checkpoints that a raw prompt does not. Every output gets reviewed against a Fair Housing language check before it is used. The skill does not drift into protected-class language because the procedure explicitly prohibits it — and because you review before anything publishes. That review step is not optional. It is part of the skill’s defined workflow.

CRM Nurture Skills That Actually Get Used — and the Ones That Do Not

The CRM nurture category is where agents have the most uneven results with documented skills — not because the skills are weak, but because agents skip the input discipline and wonder why the output does not convert.

What Makes a CRM Nurture Skill Work

The /agent10_crm_nurture workflow runs on a schedule in our production system — not on demand. That distinction matters. A nurture skill that only runs when you remember to trigger it is not a nurture system. It is a better prompt. The value of a documented skill is that it runs at a defined time, against a defined contact list, and produces a defined output format you can review and deploy without rebuilding the context every time.

The input side is where most agents underinvest: the skill is only as useful as the lead profile you feed it. If your lead data is thin — just a name and phone number — the nurture draft will be generic. If your lead data includes source, property interest, timeline, last touchpoint, and any notes from prior conversations, the draft will be specific enough to actually send.

The Skill That Enriches Before the Nurture Runs

The /enrich-leads skill and the enrich_leads_pipeline.sh cron handle lead enrichment before the nurture workflow fires. Public records, property history, and any available profile data get pulled and added to the contact record. The nurture draft then has something real to reference. That sequence — enrich first, then nurture — is what separates a CRM skill that produces usable output from one that produces a template you immediately rewrite.

What Breaks When Agents Skip the Human-AI Split

We have had conversations with agents who came to us after attempting to build AI workflows that crossed the line we described above. The patterns are consistent and worth naming directly so you can avoid them.

Attempting to Automate the Comp Selection

This feels like a natural step — you have the data, Claude is good at analysis, why not let it pick? Here is why not: comp selection is a professional judgment call that belongs to the licensed agent. It is not a data-sorting problem. Two properties that look identical in a spreadsheet can require completely different adjustments based on conditions you observed during a walkthrough. A skill that selects comps is not saving you time — it is producing an output you cannot trust and cannot sign.

The correct workflow: you pull the comps, you choose the properties, you export your selection. The skill then runs the math against your choices, assembles the packet, and formats the output for your review. That is the workflow that is both faster and defensible.

Using Unverified Square Footage as a Pricing Input

Several publicly available data sources — Redfin, Zillow, county tax cards — provide square footage figures that may not match a licensed ANSI Z765 measurement. A skill that uses an unverified tax card figure as its primary input for a pricing packet is building the wrong foundation. The correct skill design notes the public figure, flags any discrepancy between sources, and defers to the licensed measurement or the agent’s stated verified figure. If your workflow does not make this distinction, your packet is based on data you cannot stand behind.

Prompt vs. Skill: A Side-by-Side Comparison

Because this distinction is central to the value of the skills repo, here is a direct comparison of how a raw prompt and a documented Claude skill differ across the dimensions that matter in production:

How to Get Started Without a Coding Background

The most common objection we hear when agents look at the repo is that they assume it requires coding knowledge to use. It does not — but it does require documentation discipline, which is a different skill that most agents already have and undervalue.

Step One: Document One Workflow You Already Do

Pick the task in your production week that is most repetitive, most time-consuming, and least judgment-dependent. For most agents, that is either permit research, listing remarks, or CRM follow-up drafts. Write down exactly what you do, step by step, including what inputs you start with and what output you need. That documentation is the skeleton of your first skill.

Step Two: Match It to an Existing Skill in the Repo

The open-source Claude skills repo for real estate agents already has documented procedures for the most common production workflows. Before you build from scratch, check whether a skill already exists that matches your workflow. If it does, you can adopt and modify it in far less time than building new. The MIT license means you can take it, adapt it to your market, and run it without restriction.

Step Three: Define Your Compliance Checkpoints Before You Run Anything

Every skill needs at least two compliance checkpoints defined before it touches production: one at the output stage (does this draft contain any Fair Housing proxy language?) and one at the handoff stage (did a licensed agent review this before it was used in a client-facing context?). Document those checkpoints in the skill definition, not as a reminder to yourself. A checkpoint that lives in your head is a checkpoint that gets skipped on a busy Thursday.

For agents who want a structured guide to building their first documented AI workflow, the CEO Time Audit is a useful starting point — it helps you identify exactly where your production hours are going before you decide which workflow to automate first. And the follow-up system guide covers the CRM nurture side of the workflow in depth if that is where your biggest time drain lives.

