You close a deal and the next morning there are 5 different versions of the same listing photo floating around the internet — the original, the cropped one, the one with the weird filter, the one somebody shrunk to fit a template, and the version somebody spun into a completely different aspect ratio. None of them match. None of them look like they belong together. And you didn’t touch any of them. They just happened, because you don’t have time to sit and hand-craft a marketing package for every single listing. Nobody does. That’s the gap, and it’s real. It’s real on Facebook, it’s real on Instagram, it’s real on the MLS, and it’s real because we’re all pouring our energy into the next client call, the next follow-up, the next negotiation, and the marketing gets what’s left — which is never enough.
Who This Is For
If you’re pouring your own time into content and you know there’s a gap between what you’re publishing and what’s actually out there, this is your gap getting closed, live, on screen.
What It Actually Does
Here’s the thing, neither of these integrations actually exists yet. The Canva one is an idea they’ve talked about on stage — a way to get fresh, on-brand graphics into your listings faster — but it’s still an idea. As for the MLS connection, it’s not an automatic, real-time connection built into any system. It’s the kind of thing a technical team could build internally if they had the right skills on staff — the Canva one’s mostly about setting up a shared workflow, the MLS one’s about scheduling a job and letting the software run it on its own. But if you’re not technical, neither’s something you can just go buy and install. If you want to watch us build something like this from scratch, let us know — we do live sessions where we actually build these things on screen, start to finish, while we talk about what we’re doing.
How You Set It Up
Here’s the honest version of what it actually is. It’s a Google Sheet with 5 columns: the headline, the subhead, the image caption, the image URL, and a checkbox for ‘published’. Every time you want a new post, you open it, fill out those 5 fields, and save. The checked box tells the automation to actually publish it through the connection we set up — not just save it as a draft. The connection part is the piece people get wrong: it’s not ‘integrated with Canva’, whatever that would even mean. It’s a shared Google Sheet as the source of truth, and then whatever you want it to publish to reads that same sheet and publishes from it. So there’s no ‘Canva integration’ to break, and no developer to hire to set it up. You fill out the sheet, and the posting gets handed off to the automation you’ve already set up.
How It Gets You Found
Here’s the mistake we see agents make once they do want to put this on their site: they open Canva, start building a graphic, and when they get to the part where they need the listings, they don’t call the API — they open up Realtor.com, search their market, and copy and paste the results into the graphic by hand. That is the opposite of what a developer would build. A developer would build one connection that talks to the MLS in the background and fetches the right listings for that market, the same way our own listings system does. That connection becomes the single source of truth — one place to change if the market shifts, instead of 100 individual pastings that all go stale on their own. Our review found no sign that the version of this that’s circulating actually is that connection. It may be a script that copies and pastes the way we just described, which is why the before-and-afters look good in the demo and then quietly stop updating on your own site. If you want to run this on your own business, here’s the honest version of what it is: it is a listing widget, the same way the Realtor.com widget or the HomeLight widget are listing widgets. You embed it on your site, and it displays a feed of local listings. The difference is who built it and who controls it. When you build it yourself using a real API, you are the one making the call to the MLS every night, you are the one saving the results every morning, and you are the one deciding what goes into that feed and what stays out. You own the whole loop — the connection, the schedule, the filter, the display — and that ownership is what makes it work for SEO. Every time Google visits your site and sees fresh, local, unique content at the same address every single day, it understands exactly what your site is: a current, authoritative source for listings in your market. That is the exact same signal the big lead portals send to Google every day — and it is the exact signal they are trying to protect, which is why this is the one thing they do not want you building yourself. If you would rather run this on a schedule without checking the code yourself, you can set it up through Claude Code. Open Claude Code and say ‘set up the automatic MLS listing feed.’ Follow the instructions to connect your MLS and pick the market. Once it’s running, it schedules the overnight pull and the morning publish, and you never touch it again.
What It Means For You
If you’re pushing for growth, this means you can build a consistent, recognizable brand across every single listing without adding hours to your week — and that consistency is exactly what gets you found in a crowded market. If you’re building a niche business, it means you can put out targeted, on-brand content without becoming a part-time designer. And if you’re protecting your reputation, it means you’re personally approving every post before it goes out, instead of crossing your fingers and handing it to an assistant.
What It Frees You Up To Do
The real math here isn’t about what this saves you — it’s about what it lets you get back to. Every hour you’re not reformatting a flyer is an hour you can put into the next client call, the next follow-up, the next relationship. That’s real growth, real pipeline, real results — built on top of a business that’s actually scalable, because the part that used to scale by hours now scales by seconds. If you want to see this exact setup running live — the canned sizes, the automatic layout, the one-source-of-truth — book a free 15-minute call with us. The link is in the description. We’ll show you exactly what it looks like and tell you honestly what it can do for your own business. If you’d rather watch us build this from scratch start to finish, subscribe so you don’t miss the next live session — we run one every month. We’re Al and Victoria Pinder, ICON agents at eXp Realty. Come build it with us.
What To Do First
If you’re building a real estate brand online — posting on social, making videos, building a website — you’ve probably felt the frustration of wanting to share a listing and not being sure what image to use. A clean, consistent, correctly-sized listing image makes the post look professional, and a template ensures that every post looks like it belongs to the same brand, even if you’re sharing 5 different listings in a single day. For years, the only way to get that consistency was to open Canva, search for the listing, download the image, and upload it into whatever post or page you were working on — the same 4 or 5 steps, over and over, every time you wanted to share a property. This week, we’re looking at whether that workflow actually has a shortcut. The idea is simple: you open Canva, start a new graphic designed for real estate listings, and instead of searching for the property, you type the MLS number into the design, and the right image comes back — the correct size, the right branding, the right property, every time. No searching, no downloading, no switching tabs to look up what the listing actually is. This is what we hear agents asking about the most these days, in our private community and at the events we speak at. So we sat down with the team that built it to find out whether it actually exists, who it’s for, and how much it costs. If you’re pushing out content consistently — 1, 2, 3, or more posts a day — this is the kind of efficiency you’ve been asking for, and we’re going to show you exactly how it works.
Where to Start
If you want to connect with us and see exactly what we’re building, the link to book a free 15-minute call is in the description below — no pitch, just a live look at what we’re working on. Subscribe so you don’t miss the next live session — we build these on screen, start to finish, and take questions while we work. We’re Al and Victoria Pinder, husband-and-wife ICON agents at eXp Realty, and we run every piece of this stack in our own business, every single day.
Frequently Asked Questions
What is the Google Sheet workflow and how does it work?
The workflow is a Google Sheet with 5 columns: headline, subhead, image caption, image URL, and a “published” checkbox. You fill out these fields when you want a new post, and the checked box tells the automation to publish it — the sheet serves as the single source of truth that your automation reads from to post across different platforms.
Why is building your own MLS listing feed better for SEO than using a widget?
When you build it yourself using a real API, you own the entire loop — the connection, schedule, filter, and display. Google sees fresh, local, unique content at the same address every day and recognizes your site as a current, authoritative source for listings in your market, which is the exact signal that big lead portals send and want to protect.
Can you set up an automatic MLS listing feed without knowing how to code?
Yes, you can use Claude Code to set it up without checking the code yourself. Open Claude Code, say “set up the automatic MLS listing feed,” follow the instructions to connect your MLS and pick your market, and it will schedule the overnight pull and morning publish automatically.
We stopped buying attention and started building our own audience, and that audience now hands us leads every single day, without us ever paying to reach them. This is the actual, real-time ownership manual for that audience pipeline — what it is, how it’s built, and how you run it, step by step, on screen. No hype, no fluff, no rented audience. Just the 3 of us, 3 different businesses, 1 shared machine that runs the same way every time.
If you’re a few years into this business, closing deals and building momentum, you’re generating valuable information every day—market insights, client questions, deal specifics—but you’re not capturing it or reusing it in a way that works for you.
What It Actually Does
Here’s what it actually does, step by step, when you ask it a question.
First, it searches through all the information it’s been trained on — that’s a lot of books, websites, and conversations up to a certain point — for anything relevant to your question.
Second, it uses that information to generate an answer that sounds like a human wrote it. It doesn’t pull a pre-written response from a list — it builds the answer fresh, every time, based on what’s actually asked.
Third, it can pull from and cross-reference multiple sources in that information pool while it’s building your answer — so an answer on a specific market or property isn’t just a generic guess, it’s drawn from the collective knowledge it has on file about that place.
Now, two things it can’t do, despite what you might have heard.
It can’t browse the internet in real time — it can only pull from the information it already has on file, so a question asked this week gets the same answer this week as it got last month, unless that information was updated in one of its occasional refreshes.
And it can’t replace a human lawyer, accountant, or inspector — it can give you a plain-English explanation of a contract clause or an inspection report, but it can’t provide legal or professional advice, and it can’t sign anything on your behalf.
How You Set It Up
Here’s the truth about how we actually set this up — we didn’t build anything new. We started with Claude Code, which is a tool you run from the command line on your own computer, and it’s free. You install it once, and then whenever you want to connect a new source or publish to a new place, you just run one command — you don’t need to open a code editor, write a script, or worry about an API. That’s how we connected both directions: pulling in the daily digest automatically every morning, and publishing out to the website every time we add a note, without us remembering to go upload anything. And the website part is just a simple static site generated from a folder of Markdown files — no server, no monthly fee, just a folder we check into Git, and the live version updates automatically whenever we push a change. So the whole thing runs on our own machine, costs nothing to maintain, and we can see exactly how it works any time we want — there’s no black box sitting somewhere we can’t touch. That’s the whole point. We didn’t go hunting for a new tool to buy. We used what was already at our fingertips to build something that works exactly the way we wanted, for free.
How It Gets You Found
Here’s the part that actually matters if you’re trying to get found.
When a buyer or a seller in your market types a question to Google — ‘should I sell now,’ ‘what’s my house worth,’ ‘how much can I afford’ — Google doesn’t hand them a blank page and say ‘ask your agent.’ It gives them an answer, and that answer comes from one of two places.
The first is the website that showed up first when Google indexed it a few weeks ago. Indexing is when Google comes and looks at your site and decides it’s relevant enough to put into its search results. The problem with that is you have no idea when it’s happening, and you can’t ask Google to come back tomorrow and look at your newest page. You publish something and hope it gets picked up.
The second way is the one we’re getting to. It’s when the question itself goes to a real AI and gets answered directly, right there in the search box, before the user has even hit enter. That’s not an indexed page — that’s the AI reading the question in real time and coming back with an answer typed out on screen before you’ve finished reading your own question out loud.
Nobody’s typing ‘call the agent in Greensboro’ anymore. They’re typing ‘should I sell my house in Greensboro.’ That is exactly the kind of question this system answers, and it answers it with a real, specific response — not a generic ‘consult a professional’ filler. The response comes from the knowledge base you’ve built with your market data, your client insights, the season, the specific town, pulled together with the AI’s own understanding of how all that fits together. And the town is yours to define — it’s whatever you’ve put into the system.
Now, here’s the part everybody assumes, and it’s the wrong assumption. People think whoever answers that question first wins, and the AI that gets there first is the one Google ends up recommending. That’s not actually how it works. What matters is not being first. What matters is being the same AI, answering the same way, every single time that question comes in — tomorrow, next week, next month, with the exact same facts still in the knowledge base.
Being consistent is more important than being fast, because here’s the truth Google cares about: people ask the same question over and over, and every once in a while the answer actually changes.
What It Means For You
For an agent trying to stand out in a crowded market, this means you can offer something genuinely unique — a helpful, knowledgeable assistant that’s actually there to assist, not just a chatbot that spouts generic answers. You own the data, you control the conversation, and you’re the one actually doing the thinking — the AI just helps you do it faster.
If you’re building a brand around being sharp with numbers, this gives you a real advantage, because the same tools let you pull real data instead of just hand-waving about ‘the market’. If your business runs on relationships, this is how you stay top-of-mind without becoming a sales robot — a real, responsive person answers, and the record of that conversation is saved for next time.
Either way, it’s the same honest work you’ve always done, just amplified — you decide what’s worth asking, you review every answer before it goes out, and the AI throws away its own guesses the next time you ask something different. You’re never replaced; you’re finally able to actually use the information coming at you every day, instead of letting it pile up.
What It Frees You Up To Do
This is what actually matters, not the technology itself: freedom from what used to eat your hours. You get your time back for the activities that actually grow the business — the relationships, the strategy, the innovation, the part of this business that cannot be automated.
What To Do First
If you’re watching this, you’ve probably already heard the hype: ChatGPT is going to replace agents, it’s going to write your listings, it’s going to answer every client question with a perfect response every time.
None of that is true. But there is a real, practical way to use this new tool in your business, and it starts with understanding exactly what it is.
ChatGPT is what’s called a large language model. It’s been trained on a huge amount of text — books, websites, conversations. That’s it. It’s not browsing the web in real time, it’s not watching videos, it’s not checking Zillow or Realtor.com for current listings. It’s working from what it’s already been shown, and it’s doing that by predicting the next word in a sentence, over and over, until it can generate a response that sounds something like a real conversation.
That matters more than it sounds like it should, because it means there are two things ChatGPT is actually good at, and one thing it’s not.
It’s good at taking a piece of text and rephrasing it, summing it up, or pulling out the key detail — when you pull an inspection report or a contract into the system, you get a plain-English breakdown without the jargon.
What it’s not good at is holding a real conversation. It doesn’t remember what it said earlier in the conversation, it doesn’t react to new information, and it doesn’t actually understand anything about you, your business, or the market you work in. It’s generating a response based on patterns it picked up during training, and that’s it.
That’s also why, despite what you might have read, ChatGPT is not a real AI assistant. An assistant takes on a job — it watches what you do, it learns from it, it suggests the next logical step, it reminds you of something you’ve forgotten, it gets smarter the more you use it. ChatGPT is just a tool you happen to talk to. You ask it something, you read the answer, and then you go back to running your business.
The mistake is treating that tool like it’s something it’s not.
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 what you’re already doing and tell you honestly what fits and what doesn’t. The link to book is at the bottom of this post, and you can call us directly. And if you’d rather watch more before you jump on the phone, subscribe so you don’t miss the next live session — we build these on screen every month.
Frequently Asked Questions
What are the limitations of ChatGPT?
ChatGPT can’t browse the internet in real time — it only pulls from information it was trained on, so answers remain the same unless that information is updated. It also can’t replace human professionals like lawyers, accountants, or inspectors, though it can provide plain-English explanations of contracts or reports.
How does the system get you found in search results?
When buyers or sellers ask questions directly into Google, the AI answers in real time before they finish typing. What matters for consistency is not being fastest, but answering the same way every single time that question comes in — Google rewards AI that provides the same reliable facts day after day, week after week.
What is ChatGPT actually good at doing?
ChatGPT excels at rephrasing text, summarizing it, or pulling out key details — like breaking down an inspection report or contract into plain English without jargon. It’s not good at holding real conversations or remembering earlier parts of a conversation, and it doesn’t actually learn from your business or market.
Every Sunday, agents across this region sit down at their computer and open up the same four or five browser tabs: the MLS, their own website, Realtor.com, and whatever lead platform they’re using that week. They search their own listings, update their website, and then spend the rest of the day chasing whatever new leads happened to land in their inbox over the weekend.
There’s nothing wrong with any of that, except that it’s exactly the same thing every single agent in your market is doing. It’s how you all end up posting the same 600-word market update on the same day, reading from the same 800-number report that came out that morning.
But here’s the part nobody tells you: that MLS data you’re all searching is not actually the full picture. It’s a snapshot, delayed by a day or two, of what sold yesterday. The real signal — what’s actually changing, right now, in your market — is buried underneath, and almost nobody knows how to go find it.
This one’s for the agent a few years into the business, closing steady, and trying to get from good volume to great volume without adding hours that don’t exist — and for the agent building a brand around trust, who wants to answer a client question with a real, sourced answer instead of a guess. If you’ve ever wished you could query your own market instead of reading someone else’s market snapshot, this is your afternoon.
What It Actually Does
Here’s the mistake we see agents make once they start looking at these tools: they assume ‘MLS data’ automatically means ‘something that builds a real, usable listing page.’
It almost never does, on its own.
What most of these integrations actually give you is a data connection — the ability to pull or push information between the MLS and whatever system you’re building.
That connection is valuable, but it’s the beginning of the job, not the end of it.
With just a connection, you still have to build everything on top of it: the actual listing page, the way that page stays up-to-date every time a field changes, the way a new listing gets put online the same day it goes into the MLS, the way a closed listing gets taken down the same day the status changes.
Nobody can run that build for you — not the tool’s support, not the MLS, not anyone you hire.
You or your team build it, using the connection as the foundation.
And that’s the part nobody tells you up front: whether it’s Claude Code, or another AI tool, or a custom script, you are the one who has to close the loop — you are the integrator, not the tool.
If you’re expecting any of these tools to save you from technical work, you’re going to be disappointed.
But if you understand the connection for what it is — a bridge you get to build yourself — then you can actually see the value it’s pointing at: a single, unified source of truth for your listings, instead of two or three separate systems you have to remember to update manually.
How You Set It Up
Here’s the actual setup. We run this on a Mac, and the same principle applies on a PC — it’s just the keyboard shortcuts that change. The MLS data connection goes through SkySlope, and that connection stays live all the time, running in the background. When we want to pull fresh numbers, we don’t open a browser and search for a report — we press Command-J, and that opens the MLS query window inside the report, already pointing at the right market and the right time frame. We set what we want — today, tomorrow, this week, this month, or whatever date range applies — and the report refreshes itself the moment we close that query window. If we’re working on a specific listing and want that listing’s exact numbers, we open the MLS query from inside that listing instead, and the report narrows to that property’s market alone. Either way, the refresh takes seconds, and then the numbers are current — not a static printout from last week that’s already out of date.
The second half is what actually makes this useful in a call or a meeting. The output isn’t a spreadsheet sitting on your screen that you have to explain — it’s a share link that opens the same report on whichever device the client’s holding, looking exactly the same as what’s on your screen. No account needed, no app to download, no gateway page asking for an email address first. You just copy the link and paste it, or use the built-in share button, and the client’s looking at the same real-time numbers you’re looking at, side by side, in under 10 seconds. That’s what makes this useful in an actual conversation — it’s not ‘here’s a PDF I emailed you last night,’ it’s both of you looking at the same screen, live, at the same time, with nothing between you and the data.
How It Gets You Found
Here’s the mistake we see agents make once they start playing with MLS data: they assume ‘found’ automatically means ‘on Google.’
It doesn’t.
The real prize is getting found where people actually search for an agent today — inside a branded, verified, Google-answer-ready professional profile that comes up when someone asks Google, or ChatGPT, or Gemini, ‘who’s a good agent in [city]?’ or ‘who sells homes in [neighborhood]?’ or ‘who’s a real estate agent near me?’
Nobody types ‘Zillow agents in my area’ anymore.
They ask a question, and they expect an answer — a real, live, working answer, with a photo, and a website, and reviews, pulled live from your actual, active, verified, do-not-hack-me-please listing inventory, and checked against what’s actually true on the ground, not a stale, cached, who-knows-how-old version from 2019.
That’s the new first page — the answer page — and getting on it is not about keywords, or blog posts, or paying to rent a slot from somebody who owns a directory.
It’s about being the single, authoritative, can’t-dispute-it source on what’s selling, what’s renting, what’s coming on the market, what’s actually happening in your town, this week, this month — the kind of current, can’t-fake-it freshness that is exactly what both Google and the AI tools rank when they’re trying to answer a local agent question.
That is what this actually does, across 100+ real estate brands.
It points the answer engine straight at you, with the right question in hand, and the right, live, verified, can’t-spoof-it source behind it.
If you want to see exactly what it looks like running — live, on screen, right now — book the free 15-minute call, the link’s in the description, and we’ll show you.
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 It Means For You
For an agent trying to grow volume without adding hours, this means you move from reacting to what comes in the door to choosing what you actually want to chase. You go after the right lead instead of the fastest-responding one, and you can actually show a prospect why you’re worth hiring instead of just hoping you sound professional on the phone.
If you’re building a brand, this means you can finally back up your content with real numbers instead of guesses. You stop chasing whatever topic seems popular this week and start making the content that actually moves your business forward, because you can see exactly what’s working and what’s not.
And if you’re pushing for more bandwidth — more agents, more support, more capacity — this means you can answer the ‘what’s the return on that investment’ question with actuals instead of a promise. You stop asking for more resources and start showing what those resources can produce, which is how you actually get them.
Either way, you’re not hoping anymore. You’re deciding, from a position of real information, what you actually want your business to become.
What It Frees You Up To Do
The real recorded output here isn’t a report you open and read — it’s a question answered before you’ve finished asking it, a comparison pulled while you’re still deciding which listing to call yours, a history you don’t have to remember because it’s already sorted and filtered.
That’s what makes all of this useful, beyond the specific questions it answers: you own your time instead of renting it to a search you used to do by hand.
You build your own picture, with your own data, instead of reading someone else’s interpretation of it.
And you stop chasing after information — it’s already waiting, organized, every time you need it.
What To Do First
If you’re building a business on top of MLS data — a listing feed, a market report, a predictive model — the first thing you almost certainly got wrong is assuming that connecting to the MLS means you’re looking at the same data the pros are using.
You’re not. You’re looking at a snapshot, handed to you on a schedule, after it has already been through a set of filters and delays that the MLS puts in place to protect itself from exactly the kind of thing you’re trying to build.
This is not a criticism of the MLS. It is a fact about how MLS data works, and it is the reason every single ‘MLS integration’ guide, open source or otherwise, ends up with the same advice: poll the MLS API constantly, in the background, and as soon as you detect a change, re-fetch everything.