What Real Estate Agents Are Saying About AI Tool Choices in 2026

Industry headlines this week flagged over twenty AI tools competing for the attention of real estate agents. Most of them are point solutions: one tool for listing descriptions, one for social content, one for lead scoring. The challenge with point solutions is that they do not talk to each other, they each have their own pricing and compliance terms, and none of them are built on your voice or your data. A documented Claude skill runs on Claude Code, uses your exported data as its input, and produces output in your documented voice — no additional subscription, no third-party data sharing, no vendor lock-in.

That is not an argument against every AI tool. It is an argument for understanding what you are buying when you pay for a point solution versus what you build when you invest in a documented skill. The agents who are building skills are building leverage that compounds. The agents who are subscribing to tools are renting capability they do not own and cannot modify.

Why Al and Victoria Pinder Built This in Public

The open-source Claude skills repo for real estate agents was not built as a marketing asset. It was built because Al and Victoria Pinder were running these workflows in their own production business and realized that documenting them publicly was more useful than keeping them proprietary.

Al has been at eXp Realty since the beginning of his career — not as a transfer from another brokerage, but as an agent who built his entire production business inside this model. The workflow philosophy that shaped the skills repo came from that same production discipline: build systems that run on your data and your judgment, eliminate the manual assembly work, and invest the recovered time in the decisions that require a licensed professional.

In the early years, that meant working through the full cycle of paid lead platforms — a revenue-split deal, bought zip codes, then a six-month Zillow contract that produced no conversions. By year three, every paid lead platform was gone. Not because the platforms failed philosophically, but because they had built their own pipeline and the platforms were no longer adding value relative to their cost. That three-year arc is why every skill in the repo is built around the agent’s own data — because an agent who owns their CRM, their lead data, and their workflows does not need to rent someone else’s pipeline.

If you are ready to build your first documented Claude skill and want to talk through where to start in your specific production workflow, book a strategy call with Al and Victoria Pinder at calendly.com/theprosperityagent. Or grab the Blueprint to see the full framework: theprosperityagent.com/resources/blueprint/.

Frequently Asked Questions

What is the open-source Claude skills repo for real estate agents?

The open-source Claude skills repo for real estate agents is a free, MIT-licensed library of documented AI procedures built specifically for production real estate workflows. Each skill defines a specific input, a specific output, and compliance checkpoints. Skills cover permit pulls, deed checks, listing remarks, CRM nurture drafts, and packet assembly — none of them touch the MLS or produce an opinion of value, which remains the licensed agent’s responsibility.

Do Claude skills for real estate require coding knowledge to use?

No. Using an existing Claude skill from the repo requires documentation discipline, not coding. You need to understand the skill’s defined inputs, provide your own verified data, and review outputs before use. Building a new skill from scratch may involve light scripting if you want it to run on an automated schedule, but adopting and modifying an existing skill is accessible to any agent willing to invest in the upfront documentation work.

No — and this is by deliberate design. The skills repo does not include any skill that logs into an MLS, scrapes listing data, or selects comparables. The skill reads that export and handles the assembly side. This split is how the workflow stays compliant with MLS terms of service and state license law, which places the opinion of value on the licensed agent personally.

How is a documented Claude skill different from a raw AI prompt?

A raw prompt resets every session — you re-explain your market, voice, and compliance rules each time. A documented Claude skill has those elements baked into its procedure definition. It produces the same structured output format every run, can be triggered on a schedule, and can be handed off to another agent on your team without losing context. The upfront documentation investment is the only cost; after that, the skill runs without setup time.

What Claude skills run in a real production real estate business?

In active production, the skills that return the most consistent value are permit and public records pulls, deed and covenant checks, listing remarks drafting, and CRM nurture sequence generation. These are all public-records or assembly tasks that do not require a license to perform but were previously eating hours of agent time per transaction. Skills that attempt to cross into comp selection or pricing analysis are outside the design intent of the repo and create compliance risk.

Is the Claude skills repo actually free to use and modify?

Yes. The repo is MIT-licensed, which means you can use it, modify it for your market, and build on it without cost or permission. The only requirement under MIT is that you retain the license notice if you redistribute. Agents can adopt a skill, adapt the documented procedure to their specific county data sources or voice preferences, and run it in their own production workflow without restriction.

Where do Claude skills for real estate agents live and how do I install one?