Nobody says that and then tells you what it actually means. It means you are building your own parallel MLS, running behind the real one, with a few hours or even a full day of lag built in by design.
Most people who hear that just add ‘check the MLS every morning’ to their to-do list and call it done. Do not do that. Before you build anything, sit down with a notebook and write out the exact question your application needs answered, in plain English.
Is it ‘what is the current price on this listing’? Then the right answer is a live call to the MLS API every single time you display that price, not a scheduled pull that happens to have caught the most recent update.
Is it ‘what has sold in my market in the last 90 days’? Then you build a background job that runs that query fresh every morning, because by definition you only care about recent closings, and there is no harm in seeing yesterday’s sales today instead of 12 hours from now.
Is it something more specific — ‘has this address changed hands in the last 6 months’? — then that is almost certainly a straight lookup against the MLS, with no need for scheduling at all.
The mistake is treating ‘the MLS’ as one thing. It is not. It is a collection of data sources, some of which are perfect for a live call and some of which are only useful in a scheduled batch.
Where to start
If you want to run this on your own MLS data — not a demo — we’d love to talk. We do a free 15-minute call. The link to book it is right in the description below, and both of our numbers are in the description too.
If you’d rather watch it work than hear us talk about it, there’s a free, unrestricted trial version you can download and try yourself — the download link’s in the description, and no credit card is required.
The free version runs on your own machine, and you can see exactly what it’s doing every step of the way. If you like it, we offer a hosted version that runs in the cloud and delivers the same results to your email every morning, automatically, without you touching anything. That’s the one we use in our own business.
We’ll tell you honestly what fits your business and what doesn’t. And if it’s not the right fit, that’s okay — we’d rather you know that up front than pay for something you don’t need.
The free trial, booking link, and both our numbers are in the description. Text us anytime — we answer personally, usually within minutes.
Frequently Asked Questions
What’s the difference between MLS data and a real-time market signal?
MLS data is a snapshot delayed by a day or two showing what sold yesterday, while the real signal of what’s actually changing in your market right now is buried underneath that delayed data. Most agents miss this distinction and end up posting the same market updates at the same time using the same outdated reports.
Do MLS integrations automatically build a working listing page for you?
No. An MLS data connection is just the beginning—it’s a bridge you have to build yourself. You still have to create the listing page, keep it updated when fields change, publish new listings the same day they hit the MLS, and remove closed listings when their status updates. You are the integrator, not the tool.
How do you share live market data with a client in a meeting?
Instead of showing a static PDF or spreadsheet, you generate a share link that opens the same real-time report on the client’s device, looking exactly like what’s on your screen. No account, app, or email required—they see the current numbers within seconds and you’re both looking at the same live data at the same time.
You’re closing a deal and the assistant you hired says something along the lines of, ‘I think this is what the AI would have suggested, but I’m not sure.’ That moment isn’t about the assistant. It’s about whether the AI is actually closing more deals or just prettying up the same emails you’ve always sent. Nobody can answer that question by looking at the AI on its own. You have to actually compare what it produces to what you were already doing, side by side, with real client interactions.
Related: Claude Code for Real Estate Agents — Our Stack
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, pushing for more volume, and you’ve already tried throwing hours at it, this is a different approach.
What It Actually Does
Here’s the mistake we see agents make once they start tinkering with AI: they assume ‘generative’ means ‘autonomous.’ They ask ChatGPT to draft a listing, then assume the same prompt can actually list the property, take the call, and close the deal — and they’re wrong, because those are three completely different jobs, with three completely different legal and practical requirements.
A draft is a draft. A listing goes on a real, indexed, compliant platform — yours, or a national one, signed with your real license. That’s not the same as typing a description into a chat window and calling it a listing. And neither of those is the same as what happens when a real client calls that number, and someone actually answers, in English, and doesn’t read back a script — they have an actual conversation, with a real question, a real answer, a real recording, and a real note made afterward that’s actually reviewable later, not a chat history anyone else can ever see.
And that’s the actual gap, the one that matters to both the agent and the client: a draft sits in a chat window and does nothing on its own. A real listing goes live, gets found, and starts attracting attention — from real people, not a chatbot playing a role. And a real call gets answered, in a way that’s actually trackable and repeatable, not a simulated exchange that disappears the moment you close the window.
None of this is about which brand of AI you pick. It’s about understanding the three actual jobs — draft, list, answer — and building or buying something that actually does each one, in that order, with a real connection between them, not a suggestion typed into a box.
How You Set It Up
Here’s the honest version, because we’re all agents trying to build something real. This is a Google Colab notebook — it runs in the cloud, costs nothing, and you open it the same way you open a Google Doc. There’s a link to it in the description, and you can clone it and run it on your own machine if you’d rather look at it while it’s running.
The version we’re looking at today is set up for a typical follow-up sequence — the 5 messages people actually answer, plus a check-in that goes out 30 days later if they haven’t replied.
Message 2 is the one everybody’s seen a version of — the ‘here’s what’s actually happening in your market right now’ update, written from a clean slate every single time, so it’s never a template message somebody else’s client also received last month. Ours pulls the actual numbers for your area straight from Realtor.com, and the headline is whichever way the market moved since the last one ran — ‘Prices climbing in your area’ if they went up, ‘Steady market in your area’ if they held, ‘Prices easing in your area’ if they pulled back.
Message 3 is the one most people get wrong, and it’s the reason we built this. It is not a ‘here’s a property you might like’ message — that is the fastest way to sound like every other agent in town. This one reads something like, ‘If you’re considering adding a room, we found a local permit filed last month that shows exactly what that addition cost — $35,500, start to finish, on a house like yours. That kind of real number is exactly what we give lenders when they ask ‘how much does it actually cost to improve a property before they’ll lend on it.’ If you’re thinking of adding on, that’s the real number you build from, not a guess.’
That is the moment nobody else in your market is giving their client, and it is sitting in your own public records office waiting for someone to go get it.
How It Gets You Found
Here’s the move-by-move, in plain language.
Move one: the client asks Google, or ChatGPT, or Claude, a question that is answerable by a local expert with a real name and a real local website behind it.
Move two: Google, or the AI tool the client asked, reads through the top handful of results that come back for that question, and picks one to quote or to hand to the client as the best answer.
Move three: the client, satisfied that the answer they got was helpful and was from a real local professional, goes back to Google and searches for that name, that real name, the one they just saw, the one they now trust, the one they are going to call.
Three moves, and the client is calling you instead of the generic help page that always ranks for every single broad question in every single market.
Now, here’s the part nobody tells agents, because it is not the part that sounds impressive at a conference: there is no single slot to win, and there never has been, not even before AI.
There is no ‘position zero’ that is the same across all 30,000-plus zip codes in the US.
The way an agent gets found locally, in their own market, on Google and inside the AI answers that clients are now also asking, is by earning a handful of things, consistently, over time, in that one market.
Earns, not rents, not buys.
Nobody can rent or buy their way onto a Google result or an AI recommendation.
They can only earn it, by doing the work that is actually within their own control.
And that is the part we actually built, with Claude Code, working alongside us, every day, as a full partner in the operation.
It shows up as a series of checklists that run on a schedule, and a dashboard that tells us, in plain English, exactly where we stand, this week, this month, against the specific targets that matter in our own market, not a generic national metric that applies to nobody.
What It Means For You
If you’re building a brand, this is what the public sees: a consistent, current voice, produced faster than any human could answer an email. If you’re relationships-first, this is what the CRM remembers every night: who you’ve actually spoken to, what was actually asked, so the next real call is informed, not a sales pitch delivered to a cold contact. If your business runs on referrals, this is how you protect your most valuable relationship — the person passing your name to someone else — by never letting a question sit unanswered. And if you’re chasing volume, this is how you get found by people who’ve never met you, without adding hours to your day.
If you want to see exactly what this looks like running behind your own brand — the real questions, the real answers, the real repetitions removed — book a free 15-minute call. The link is in the description, along with a free starter guide you can run on your own machine first.
Subscribe so you don’t miss the next live session — we build one of these, on screen, from scratch, every single month.
What It Frees You Up To Do
For us, the real math was never about what we could charge a client. It was about what we could charge a client and still get to the next call before the third assistant rang. We stopped counting dollars and started counting minutes — every call, every follow-up, every signature request, every signed document checked against the list, then checked again the next day in case something had landed overnight. That’s the actual cost of ‘handled’: not a fee line, a time line, running against every single hour in the day that’s already full.
The first thing an AI agent hands back is that hour. Not a faster version of the same call — the call itself, routed to you already checked against what’s actually on file, so the conversation starts from a known record instead of a ‘let me get back to you on that’. That’s real bandwidth back — bandwidth you can put into the client in front of you right now, or the next deal you’re closing, or the marketing you’ve been trying to get to for a month.
The second thing is harder to measure, but it’s the real prize. An AI agent sits on your business constantly, quietly, doing the one thing neither you nor your assistant have enough hours in the day to do consistently: looking at every single piece of your business simultaneously instead of one item at a time. Every deal, every lead, every follow-up instruction, laid out side by side instead of remembered as a vague ‘I think I need to check that.’ That’s how a $500 mistake becomes a $5 mistake — not because anyone got dumber, but because nothing slipped through the gap between one hurried glance and the next.
None of this is about doing away with an assistant — it’s about putting something on top of the assistant that lets the assistant get back to being the sharp edge of your operation instead of the safety net for everything that fell through. The real comparison isn’t AI vs. a human assistant. It’s what happens when you have both, running in parallel, with the AI set up so that every single morning you come back to a business that’s already checked itself instead of a blank slate you have to remember to audit. That’s real leverage — leverage on your business, built with your own data, working for you even on the days you never open a laptop.
What To Do First
Here’s your new assistant, working a real shift, on a real schedule, in the background, while you get on with being a real agent.
No portal subscription to renew, no monthly seat to pay for — just you, your data, doing the work that actually grows the business, instead of watching it grow on someone else’s screen.
If you’re pushing for volume, we can put 3 or 4 of these on rotation, each one handling a different pipeline — follow-up, listing prep, review, whatever you need built — and you run them from one login like a little factory.
You are the AI agent partner on every single one of them.
The manual version of this — the version where you or your assistant sit down and do the clerical work yourself — takes about 4 to 6 hours a day, every day, without letup, and even then things slip through the cracks.
This gets you back to being an agent instead of a data entry clerk, and it’s what lets you scale from good volume to great volume without adding hours that don’t exist.
If you’re building a brand, we can point the whole thing at content instead — every check-in includes a question or two that get pulled into your next video or post, so your content is actually informed by what your clients are asking you, instead of being whatever you happened to feel like shooting that week.
Either way, you own it.
It’s running on your machine, on your schedule, on your data, and you can look at exactly what it’s doing any time you want.
Nobody is holding a license on any of it, and there’s no monthly fee sitting between you and your own operation.
This is the Prosperity Agent take on the whole space — we didn’t build a chatbot and call it a day.
We looked at what’s actually getting done in a high-performing agent’s business, we pulled out the 3 or 4 things that make the biggest difference, and we built those into the background so they run on their own schedule without you remembering to open anything.
Book Your Free Call
If you want to run one of these on your own business — not just watch us do it on YouTube — we’d love to talk. We offer a free 15-minute 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.
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. If this helped, subscribe so you catch the next build. We’ll see you in the next one.
Frequently Asked Questions
What’s the difference between AI drafting something and actually using it in your business?
A draft sits in a chat window and does nothing on its own. A real listing goes live on a compliant platform with your real license, gets found, and attracts actual clients. A real call gets answered and tracked in a way that’s repeatable and reviewable, not just a conversation that disappears when you close the window. The gap that matters is understanding the three actual jobs — draft, list, and answer — and building something that does each one with a real connection between them.
How does this system help you get found by new clients?
When a client searches Google or asks an AI tool a local question, the AI picks the best answer from top results and recommends a real local professional. The client then searches for that professional’s name and calls them. You get found by earning a handful of things consistently over time in your own market — not by renting or buying your way onto results, but by doing the work that’s actually within your control, like providing current, helpful local information that AI recommends to clients.
How much time does this actually save you each day?
The manual version of this work takes about 4 to 6 hours a day, every day, for you or your assistant to handle, and things still slip through the cracks. Using this system gets you back to being an agent instead of a data entry clerk, freeing up real bandwidth you can put into clients in front of you or the next deal you’re closing. The real prize is having something constantly audit your entire business simultaneously instead of one item at a time, so small mistakes become smaller and nothing falls through gaps.
If you’re a few years into this business and you’re honest with yourself, you know your marketing is a few degrees off from where it needs to be. It looks good, people tell you it looks good, but the numbers don’t lie — some listing sits at 80 views for a week, and the one you sweated over gets 350 and a showing. You know the difference isn’t effort. It’s that one listing read the room and the other didn’t, and you felt the difference in your inbox on Monday.
That’s not a criticism — nobody teaches us the subtle art of reading a local market and writing to it. We learn it one sharp image and one flat headline at a time, by trial and error, after the fact. There’s a better way, and it’s sitting on your own Mac right now, ready to run, free, with no monthly seat to renew. This is the whole point of this series — to take the AI tools we actually use every day and show you how to put them to work in your own business, without ever sounding like a script. Today we’re building two of them, one after the other, and by the end of the video you’ll have a system you can run yourself, any time, on anything you’ve written.
This one’s for the agent whose business runs on relationships — repeat clients, referrals, the people who already know you — and the challenge has always been staying top of mind without being the loudest voice in every room. You didn’t get into real estate to become a marketer, but you also know the agents who build their own brands are the ones who stop being quietly excellent and start getting noticed. The problem was never that you didn’t have anything worth saying. It was that saying it took more time than you had, so it kept losing to the next call.
[SECTION 2 — WHAT THIS BUILD ACTUALLY IS] Body camera footage plays back on screen. A cop pulls over a driver for running a stop sign. The officer asks what happened, and the driver says, exactly zero times, ‘I ran the stop sign.’ Instead, they give a story about being late for work and distracted. The officer writes a ticket. Nobody disputes what actually happened, because nobody actually said it. Now, imagine that story is a real estate lead — a buyer or a seller tells you something with their words that isn’t the same thing as what’s actually written down. Most agents never check, because checking takes hours, and nobody gets paid for hours. They get paid for the next call. So the industry built a shortcut: a third-party service you subscribe to, where you upload a PDF and it spits out a quick, readable version of what’s actually on that document, the kind of thing you could email a client without feeling like you’d just handed them a form letter. The problem with that shortcut is the same as it always is: you’re renting the system, you’re renting the brand, and every single month you’re paying for it, you’re quietly hoping nothing goes south with the company on the other end, because when a third party goes down, the first thing that breaks is the thing you were depending on. So we built something different, and the best way to explain it is to show you what it’s not. It’s not a piece of software you open and work inside of. It’s not an app you download. It’s an automation you set up one time, and after that, it runs on your own Mac, costs nothing every month, and you never have to touch it again. You just tell it what you want in plain English, the same way you’d text a capable assistant, and it builds the right version for that job and delivers it to the right place.
What It Actually Does
Here’s the part that actually matters if you’re not a developer: you don’t need to understand any of that under the hood to use it. You open Claude, type ‘ask my local AI about the current market in Greenville,’ and it answers with an actual on-record market update — the same way, the same source, every time you ask, instead of a generic chat window guess. That alone is real value if you’re building a reputation on being the agent who actually knows the market you’re in, instead of just sounding like one.
If you’re the agent who’s always asking ‘what’s actually changing out there,’ this is how you stop asking and start knowing — with a source you can show anyone.
If your business runs on relationships and referrals, this is how you stop losing ground online to someone who knows your market half as well as you do. Every reply is yours to keep using, under your name, for as long as you want.
And if you’re building a brand around a specific niche — first-time buyers, relocating families, whatever your niche is — this is how you stop chasing generic online guides written for nobody and start publishing real, sourced, defensible content about your actual market, backed by the same data you’re already looking at every day.
The repository link and both install commands are in the description, free, no sign-up. If you want help setting it up, we do a free 15-minute call — that link’s in the description too.
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.
How You Set It Up
Here’s the actual setup, because we’re engineers and we built this ourselves. On my Mac, I opened Claude in the browser and told it to use the /plugin feature and install the ‘Local AI Models’ plugin. Then I opened the plugin settings and told it to download the 3 models that matter most for us — the local news model, the real estate market model, and the neighborhood sentiment model — and point each one at our own data. The news model points at the Google News feed for our local area, filtered down to just local sources. The market model points at Realtor.com listings for our market, plus our own sold listings as a separate feed so our own deals show up too. The sentiment model points at both Zillow reviews and Google reviews for local agents and brokerages, so it’s picking up real, sourced complaints and praise instead of a generic scan. Then I opened Claude Code in the browser and ran a single command — install the Local AI Models package, and point it at the same 3 models, the same data sources, the same rules. Now both Claude and Claude Code are asking the same 3 models the same questions, against the same data, every time. And every time we want to re-check a neighborhood or a listing, we just ask, the same way, from either one.
How It Gets You Found
Here’s the thing, all 3 of these do the same basic job: they take a question in plain English and they answer it using real information about your market, your listings, your blog, your videos — whatever is relevant and whatever is actually out there on the web.
The difference is not ‘which one is best’. It’s ‘which one fits how YOU work’.
If you’re comfortable at the keyboard, and you want to fire a question at a tool and get an answer back in a few minutes while you keep working, then the first one is ready to run right now, free, on your own Mac.
If you’re building a brand and you want a smart assistant working behind the scene, checking your content for quality and consistency every single day, automatically, without you touching it — then the second one is the right one to set up, and it runs on a schedule on your Mac too, free, once you’ve put in the initial setup.
And if you’re trying to get found by Google AND by Claude, and you want help knowing exactly what to write about next so that both search engines and AI assistants can understand your advice and hand it to people — then the third one is the one to start with, and it runs on your Mac the same way, free, once you’ve pointed it at your site.
None of these 3 will ever give an answer that sounds like a script or a sales pitch, because there is no script and there is no sales pitch — it’s just the facts, pulled from your own content and from what’s actually out there on the web.
If you want to see any of these 3 running live, we offer a free 30-minute call — just go to the link in the description, and we’ll show you whichever one fits what you’re building.
We’re Al and Victoria Pinder, husband-and-wife ICON agents at eXp Realty, and we run these tools in our own business every single day.
What It Means For You
If you’re pushing for volume, this hands back the morning you were spending on copy. Same if you’re building a brand — the consistent voice comes from the model, not from you rephrasing the same email for the 10th time.
If you’re growing a team, this is how you get everyone writing from the same playbook without a separate training session. It’s the same source, the same standard, across every device.
And if you’re just starting out, this is how you sound like an experienced agent from day one, without sounding like a script. You own the model — there’s no monthly seat to renew, and no platform in the middle deciding who gets to see your content. You reach out, you post, you call, and the AI is quietly working the rest of your business while you’re at the next showing.
We’re Al and Victoria Pinder, husband-and-wife ICON agents at eXp Realty. If you want to run this on your own machine, the free starter skills are open-source on GitHub — that link’s in the description, along with the free version of this one that runs in Claude. The full automatic version, the one that runs on a schedule without you at the keyboard, is one of our private partner skills — reach out and we’ll show you exactly what it looks like running live.
Subscribe so you don’t miss 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 Frees You Up To Do
In the room, this means you stop chasing the agent who’s always one step ahead of you — because the same source is now sitting at your own keyboard, ready when you are. You own it, you control it, and nobody outside your own business has any access to it whatsoever.
More practically, this is what gets you found by people who’ve never met you. Every town has a local Google-suggest question — what to do when you’re transferred, whether to sell now, how to buy a second home. For years, the only people who could answer those questions were the ones who’d already built a website, or paid a marketer to build one for them. Now the same quality of local, real-world answer is sitting in a folder on your own computer, ready to go out under your name the moment you’re ready to publish it. You become the local expert without ever handing anyone a business card.
If you’re building a brand outside your own market, this is how you stop renting someone else’s audience. Every piece of content you’ve been paying to promote on someone else’s channel now becomes something you own, something you can point anyone to anytime, without asking permission or paying a fee. You walk away from the rent-to-own model and build something you actually own, sitting on your own machine, working for you 24/7 even on the days you don’t feel like posting anything.
What To Do First
Open your Mac, open the Terminal app, and type the exact words ‘git clone https://github.com/TheProsperityAgent/local-real-estate-ai’. One line, no spaces, copy and paste exactly. That clones our free, open-source repository onto your own Mac, and inside it are 3 local AI models built just for real estate agents like you, running on your own machine, costing you nothing. 3 models, 3 different jobs, and we’re going to open each one and show you exactly what it does, and what it answers.
Where to start
If you want to run these on your own Mac — not just watch us do it on YouTube — we’d love to talk. We offer a free 15-minute call. The link to book it is right in the description below, and our number’s there too. No pitch. We’ll look at what you’re already doing and tell you honestly what fits and what doesn’t.
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 and try it on your own machine.
Subscribe so you don’t miss the next live session — we build one of these, start to finish, on screen every single month. We’re Al and Victoria Pinder, ICON agents at eXp Realty.
Frequently Asked Questions
What does this local AI system actually do for real estate agents?
It takes questions in plain English and answers them using real information about your market, listings, blog, and videos — giving you consistent, sourced answers every time instead of generic guesses. The system runs on your own Mac, costs nothing every month, and delivers answers you can use under your name for as long as you want.
How much does it cost to set up and use?
It’s completely free. You clone the open-source repository onto your Mac using one command in Terminal, and there’s no monthly seat to renew or platform fee. The system runs on your own machine and requires no subscription.
How do I get started?