The canonical source is the open-source Claude skills repo for real estate agents at theprosperityagent.com/skills. Each skill is a documented procedure file. Installation means placing the skill definition where Claude Code can reference it and providing your local data exports as inputs. The repo page includes setup guidance for agents without a development background.

Claude Vs Gemini For Coding: A Local Breakdown

by Al Pinder | Sep 3, 2026 | Uncategorized

Claude Vs Gemini For Coding: A Local Breakdown

The open-source Claude skills repo for real estate agents answers a question most AI tool reviews never ask: where does the data come from? If you are already using Claude Code in your business, the skills in that repo divide cleanly into two categories — skills that run on your licensed data and skills that run on public records. Understanding that split is not a technical detail. It is where your compliance line lives.

This post goes narrower than the overview page. If you want the full list of what the repo contains and how to install a skill, start at the open-source Claude skills repo for real estate agents. This post is for agents who are already in the repo and want to know exactly which workflows are pulling from agent-supplied inputs versus which ones run autonomously against public data — and why that distinction protects your license.

The Two-Lane Data Split Every Agent Needs to Understand

Before you run any skill from the Claude skills repo, you need a mental model that the repo’s overview page does not spell out in granular terms: every skill in the library belongs to one of two data lanes.

Lane 1 — Agent-supplied data. These skills do not run until you provide input. They accept your MLS export, your comp selections, your listing remarks draft, or your client CRM notes. The skill formats, analyzes, or assembles based on what you bring. It cannot do anything without you.

Lane 2 — Public records data. These skills query open government portals — permit databases, GIS parcel data, Register of Deeds records — and return structured results without needing any input from your licensed workflow. They are fully autonomous on the public-data side.

The real power — and the compliance-safe design — comes from combining both lanes in sequence. That combination is the system. Neither lane replaces the other.

Which Skills Require Your Input to Run?

Several skills in the Claude skills repo for real estate agents are input-gated. They literally wait for you. Here is what that category includes and what each one does with your data when you supply it.

The Price-Analysis Skill

This is the skill most agents ask about first, and it is the one where the data-split matters most. The price-analysis skill runs in two sequential steps. Step one is yours entirely: you log into your MLS, run your comp search, apply your filters, and export your results. In the workflow Victoria runs, that export lands as a local CSV file the script reads directly. The MLS itself has no API connection to this system — she pulls and she chooses.

Step two is the automation: the skill reads your export, then goes out to Pitt County’s permit portal and open data sources to pull permit history on the subject property. It checks whether additions or conversions have a closed certificate of occupancy. It cross-references the Register of Deeds for covenants and leasing restrictions. Then it runs three valuation methods against your comps and builds the packet.

Your comp selection drove the output. The automation handled the retrieval and assembly. That sequence is intentional and non-negotiable.

The Listing-Remarks Skill

The listing-remarks skill is purely agent-input-driven. You supply the property details — features, recent updates, lot characteristics, any seller-provided notes. The skill drafts remarks. You review before anything touches the MLS. There is no data pull here; the skill’s job is language, not data retrieval.

The Listing-Presentation Skill

This skill takes your pricing opinion — which you derived from your own comp analysis — and builds the presentation packet around it. It pulls in the math you already ran, formats the net-to-seller calculation, and assembles slides or a Gamma document for the seller conversation. Again: your judgment first, assembly second.

Which Skills Run Autonomously on Public Records?

A separate category of skills in the repo runs on a schedule without waiting for you to trigger them manually. These are the cron-based public-records skills. They operate on Lane 2 data exclusively — nothing that touches MLS, nothing that requires a licensed input, nothing that produces an opinion of value.

The Permit-Pull Workflow

On a schedule, this workflow queries the Pitt County EPL portal and the Pitt County Permits open data source. It returns permit history for a specified parcel — what was pulled, what was closed, what is still open. An agent reviews this output; the skill does not interpret it. The output is raw permit data structured for easy reading, not a recommendation.

The Public-Records Pull

The public-records skill queries Pitt County OPIS GIS parcel data and ArcGIS open data layers. It surfaces ownership records, lot boundaries, and parcel-level characteristics. The Register of Deeds pull — handled by a separate documented script — retrieves deed covenants and amendments, including any owner-occupancy or leasing restrictions that might affect an investor’s purchase decision.

The Market Intel Cron

Victoria’s daily market intel cron runs at 5:50 PM and writes a structured JSON file with market-level signals. That file is the only source from which numbers appear in published content. If a number is not in the file, it does not get published. This is the specific reason any post on this brand that cites market data is traceable — not because the AI is confident, but because the pipeline enforces a citation gate.