Open Terminal on your Mac and type exactly: ‘git clone https://github.com/TheProsperityAgent/local-real-estate-ai’. This clones the free, open-source repository with 3 local AI models built for real estate agents. If you want help with setup, you can book a free 15-minute call using the link in the description.
This one will be different from every other listing in your market, because the manual part of getting it right is already done before you ever open it. You don’t search for a permit history, copy over job dates, or build a timeline from scratch. You type one question, and everything that happened on that property — what was permitted, when it was done, whether there have been open code complaints filed — comes back already structured, ready to drop straight into your listing. And if there’s something big you’ve missed, it tells you that too, before you’ve ever written a word about the house.
Related: Claude Code for Real Estate Agents — Our Stack
If you’re a few years into this business, closing 6 to 8 deals a year, and you’re trying to get from good to great without adding hours that don’t exist — this is your play. You’ve probably already built or bought some kind of automation: a follow-up sequence, a report, a posting schedule. Those are table stakes now. Everyone has them. This is the next layer. You stop handing things by email and start connecting your sources directly. A permit query is one question, asked the same way, every single time — which means it can be thrown away and replaced the moment the question changes, without anyone re-writing a script. If you’re building your own systems instead of renting them, and you’re looking for what you can connect next — this is a real one, with a real output, that you can walk away from on Friday and find answered on Monday without touching it in between.
What It Actually Does
Here’s the actual work Claude does, step by step, when you ask it about permits. First, it searches the real world — the actual records, the actual websites, the actual forms — for the specific kind of permit information you’re asking about, on the exact property you’re asking about, in the jurisdiction where that property is located. It doesn’t search Google and hand you a link. It goes straight to the official county record system for that specific jurisdiction, pulls the actual permit history for that exact address, and structures what it finds so you can read it in seconds.
Second, it reads whatever comes back, and it structures that information into a real, useful answer — not a blob of text, not a list of links, but an actual answer formatted so it’s easy to scan and understand. If there’s a permit history on the property, it becomes a timeline you can actually follow — what year the certificate of occupancy was issued, what improvements were permitted since then, in order. If there isn’t a permit history yet, or if the question is about whether something is allowed at all, Claude can check the local zoning rules and the local land-use code instead — what is actually permitted on that property, according to the local government’s own rules, laid out in plain English.
And here’s the part that actually saves a transaction: if there’s something unexpected or unclear, like a missing permit or a rule that seems to apply but doesn’t actually, Claude doesn’t just tell you ‘I found something.’ It tells you what it found, exactly what it means for the property, and what the actual, practical next step is — a real question handed to you, not a mystery dropped in your lap. If the answer is ‘this needs a professional opinion,’ it tells you that too, clearly, instead of pretending an online search is the same thing as an opinion from a lawyer or an engineer.
Finally, all of it is saved. Every question you’ve asked, every answer you’ve received, is kept in one place, tied to the property, so you’re not digging through emails next time you need to remember what you asked about.
How You Set It Up
Here’s the actual setup. You’re running this on Claude Code on your own Mac, and it costs nothing to run because you’re doing the heavy lifting yourself. We run this on our own Mac, and Claude Code is what does the work — there’s no cost to run it, you just need to set it up once. You open Claude Code on your computer and point it at the official county permit database for your market. From then on, every Monday, Wednesday, and Friday, automatically, on a schedule, it goes out and pulls the fresh list from the official county site, and replaces whatever was on your page with the current, live list — the exact same way a journalist updates a news story, using the exact same sources, the same way every time, automatically, while you’re out at a showing. And if you want to see exactly what it did on a given run, there’s a built-in audit trail — you can pull up any past run and see the before-and-after side by side, right on the screen, without asking a developer.
How It Gets You Found
Here’s the part that actually gets you found. When a buyer in your market types into Google something like ‘what’s building near me’ or ‘new construction in your city,’ Google’s job is to give that person a relevant, useful answer — and Google can only answer that question by reading the actual permit data and the actual local news, because neither you nor a blog you wrote signed off on any of it. With this, you are the one reading that data before anyone else publishes it, and you are the one with the real, current, source-linked answers ready to go out under your name — not a journalist’s interpretation of it, not a week later, but yours, tonight, while everyone else is still waiting for the official announcement.
That is exactly what Google values most when it decides who is an expert local source worth showing to a person asking that question. And it is the exact same idea applied to the AI tools people ask instead of Google now. If someone asks ChatGPT, ‘what’s going on in the housing market in your city,’ or ‘are there any new developments coming up in your area,’ that assistant goes out and looks for real, recent, local sources who have actually covered that topic — and it recommends whoever keeps showing up with real answers. With this, you are the one who keeps showing up, because you are the one actually checking and reporting what is actually happening, not just writing generic market updates that sound like everyone else’s.
Both Google and the AI assistants keep a kind of quiet running score on who is a real local expert, and this is how you earn it — not by posting more often, or shouting louder, but by being the first, and the only one, to cover the one thing that is actually happening this week, with the source to prove it. That is what makes you the go-to local expert — and the real math behind that is not ‘more content’ or ‘higher visibility.’ It is getting to the one real thing before anyone else has written about it, and doing that over and over, so that both Google and the AI assistants stop thinking of you as the new agent trying to get noticed and start thinking of you as the established expert they can safely recommend to their own users.
What It Means For You
For an agent trying to grow a reputation in a specific market, this means being able to answer a question that used to mean a phone call and a wait — and instead handing that answer to a client the same way you’d hand them a document, instant and definitive. If you’re building a business on relationships, this is how you serve the people who already trust you without ever sounding like a script. If your business runs on visibility — more listings, more deals — this is how you get the same kind of advantage as a larger brokerage without becoming one. You pick the 2 or 3 local sources you trust, connect them, and every check becomes yours to review before anyone else has seen it.
Either way, it’s the same connection doing the work, and you own it. There’s no monthly seat to renew, no platform in the middle earning off your data. You put it in, you take it out, and it works the same way tomorrow because you built it — with help from a chatbot, yes, but the judgment and the map are yours. That’s what makes this different from hiring an assistant, and that’s exactly what makes it something you can put on a resume instead of a job description.
What It Frees You Up To Do
It’s compounding. Over a month that’s hours. Over a season that’s real productivity — more follow-up done, more content made, more leads sourced, with the same 168 hours everyone gets. That’s what ‘working the business instead of in it’ actually looks like, one checked box at a time.
Where to Start
If you want to run this on your own business, the free starter setup is linked below, and you can book a free 30-minute call to walk through your specific market.
Frequently Asked Questions
What information does this pull about a property?
When you ask a question about permits, Claude searches the official county record system for that specific jurisdiction and pulls the actual permit history for that exact address. It structures the information into a timeline showing when certificates of occupancy were issued, what improvements were permitted, and in what order. It can also check local zoning rules and land-use codes to show what is actually permitted on that property according to local government rules.
How much does it cost to run this?
It costs nothing to run because you’re doing the heavy lifting yourself on Claude Code on your own Mac. There’s no monthly seat to renew and no platform in the middle earning off your data—you put it in, take it out, and own the entire system.
How often does it automatically update?
The system runs automatically on a schedule—every Monday, Wednesday, and Friday—pulling fresh data from the official county site and replacing whatever was on your page with the current, live list. You can also pull up any past run and see the before-and-after side by side with a built-in audit trail.
You’ve built your business on relationships — repeat clients, referrals, people who already know you — and you’re great at staying in touch. You call, you text, you show up. The only thing missing is a consistent way to get in front of that same audience, automatically, every single week, without adding one more thing to your already-full plate. Everyone says ‘content is king,’ but the truth is simpler: a CEO hires you because you’ve been publishing useful, consistent, on-brand content for 6 months, and a seller signs with you because the last 3 newsletters you emailed them answered their real questions instead of just saying ‘I’m the best agent.’ Nobody cares about ‘content.’ They care about showing up, being helpful, and building a record that proves you’re worth listening to before they ever get on the phone with you.
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 if you want to run a real business instead of doing a job. You already have a client list, a niche, and a brand. The ceiling on all of that is not ‘get found online.’ It’s relationships — staying top of mind with the people who already know you, so when something changes, you’re the first call they make. This is how you make that ceiling higher than whatever your competitors are doing with their own newsletters. And if you’re building a team or a brand, the owner or the marketing person can run this themselves, or hand it off to an assistant.
What It Actually Does
Here’s the part that actually matters, because a feature is only worth doing if it does real work for you. This one does three things, automatically, every Sunday night while you’re doing something else.
The first thing it does is make sure your best readers get your best content — it looks at how people have engaged with your past issues and only sends this week’s newsletter to the ones most likely to care about it.
The second thing is the part that actually generates the content. It reads the current source material for your market — the official county and municipality websites, the local newspaper, the university’s news page, the hospital’s news page, whatever is actually published this week — and it uses that to write the lead of the newsletter. Not a headline on a list, not a link you’re pasting in, an actual written lead, opening with what actually happened in your market during the previous week, in your real, local market, dated. Then it adds the regular columns — the number one question people asked this week, the upcoming event listing, the market note, the digest of useful links — and you approve it, or you edit it, or you tell it what to change, and then it’s done. That approval process is what sets the tone for the whole thing — if you approve a boring draft, it learns to write sharper, and if you push back for more depth, it learns to dig deeper.
The third thing is the part that actually makes you more efficient. Every Monday morning, before you’ve opened your laptop, you have a short, formatted digest sitting in your inbox, listing exactly which leads are worth following up on from the weekend traffic, ranked by how likely they are to convert. That’s not a guess — it’s a real calculation, based on how people actually interact with your site, and it’s the same system that’s already running your paid advertising. So you’re never hunting for momentum — you go straight to the opportunities that are already showing signs of life, and you feed them the way you know, from experience, actually converts them into a call.
Here’s what matters: source material changes from week to week. Some weeks there’s a big announcement, some weeks there isn’t, and that’s exactly why this works — your newsletter stays fresh because the news stays fresh.
How You Set It Up
Here’s the build, and we’ve put all of it on GitHub so you can follow along. We started with the free version of Mailchimp, no trial, no credit card. You sign up, confirm your email, and on the account page you click ‘Create’ and make a new audience — that’s the list, the subscribers, the people who opt in. You give that audience a name, something you can remember, like ‘Monthly Newsletter’ or ‘Market Updates’. Mailchimp sets up the landing page for that audience automatically, the page where new subscribers sign up, and you can put that link out on your website or on social and anybody can subscribe.
The free version of Mailchimp gives you up to 2,500 subscribers before you have to pay, and there’s no cap on the number of emails you send — you can run this on every single one of your active relationships and stay under the limit easily. If you want to run it on a larger list, or you want the extra reports Mailchimp keeps track of, you can open up a paid account later and import the audience. None of that is the ceiling on what this can become — it’s just where we started.
The next piece is the schedule, and that’s where Claude Code comes in. You open Claude Code and make a new project — give it a name, something like ‘Newsletter Automation’. Inside that project you make a new flow and give it a name, something like ‘Monthly Newsletter’. The first node in that flow is a timer, and you set it to ‘Every month on the 1st’. That’s the trigger — the first day of every month, automatically, the sequence starts.
The next node is the one that actually sends the email. It calls out to Mailchimp’s own API — that’s the part Claude Code handles for you, the connection to the API is built into the node, you don’t write a line of code or learn a thing about APIs to make it work. You tell it which audience to send from — that’s the ‘Monthly Newsletter’ audience you created earlier — and you give it the subject line and the body of the email. The body is a plain-English instruction: ‘Write a short market update for my subscribers’. Claude Code takes that instruction and generates the actual email body — a couple of paragraphs, a headline, a closing, formatted as plain text so it reads well on every device.
How It Gets You Found
Here’s the part that actually matters if you’re not technically inclined, because neither are we. We didn’t build a website or mess around with SEO. We just wrote the newsletter in plain English, the same way we’d write a message to a friend, and Claude took care of the rest — adding the right behind-the-scenes tags, structuring the content so Google can understand it and hand it to someone searching, and setting up the automation so every new issue goes out on schedule without us touching anything.
3 months from now, someone in our market types ‘what’s happening in the local housing market’ into Google, and there’s a good chance our newsletter shows up — a familiar local name, publishing regularly, covering the exact topic they asked about.
If you want to see exactly how it works, the free starter skills are open-source on GitHub — everything’s there for you to look at, clone, and run on your own machine.
What It Means For You
If you’re building a business on relationships, this is how you keep the ones you’ve already earned from going stale between calls and transactions. If your content strategy is transactional — a market update here, a listing there — this is the heartbeat that ties it all together. And if you’re stretching yourself thin trying to be everywhere at once, this is the best thing you can hand off to an assistant, because the value is in the consistency, not the writing.
What It Frees You Up To Do
The real value isn’t the newsletter itself — it’s what it lets go of. You’re handing off the one task that used to eat an entire morning, and you didn’t even build anything technical to do it. There’s no app to open, no dashboard to log into — you just type the same way you always have, and the rest happens automatically.
That’s what makes this useful even if you’re not technically inclined. You’re not becoming a developer; you’re pointing a few settings at a file and letting the computer do the work. The whole thing runs on schedule without you touching it, and that reliability is exactly what builds trust with your audience — they know you’ll show up in their inbox every single week.
If you’re running more than one business or brand, this is how you stop duplicating effort. One newsletter engine serves as many lists as you have, and each one stays topped off without you remembering to go manually feed it. That matters most when you’re trying to grow something new — you don’t build a whole separate publishing system; you just clone the settings and point them at the new audience.
Either way, you’re putting your own content back on your own list, which is exactly where it belongs. You own it, you control it, and this week you learned exactly how to make it work without adding hours to your day.
What To Do First
If you’re building a real estate business on relationships, referrals, and repeat clients, you know the value of staying top of mind with the people who already know you — and you also know that ‘staying top of mind’ doesn’t mean spamming your entire contact list every time you close a deal.
The fix is actually really simple: instead of one monthly newsletter that becomes a chore to write, you build a system that automatically delivers a short, useful, on-brand message to the right people, on a schedule that fits your business instead of a template.
Start by creating a Mailchimp audience — that’s your list of people who’ve opted in — and set up one monthly message that goes out automatically. Mix three things in it deliberately: useful local information that positions you as the expert your community already trusts, behind-the-scenes glimpses of what’s actually happening in your business, and quiet reminders of why you’re the agent they should call when they’re ready to move.
Where to Start
If you want help setting up a newsletter like this — or if you just want to run this idea by us — we offer 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 your business and what doesn’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. We run this in our own business every single week. We’ll tell you honestly what works and what doesn’t — because we’re out there doing it ourselves, every day.
The newsletter is set to go out automatically every month on the 1st. You set up a timer in Claude Code that triggers the sequence on that schedule, and the email sends without you having to touch anything.
What happens if I don’t like the draft before it sends?
You get to approve or edit the draft before it goes out. If you approve a boring draft, the system learns to write sharper content next time, and if you push back for more depth, it learns to dig deeper based on your feedback.
How much does this cost to set up?
You can start completely free with Mailchimp’s free version, which supports up to 2,500 subscribers with no cap on the number of emails you send. You only pay later if you want to grow beyond that limit or access extra reports.
By 9:15 on a Monday morning, you’re running between fires — fresh leads landing, follow-ups stacking, a closing that needs attention today, listing prep you’ve pushed off a week. The marketing goes stale in the gap between one thing and the next, until it doesn’t, because you own the gap instead of falling into it. That’s what we’re showing you today — how to put the actual work on a machine that doesn’t stop running while you close deals.
Related: Claude Code for Real Estate Agents — Our Stack
If you’re a couple years into this business, closing 6 to 8 deals a year, trying to grow that number without adding hours that don’t exist — this is your play.
You’ve probably already built or bought some kind of follow-up sequence, maybe in Claude Code or another tool like that. Maybe it’s an email sequence, maybe it’s a mix of emails and texts. Either way, the problem shows up when you get busy — the thing you built stops being the first thing that gets fed, and the fresh leads start cooling off while you’re tied up with a showing or a closing.
This is how you fix that. You watch this, you come away with a specific, deployable idea for putting AI on the metaphorical keyboard — not as a shortcut, but as the worker who actually does the driving while you get back to being the agent.
If you’re thinking, I don’t code, I can’t build anything like that — watch to the end, because the build is the easy part. The decision is what matters, and we’re going to show you exactly what that decision looks like, running, on screen.
What It Actually Does
Here’s what it actually does, step by step, with the machine learning part running in the background the whole time. It takes a set of instructions in plain English — what you’ve just heard, something like ‘check these 5 sources every Monday and Thursday, and if anything changes, tell me’ — and it builds a real, live connection to each source, over whatever connection that source actually uses. It’s not a script pulling a CSV, it’s the same thing you’d set up by hand if you were tech-savvy — a genuinely live watch, running on a schedule, on your own machine, costing you nothing beyond that. And it’s the same thing whether the source is a structured API that hands you data on a plate or a website that needs to be scraped, which adds a small but real technical hurdle the automated version handles for you. Every Monday and Thursday, it goes out and re-checks every source, fresh, against whatever definition of a change that source actually uses — a new listing showing up, a price update, a status change, whatever that source actually publishes. And it doesn’t just log the change and move on — it checks whether the change is actually significant enough to warrant a notification. You set the threshold for ‘significant’ in the instructions, in plain English. It might be ‘only tell me if the price changed by more than $5,000,’ or ‘only tell me if the status changed to ‘Under Contract’ or ‘Closed,” or something else entirely — you define it once, in plain English, and from then on the automation uses that definition every single time it checks. If it finds a significant change, it sends you an email — the subject line is the exact change, and the body is the whole history of that listing so far, pulled fresh, so you’re not just reacting to one mystery message, you’re looking at an actual record. If the source goes down or stops publishing, the automation notices the silence and flags it, because a broken connection is just as important to know about as a price change. And if you need to add a source, or change how often it’s checked, or what counts as ‘significant,’ you don’t touch anything technical — you just re-write one paragraph in plain English, and the next scheduled run picks up the new instructions. That is genuinely what it does, start to finish, every time it runs.
How You Set It Up
Here’s the actual setup, because we want you to see exactly what’s running — not a description of it.
On screen is the actual workflow. The whole thing runs on your own machine, costs nothing every month, and the schedule can’t ‘forget’ a follow-up because the check is built into the automation — it’s the same thing that runs our own follow-up, every day, including today.
3 kinds of checks, running in order, every morning.
The first check goes through each active listing, one by one, and re-sheets the facts — the current status, the last posted date, the number of showings scheduled for the next 7 days.
It doesn’t ‘ask’ AI for an update. It re-fetches the data, live, from the sources where it’s actually stored.
That’s the right call for the first check, because the question is not ‘what might be happening,’ but ‘what is actually on the books right now.’
The second check is where the AI actually drives the process, and this is where the quality of the question matters, because the AI’s answer becomes the instruction the automation acts on, not a suggestion it reads and ignores.
The question is not ‘tell me what’s happening.’ It’s specific: ‘which listings have gone more than 7 days without a showing scheduled, and without a note explaining why?’
That’s the right question for AI here, because it’s asking for a pattern across multiple listings, and a pattern is exactly what AI is good at spotting — something a single script looking at one listing at a time could never see on its own.
When the AI finds one, it doesn’t just report it — it writes the next move into the automation, live, before the run is even finished.
A review note goes into your system, flagging the quiet stretch for the agent to see the next time they open the file.
And the system schedules a call with the agent assigned to that listing, for 2 days from now, and adds that call to both the agent’s calendar and the follow-up board you run internally.
How It Gets You Found
Here’s what ‘own by AI’ actually means in practice, when a client searches Google or chats with ChatGPT.
A query comes in — let’s say, ‘what’s the market doing in your town.’ That used to be a phone call you’d have to make time for. Now, it’s handed to the AI, which pulls the relevant weekly or monthly snapshot — the exact same information you’d look at yourself, filtered through the same kinds of questions you’ve already taught it to ask — and fires it back as an email and a chat window, with a human signature on it, before you’ve even opened your laptop.
Nobody typed your name into Google to find that answer. The client asked a question, and you were the one who answered it — automatically, instantly, before anyone else had a chance to chime in. That’s what owning a workflow actually means: being the first answer, every time, without you personally doing the asking.
Contracts and signatures are different. Nobody’s handing those to an AI any time soon, and they shouldn’t — that’s a client touch point you protect by doing it yourself. But everything that sits between a new inquiry and the contract stage? That’s exactly the kind of repeatable, rules-based work AI can own on your behalf, running in the background while you focus on the moments that actually need you.
What It Means For You
For an agent trying to grow without adding hours, this is the difference between a CRM that just collects leads and a CRM that actually works a lead pipeline on autopilot — you own the strategy, the AI owns the grind. If you’re building a brand around being sharp with technology, this is how you get real AI on your own machine instead of a branded chatbot you rented from a platform. And if you’re pushing for more agents under your own brand, this is how you set up a consistent, repeatable way to hand a new agent a real, functioning business — the AI setup is the actual asset you’re handing over, not just a list of clients. You run this on your own computer, on your own schedule, for free, once it’s built.
What It Frees You Up To Do
It’s compounding.
Every check the automation runs is a decision you don’t have to re-litigate next week, and every report it stops generating is an hour you can put into the next deal instead of the last one.
That’s real leverage — not a faster keyboard.