How the Two Lanes Combine in a Real Transaction

Here is a concrete walkthrough of how the two lanes operate together during a listing appointment prep sequence. This is the actual workflow, not an aspirational example.

The day before the listing appointment, Victoria logs into NCRMLS and runs her comp search. She applies her own filters — square footage range, age, location, condition adjustments she knows from market experience. She exports the results as a CSV. That file lands in a local directory the scripts read.

The price-analysis skill reads her CSV. It then queries Pitt County’s permit portal for the subject property’s address, checks for any open permits that could affect the closing timeline, and pulls deed records from the Register of Deeds to flag any restrictions the seller may need to disclose. It runs three valuation methods against her comps. It assembles the packet.

She reviews the packet before it goes anywhere. The Canon-Lock gate in the workflow means nothing ships until she says go. That is not a best-practice suggestion — it is enforced in the system architecture.

The result: a packet that took hours to assemble manually now takes minutes. And her name is on it because her judgment is in it.

Want to see the full workflow map? We broke down how we built our AI stack — and what it actually does versus what most AI tools claim — in the AI Prompts for Agents resource guide.

Skill-by-Skill Data Source Comparison

The table below maps each documented skill to its data source, trigger type, and the agent action required before output is usable. This is the reference sheet the overview page does not include — bookmark it for your own implementation planning.

Notice what is not in this table: there is no skill that logs into an MLS on your behalf, no skill that selects comparables for you, and no skill that produces a CMA without your comp data as the input. Those capabilities do not exist in the repo — and their absence is the compliance design, not a limitation.

For a deeper look at how the repo stacks up against building raw prompt chains from scratch, the agent resource guide on brokerage systems and tools covers the tradeoffs in plain terms.

Where Your License Line Sits — and Why It Matters

This section is the one most AI tool marketing skips entirely — and it is the one that should anchor every decision you make about your AI stack.

NAR Code of Ethics Article 11 places the opinion of value on the licensee personally. Not on the tool. Not on the brokerage. On you. That means comp selection is yours. Adjustments are yours. The final price recommendation is yours. Automation that performs those steps on your behalf is not a productivity tool — it is a liability transfer you did not sign up for.

The Claude skills repo for real estate agents is designed around that constraint. The price-analysis skill does not select your comps. It reads the comps you already selected. It does not recommend a list price. It runs valuation math against the comps you brought and presents the result for your review.

The permit-pull and public-records skills operate entirely outside the licensed opinion-of-value workflow. They retrieve factual public data — permit status, deed covenants, parcel boundaries — that you would otherwise chase by hand through county portals. They do not interpret that data for you. They present it.

That design is also why the Canon-Lock gate exists in the price-analysis workflow. Nothing ships until the agent reviews and approves. A citation gate blocks any draft from reaching a live brand surface unless the numbers are traceable to the verified data file. These are architectural constraints, not suggestions.

If you are evaluating any AI tool for your real estate business — whether from the Claude skills repo or anywhere else — run this test: can you trace every number in the output back to a specific, verifiable data source? If the tool cannot answer that question, you should not put your name on its output.

What This Means in the Broader AI Tools Conversation

Real Trends published a roundup of twenty AI tools for real estate agents this week. Lists like that are useful for awareness — but they rarely answer the data-source question. And in 2026, the data-source question is the one that separates tools that help you from tools that create exposure.

The agents who are winning with AI right now are not the ones running the most tools. They are the ones who built one documented workflow that runs on their own data — their MLS export, their county’s permit portal, their own CRM notes — and who can explain exactly what the automation did and did not do at any point in the process.

That is what the open-source Claude skills repo for real estate agents was designed to enable. Not a magic button. A documented, auditable, agent-controlled workflow that does the assembly work so you can spend more time on the analysis and the relationship.

Billionaires are flooding into AI infrastructure right now — data centers, training compute, inference capacity. That capital is moving because AI is becoming the operating layer of every industry. Real estate is not exempt. The agents who understand their tools at the data-source level will be the ones who use that infrastructure without becoming dependent on it.

Related: if you want to understand how the SEO and content side of our AI stack runs — specifically how the keyword tracking cron feeds our publishing decisions — the YouTube Starter Kit walks through how we use scheduled automations to drive consistent content output without manual daily decisions.

How to Start Running These Skills Today

If you are an agent who is already producing and you want to add the Claude Code skills workflow to your business, the entry point is simpler than most technical content makes it sound. You do not need to be a developer. You do need to be willing to run a skill the first time, see what it returns, and decide what it means for your transaction — exactly the way you would evaluate any other data source.