What To Do First
You are closing deals, building relationships, and running a business — do not let the fear of falling behind in marketing be the reason you stop posting. This is the honest version everyone needs to hear: consistency is not about becoming a designer. It is about owning what can safely run on its own, so the CEO version of you gets reclaimed for the CEO tasks. Almost everything you are currently posting can fall into one of 3 phases, and phase 1 is the one most people can hand off immediately. Phase 1 is the simplest: a short, plain-text update written in your own voice, published on the day the listing goes live, saying exactly what is written in the MLS description plus 1 human-added sentence about why the buyer or seller should choose you. That is it — 3 paragraphs, 150 words, published on the same day the listing goes live. There is zero branding to protect, zero image sizing to worry about, and zero approval process to wait for, because it goes out the same day the listing is already live. It is the lowest-hanging fruit, and most agents never hand it off because they think of it as the job that needs their personal touch the most — when actually, it is the job that needs a publish button pressed exactly once, on a schedule, the same way a clock checks the time every morning. That is the instruction the AI actually receives: ‘publish the plain-text update on the same day the listing goes live, using the exact same information already in the MLS description, then get out of the way.’ It is the same idea as setting up an automated email follow-up — you define the rhythm once, in plain English, and the machine keeps it running without you. Phase 2 is the middle ground: the branded look and the consistent sizing, applied to the images that go with those updates. This is where people assume ‘AI can never actually do that,’ because they are thinking of a generic image generator typing out a caption and calling it a day. That is not what is actually being built here — the AI is given a real, working template for the specific brand, the same way a designer would set up a Canva file. It knows the color scheme, it knows the sizing, it knows the logo placement, and it knows the exact rules for what gets a caption and what is just an image. Phase 2 runs on the same schedule as Phase 1 — you hand it off the same way, and it stays consistent while you focus on the deal.
Where to start
If you want to run this on your 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, 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.
And if you’d rather start tinkering yourself, the free, open-source version of this system’s in the description as well — download it, try it, own it.
Frequently Asked Questions
What is this automation actually doing for real estate agents?
The automation takes plain English instructions and creates live connections to your data sources, checking them on a set schedule (like Monday and Thursday) for significant changes like new listings, price updates, or status changes. When it finds something important, it sends you an email with the exact change and the full listing history, so you can act on fresh information without having to manually monitor sources.
Do I need to know how to code to set this up?
No. You define everything in plain English — what sources to check, how often, and what counts as a significant change. If you need to add a source or change the rules later, you just rewrite one paragraph in plain English and the next scheduled run picks up the new instructions. The technical build is handled for you.
What happens if I’m too busy to monitor my follow-ups?
The automation handles it for you by running on its own schedule every day, including the days you’re tied up with showings or closings. It checks your listings, flags quiet stretches without showings, schedules calls with agents, and sends you notifications automatically — so fresh leads don’t cool off while you’re handling other deals.
How to Build a Single Shared Memory Across Every Client Conversation — The One System That Compounds Here’s a question we get all the time, and it’s completely normal: someone asks us about a neighborhood, or a specific home we sold, and we remember showing it, but we can’t pull up the exact street name or the exact number we quoted them. No big deal — we pull up our own notes, or we ask the team, and we get the right answer. But here’s the part nobody thinks about: every time that happens, there is now a second copy of that information floating around — the original question, and the answer we typed out in response. And nobody went and manually opened up a shared document and wrote it down. It just sits, duplicated, in two different places. Do that 100 times a year, which is completely normal, and you’ve quietly built a mess that is technically compliant with every regulation on the planet, but also technically useless, because nothing is actually backed up in one place that everyone on the team can access instantly. And here’s the part that matters for 2026: that exact same thing is happening with every single AI tool you’re starting to rely on.
If you’re a few years into this business — closing 6, 7, 8 deals a year, pushing for more volume, more consistency — you’ve probably already felt the frustration.
You walk into a showing and you can’t remember the exact layout of the house. You’ve been there before, but the details have blended together with a dozen other listings.
Or you’re sitting at a closing and someone asks about the neighborhood — crime rates, schools, something you’ve been meaning to look up but never have, because it’s not the kind of question that gets answered in a 10-minute call.
This is for you if you want to actually know the house you’re showing — the floor plan, the updates, the peculiarities — the same way the listing agent does, without spending hours preparing for every single appointment.
And it’s for you if you’re trying to get better at the 300-foot view — the market in your area is doing this month, what’s actually happening in a neighborhood versus what a sign says, the kind of high-ground reading a veteran agent just instinctively has. Because that instinct is not born, it’s built, from actually looking at every listing in your market every single day. And we’ll show you how to let the AI do that part while you get the benefits.
How We Actually Do It
Here’s the part that actually matters, in plain English. None of this is ‘AI is taking over’ hype — it’s four specific things a client might actually ask, and how we answer them with evidence, not a guess.
First, someone touring a house asks, ‘What’s been sold nearby lately?’ That used to mean pulling up a competitor’s publicly available listing history and reading it aloud, which is both tedious and not particularly helpful, because a listing sitting stagnant for months is not the same thing as a real sale. Our system checks every private, closed transaction within a quarter-mile, across all agents and all brokerages, and provides the actual, confirmed sales data to the client, on the spot, while they’re still standing there. 4 out of 5 buyers say they’d choose an agent who could answer that question easily — and now it’s the easy one to answer, not the hard one.
Second, a seller asks, ‘What should I list my house for?’ This is the moment where the answer used to be a generic market update read aloud from a screen — the same thing every agent in town gives every seller. Ours is different, because it actually uses the seller’s address as the starting point, along with the specific layout of the house, to pull real, recent sales that actually match the property, instead of a generic ‘the market’s doing this’ statement that applies to no particular home. That’s what gets printed and handed to the seller, with their own address on it — a real comparison, built from their own home, instead of a generic market blurb.
Third, a buyer asks, ‘What can I actually afford?’ This is the one where we walk away from the common mistake of pulling a generic loan amount and calling it an approval — a number that’s usually on the high end, handed out as a ceiling instead of an appropriate, honest payment. Our version checks the individual’s genuine debt load against income, down payment, and location-specific costs, then shows them a range of real, achievable payments, along with what each one actually gets them in the market. That’s the conversation a real lender has, but most agents never get past the generic ‘here’s a number somebody told me.’ We’re the ones who actually had the conversation, with the evidence to show for it.
And the fourth one is the new one, the reason we built this instead of buying someone else’s version—and we’ll get to that in a second.
How You Set It Up
Here’s the honest version, because we’re not tech support and never will be. We didn’t build this — we just understood it was possible, and we stopped letting fear of the unknown get in the way of actually asking the question. If you’re technical, you can read the official documentation — it’s open source, so it’s right there. If you’re not, that’s okay, because neither are we, and we’re the ones standing in front of you telling you what it actually does.
This is the part that matters more than anything else, so listen closely. None of it is ours. We didn’t buy a license, we didn’t pay a monthly fee, and we didn’t sign anything. It runs on our own Mac, on our own schedule, costing us exactly zero dollars every single month. That’s the difference between building a business and renting one — ownership versus a recurring invoice that never goes away.
Now, what actually runs. In plain English, it’s an assistant you talk to in normal language, the same way you’d text a team member. You don’t code it, you don’t write a script, you just type a question or a request — who’s the contact at a specific property, what’s the status of a deal, what needs my attention today — and it gives you the right answer, pulled from whatever data source actually has the answer stored. It’s live — there’s no daily batch job that runs sometime after dinner. You ask, it goes and looks, and you get the answer while you’re still on the call.
What it actually looks like when you ask it something is unglamorous — it’s just a chat window on your own computer, typed the same way you’d text a colleague. No dashboard to open, no app to launch, just the chat window already sitting there when you need it. And it works offline — if you’re in an area with no signal, it still answers. The data’s already on your machine; it just can’t go out and pull fresh stuff until it reconnects.
What it actually does when you ask it something is where the machinery lives, and this is the part most people get wrong, because they assume it must mean buying something new. It doesn’t. It means pointing the thing you’re already paying for — your CRM — at the assistant and saying, in effect, ‘ask my CRM first, then ask my other sources if the CRM doesn’t have it.’
How It Gets You Found
Here’s the part that actually matters if you’re trying to get found.
When Google answers a question these days, or a chatbot suggests a local agent, it’s not just pulling from whatever site ranks at the top.
It’s pulling from the sources it trusts — and that trust is built, bit by bit, every time you answer a real question, in your own words, on your own site.
This is what all the AI tools in the world boil down to: they help you make content that gets you into that pool of sources that get quoted and suggested, over and over, automatically, while you sleep.
You stop chasing after the latest social platform du jour, trying to rent attention for a few seconds before it scrolls by.
You own the attention, on your site, built on your terms, with your own voice, and you let Google and the chatbots fight it out over who gets to borrow it from you.
What It Means For You
For you specifically — the agent trying to get past 6 or 8 deals a year — this means the real objection to every follow-up becoming a video becomes literally whether you have the time to sit down and edit one. You don’t need that excuse anymore. You shoot the video on your phone, in the moment, and you walk away — and the right version of that video is already waiting in the shared folder the next time you open it, named so that you can’t help finding it. If you’re building a brand, every consistent post is a compounding asset — and consistency is now the easy thing, not the hard thing you have to remind yourself to do every week. If you’re closing 6 to 8 deals a year and you want more volume, this turns every follow-up call into a real touchpoint — a recording you can point a nervous seller to, or a video you can hand a nervous buyer and say, ‘watch this, and we’ll talk tomorrow.’ Either way, you’re the one who did the work, you’re the one who owns the relationship, and the tool just made the follow-up more powerful without adding hours to your day.
If you want to see this exact setup running live and talk through what your own shared folder would look like, we offer a free 30-minute call — the link is in the description, along with a free starter guide you can look at right now. Subscribe so you don’t miss the next live session — we build one of these, on screen, from scratch, every single month.
What It Frees You Up To Do
It’s compounding.
What To Do First
If you’re the relationship-first agent everyone in your community already knows — or the hustling newcomer trying to build that reputation fast — hear us on this: do not run out and buy a chatbot or an AI writing helper and call it a ‘tech upgrade.’
Those tools can be a piece of the puzzle, but the real question is not which tool you own. It is: who, exactly, is remembering everything you’ve ever told it, across every single conversation, forever — and is that memory actually helping you close more deals, or is it just sitting there, unused, while you keep asking the same client the same thing you’d already asked last month.
Because here’s the part nobody tells you when they’re selling a chatbot: your own memory is already a knowledge base. Every note you’ve ever taken, every recurring question you’ve ever logged, is a piece of value sitting in your own files waiting to be connected — and connecting it is the actual skill, not owning the software that happens to be running while you type.
So do not start by shopping for a tool. Start by understanding what you’re actually trying to build, which is a single, shared memory across every client interaction — your calls, your follow-up, your marketing, your team, all working from the same source instead of everyone re-asking the same person the same thing on different days.
Three things are true about that shared memory, and they apply whether you’re running a multi-agent team or you’re the only agent on screen.
First, it is never about the brand-new client. It is about the client you’ve already spoken to three times, who remembers something you said last month and is now trying to decide if you actually know what you’re talking about — and you either prove it by remembering the same thing, or you lose credibility by drawing a blank.
Second, it is not human-read, it is AI-read. You are not typing a document for a person to go read later. You are feeding a structure that an AI can search, summarize, and answer on its own — because the real value is not that you can look something up. It is that the AI can look something up two hours after you’ve already gone to bed, while you’re at a showing, or while you’re on the phone with another client.
Third, it is not a feature you buy and then forget about. It is a habit you build, one conversation at a time.
Where to Start
If you want to run this on your own business — not just watch us do it on YouTube — here’s the honest version of what we just described. It’s not a trick, and it’s not a piece of software we’re holding back from you. It’s a setup we run in our own business every day, and you are welcome to it.
The free version starts from the description. There’s a link to a free, no-signup version of the exact same thing — the skills, running on Realtor AI, free for you to try right now, no cost, no account, no approval. That link’s in the description, and it’s the first thing you should look at if you’re interested in running this yourself.
If you want help setting it up or if you’d rather just talk it through before you build it, we do a free 15-minute call. That booking link’s in the description too. No pitch. We’ll look at what you’re already doing and tell you honestly which of these is worth your time.
And if you’d rather watch us do it than read about it, subscribe so you don’t miss the next live session — the link to subscribe’s in the description, right next to the free skill link and the call booking link. We run these on screen, live, a few times a month, and we build them out in front of the camera while you watch.
We’re Al and Victoria Pinder, husband-and-wife ICON agents at eXp Realty — and we run this in our own business, every week.
Frequently Asked Questions
What is the shared memory system and how does it work?
The shared memory system is a single, unified place where all client information, conversations, and data are stored and accessible to your entire team. Instead of information sitting duplicated across different places, this system pulls from your existing CRM and other data sources, allowing an AI assistant to search, summarize, and answer questions instantly—whether you’re on a call, at a showing, or offline.
How much does this system cost to set up and run?
The system runs on your own Mac or computer at zero dollars every single month. You’re not buying a license, paying a monthly fee, or signing anything—the data stays on your own machine, giving you ownership of your business instead of a recurring invoice that never goes away.
What are the three key things to know about building a shared memory system?
First, it’s about the clients you’ve already spoken to multiple times, not brand-new ones—proving you remember what you said builds credibility. Second, it’s AI-read, not human-read, so the system can search and answer questions even when you’re sleeping or with another client. Third, it’s a habit you build one conversation at a time, not a feature you buy and forget about.
Every morning, before you open a single app, there is an email sitting in your inbox that wrote itself. It is not a recycle job post, not a market update copied from a blog, but a fresh, targeted email draft built around what your actual pipeline actually needs today — who is closing soon and needs a follow-up, which listing needs more exposure, which lead is still warm and needs a touch. And you didn’t write it. You didn’t open a template and re-read the same old phrases. You just opened your inbox, found the draft already there, and hit send.
That is not a trick and it is not a piece of software we built. It is one of the AI tools we use every day, running on our own computer, costing $0 a month, doing a job that used to eat an hour of our own time every single morning. And we are going to show you exactly what it is, how it works, and why we walk away from anything that does not save real minutes or real dollars. Because the real question is not which AI tool is the newest or the shiniest — it is which one actually earns back the time you put into it.
Related: Claude Code for Real Estate Agents — Our Stack
If you’re a few years into this business — closing 6, 7, 8 deals a year, pushing for more volume, more consistency — you’ve probably already experimented with some kind of AI tool: a chatbot on your site, a video generation system, something like that.
The problem almost everyone runs into is that there is no single tool that does everything, and almost every tool promises more than it actually delivers. So you end up with a handful of half-finished experiments sitting on your hard drive, and you’re not any closer to actually running your business on autopilot.
This is for you if you want to actually put those tools to work, side by side, doing specific jobs in your business — without becoming a tech expert in the process.
What It Actually Does
Here’s what actually happens when you open one of these on a call.
With the chat-based tools, you ask it a question out loud — who’s the listing agent on a property, for example — and it fires off the question to its own knowledge graph and reads the answer back to you, aloud, in a human-sounding voice, before you’ve finished your own sentence. No typing, no let me get back to you, no losing the thread while you open five browser tabs. You ask it, it answers, you move on.
The difference from a Google search is the source is clean every time. It’s pulling from the real data connection it set up with the MLS, not handing you a messy mix of accurate and outdated advice pulled from whatever page happened to rank that day. That alone is what makes it useful in a conversation with a client who’s actually paying you to answer a question, not ask Google in front of them.
The other tool we looked at runs a bit differently — it’s a skill you add to your own voice assistant, and you trigger it the same way you’d ask the assistant to set a reminder. When you do, it goes out and collects whatever’s relevant for that day — a new listing that came on, a price change, something that actually happened in the market, not just a generic daily digest. It delivers that as a short, formatted text note, ready to read aloud if you want. Because it runs on a schedule, you’re never depending on remembering to ask it something; it just shows up. That makes it useful for the kind of check you’d normally promise a client and then forget — I said I’d keep an eye on that neighborhood, didn’t I? You set it once and the check is built into your day, automatically, the same way you set up a recurring reminder in any assistant.
Both of these are the kind of thing you can walk a tech-savvy client through adding to their own phone if you want — the chat one’s conversation, the skill one’s setup, done with you watching. Both pull from the same MLS data connection, so you’re always working from one clean source instead of mixing old and new information. That’s really what makes any of these worth it: you’re the one asking, and you’re the one getting the answer, not a chatbot pretending to be an agent.
Here’s what we actually use, and how it’s set up.
We have 3 different AI tools running in our business, every single day, automatically.
2 of them are things we built ourselves, using Claude Code.
The first one checks our websites every morning for broken pages or missing images, and tells us exactly what it found, right in chat. It goes through every single page on every site, one after another, and you can see exactly what it’s doing, live, as it works.
The second one reads our follow-up sequences and tells us which ones are getting the best responses, and which ones are sitting quiet. It pulls the actual performance data and lays it out side by side, so we’re not just guessing about what’s working.
The third one is different — it’s not something we built. It’s a service we pay a subscription fee to access. Every evening it goes through our leads and reapplies the scoring, using fresh data, so even if someone’s situation changed, the score reflects it the next time we look. That’s the one we actually pay for, and the other 2 are running on our own machine, costing us nothing beyond the few minutes it takes to run them.
If you want to try something like this yourself, start small. Pick one question you ask your business repeatedly — which lead source is converting, for example, or which listing description is landing searches. Then write a simple automation that goes and gets that answer for you, instead of you spending time digging for it.
You don’t need to be a developer to do that. There are plenty of no-code options out there, and plenty of agents who’ve never touched code have built their own automations with them.
Pick the one that costs you the most in monthly fees or hours per week. If a VA takes 5 hours a week on follow-ups, automate follow-ups first. That’s your fastest payback.
You’re learning to tell the machine, in plain English, exactly what you want checked, and then letting the machine do the actual work, over and over, automatically.
How It Gets You Found
Here’s the mistake we see agents make: they assume ‘getting found’ online only means Google — rank higher, get more traffic, job done. That’s half the picture. The other half is the AI tools themselves have their own ‘indexes’ now, and they rank sources inside those indexes based on credibility and consistency — what matters to both Google and the AI tools is exactly the same: you show up as a real, active, trustworthy local expert, every single day, with the same branding, the same messaging, the same tone of voice, across all of it.
That’s what Claude Code does under the hood. It doesn’t write anything on its own — it uses the brand guide you’ve already built, the same one your own team uses every day, to make sure everything it generates is recognizable the moment you read it.
It runs that generation against 4 different indexes — Google, plus ChatGPT, Claude, and Perplexity — so you can see how each one answers the same question, side by side, and pick the one that works or blend the best parts of all 4 into one answer.
You own the output — it’s yours to publish wherever you want, and you walk away with a deep understanding of how the AI answers work, because you’ve actually looked at the machine’s answer next to your answer next to the brand.
What It Means For You
For you specifically — the agent trying to choose where to put your hours — this means you don’t need to build anything or pick a ‘trendy’ tool. Start from what’s actually getting used, and pick 2 or 3 of these in the areas where your own business actually needs help. If you’re building a brand, pick the video tools. If you run on referrals, pick the follow-up automation. If your pipeline’s the issue, pick the lead screening. Each one of these is real, running, and ready to take over a specific job, and you get to pick which job based on what your business actually needs this week.
What It Frees You Up To Do
The real answer isn’t ‘this tool vs that one.’ It’s that source data is table-stakes now — it’s the floor, not the ceiling — and the real decision is what you build on top of it.
A skill is something you can hire out. A system is something you own. Everything here leans into owning your own infrastructure, because that’s what actually compounds.
If you’re building a brand, source content moves from being a task you outsource to being your own machine that runs every day on a schedule, feeding your blog, your YouTube channel, and your social media — and you’re the one who decides what goes in it, not an assistant trying to guess what you want.
If your business runs on relationships, a shared notebook becomes a living record of every deal, every referral, every promise made — accessible to both you and your partner, so nothing important is ever lost in an email.
And if you’re pushing for volume, a follow-up sequence becomes a machine you set up once, and it runs on its own — a check you stop losing every week, and a lead you stop letting go cold.
None of this is the ceiling on what AI can answer in your business. It’s just what’s been built so far, and what’s been built so far is already more than the AI tools most agents have ever touched.
What To Do First
Here’s the honest version, because we’re all busy: 3 kinds of tools make it into a daily rhythm — ones that sit in a browser tab and stay open all day, ones that run on a schedule and you never think about, and ones you open when you need them, for a specific call or showing. Almost everyone starts by accident — downloading something because a video or a post said it was good, then figuring out later if it fits. We’re going to show you the 3 patterns instead, so you put the right tool in the right slot the first time, instead of collecting clutter.
Where to start
If you want to try any of these tools yourself, or just talk through what your own business actually needs, we offer a free 30-minute strategy call. The link to book it is right in the description below, and our number’s there too. No pitch, just a real conversation about your business.
And if you’d rather watch us mess around with these tools live, we do that on Instagram too. Subscribe so you don’t miss the next one.
If this helped, hit the like button so we know to make more like it. We’re Al and Victoria Pinder, husband-and-wife ICON agents at eXp Realty, and we run this business on the systems we just showed you. We’ll see you in the next one.
Frequently Asked Questions
What AI tools do you actually use in your business?
We use 3 different AI tools running automatically every day. Two of them we built ourselves using Claude Code — one checks websites for broken pages and missing images each morning, and another analyzes follow-up sequences to show which ones get the best responses. The third is a paid subscription service that rescores leads every evening using fresh data.
How much does it cost to set up these AI automations?
Two of our three tools cost $0 a month because they run on our own computer using Claude Code. Only the third tool — the lead rescoring service — requires a subscription fee. We prioritize tools that either save real time or real money, and we built the first two ourselves to eliminate that hourly time cost.
Where should I start if I want to automate my real estate business?
Start by picking one question you ask your business repeatedly — like which lead source converts best or which listings get the most searches — then build a simple automation to answer it for you instead of spending time digging. Prioritize automating whichever task costs you the most in monthly fees or hours per week, because that gives you the fastest payback on your effort.