Here is the practical sequence for getting started with the price-analysis skill specifically:

1. Export your comps from your MLS. Your filters, your selections, your export. Save the CSV locally.
2. Point the skill at your export file. The skill reads the path you specify. It does not access your MLS directly.
3. Supply the subject property address. The permit-pull and public-records pulls run against that address on Pitt County’s public portals.
4. Review the assembled packet. Check the valuation math against your market knowledge. Adjust your pricing opinion as needed. Approve before anything goes to the seller.

The first time through, budget an hour. By the third transaction, the assembly step is genuinely minutes. The time you recover goes back to comp selection — which is where your expertise actually lives.

For agents outside Pitt County: the public-records and permit pulls are written for the specific portals available here. The price-analysis math and the listing-remarks and listing-presentation skills are market-agnostic — they run on whatever comps you supply and whatever property details you provide. The public-data skills require adaptation for your county’s specific portals, which is part of why the repo is open-source. You can see exactly what each script queries and modify it for your market.

The CEO Time Audit resource is a useful companion here — before you add any automation layer, knowing exactly where your hours are going tells you which skill will have the highest immediate impact on your production time.

And if you want to walk through the full stack — what runs on a cron, what runs on manual trigger, how the compliance gates work, and how we have adapted these skills across multiple market conditions — Al and Victoria Pinder are available for a direct conversation. Book a strategy call at calendly.com/theprosperityagent or grab the Blueprint at theprosperityagent.com/resources/blueprint/.

You spent years building your market knowledge. The Claude skills repo for real estate agents is designed to make that knowledge move faster — not to replace it.

Frequently Asked Questions

What is the open-source Claude skills repo for real estate agents?

It is a library of documented procedures — called skills — that real estate agents run inside Claude Code. Each skill handles a specific task: pulling public permit records, assembling a pricing packet from agent-supplied comps, drafting listing remarks, or retrieving deed covenants from county databases. The repo is free, MIT-licensed, and built around a compliance-safe design where agents supply the licensed data and the automation handles public-records retrieval and assembly.

No. Claude Code does not log into any MLS, Flexmls, or listing platform in this system. The agent runs the MLS themselves, exports their selected comps as a local file, and the price-analysis skill reads that file. There is no API connection to the MLS. The agent’s comp selection and judgment are never delegated to the automation — that separation is the core compliance design of the repo.

Which Claude skills for real estate agents run without manual input?

The permit-pull cron, public-records pull, and daily market intel cron run on a schedule without manual agent input. They query open government portals — Pitt County EPL, OPIS GIS, ArcGIS, and the Register of Deeds — and return structured public data. They do not produce an opinion of value, select comparables, or recommend a price. The agent reviews their output in the context of each transaction.

How does the Claude skills repo protect an agent’s license compliance?

The repo is designed so that the opinion of value — the step NAR Article 11 places on the licensee personally — always requires agent input before it runs. The price-analysis skill reads agent-supplied comps; it does not select them. A Canon-Lock gate blocks any pricing output from shipping until the agent approves. Permit and public-records pulls return factual data for agent interpretation, never recommendations. Nothing about the system bypasses the agent’s professional judgment.

Can agents outside Pitt County use these Claude skills?

The price-analysis math, listing-remarks, and listing-presentation skills are market-agnostic — they run on whatever comps and property details the agent supplies. The permit-pull and public-records scripts are written for Pitt County’s specific portals. Agents in other markets can modify those scripts for their own county’s open-data portals, which is one reason the repo is open-source: you can read exactly what each script queries and adapt it for your jurisdiction.

What is the difference between the Claude skills repo and a general AI prompt library?

A prompt library gives you text you copy into a chat window. The Claude skills repo gives you documented procedures — code and workflow logic — that run in Claude Code as a structured skill, accept specific data inputs, call external public-data sources, and produce structured outputs. The difference is the difference between a recipe and a kitchen: the repo is a system, not a collection of starting points.

How long does the price-analysis workflow take once the agent exports their comps?

Based on how the workflow runs in practice: after the agent exports their comps and points the skill at the local file, the permit pull, public-records retrieval, valuation math, and packet assembly typically complete in minutes. The first time through the setup takes longer — expect roughly an hour for initial configuration. By the third transaction, the assembly step is a background task. The time the agent recovers comes directly from the research and formatting work that used to be done manually.