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.
Claude Code is not something we built — it’s a tool we found the same way you probably find new tools, by asking around, reading what agents are posting about, and trying a few till one actually helps. And the honest version of what we were looking for is right in the name: we wanted a skill that could sit in the background and actually work a repeatable task for us, without us remembering to open it or tell it what to do next. Most of what’s out there is not that — it’s a chatbot you type a question into, or a video script generator you load a template into once a week. Those have their places, but they’re not the same thing as something that runs on its own schedule and hands you a finished piece of content every time you open it. That’s what made us sit up when we heard about this, and it’s what made us want to run it by you, because we thought you might be looking for the same thing we were.
Related: Claude Code for Real Estate Agents — Our Stack
If you’re a couple years into this business, closing a steady handful of deals a year, and you’re hungry to get off the content treadmill — you know, the never-ending cycle of writing a blog, posting a video, then watching it sit there with 25 views — this is for you if you want your tech actually working a shift alongside you, earning your hours back every single day.
What It Actually Does
Here’s the thing about these skills. They are not a shortcut to becoming a tech genius. You do not need to know how any of this works under the hood. You just tell Claude, in plain English, what you want, and it builds it and runs it for you. And the 4 ways we use it, across our own business every single day, are actually pretty common. Almost every agent does some version of these 4 things. It’s just that most agents build a separate tool or a separate login for each one, and end up with a messy row of tabs they barely understand. With these 4 skills, you run all of it from one place, and every piece is working the same way.
Skill 1: The Daily Check-In, Automated. The first one runs on its own clock. Think of it as your morning check-in, but you don’t actually have to open anything to run it. You just tell it, in plain English, something like ‘check my numbers’ or ‘show me what’s changed.’ It opens the right reports for you and emails you a digest, the same way you might check your own email in the morning and find your numbers already sitting in your inbox. The difference is you didn’t have to brew coffee and open anything to get it. You just told Claude, in plain English, to go do it. And you can set it up so it runs on a schedule — every morning, every Monday, whatever cadence you want — so it’s not something you have to remember to do. The source data is whatever you’ve already got running. If you’re already tracking your numbers in a spreadsheet, it pulls from that. If you have a CRM with a report builder, it uses that.
Here’s the mistake we see agents make once they start automating: they assume ‘automation’ means one thing happens automatically, and that’s it. A skill isn’t one job it does daily. It’s a system that watches your business constantly, and when something specific happens, it takes an appropriate action. Not a generic one, the right one for that exact situation.
3 examples, quickly. The first is the watchlist monitor. It doesn’t just check a static list every morning. It watches Zillow’s own saved search APIs in real time, so the moment a new listing appears that matches your watchlist criteria, you get a notification before anyone else on the watchlist does. Not 6 hours later, the moment it shows up.
The second is the follow-up sequence. It’s not a single scheduled email. It’s a series of touches that fire in the right order, depending on what the client has already opened and replied to. If the client engages with the first email, the next one in the sequence is a personal check-in, not a broadcast. If the client goes dark, it switches to a different track entirely — a shorter, more pointed question, delivered from a real email address, not a template. It reads the actual replies and adjusts the next move accordingly—a warmer follow-up if they’re engaged, a shorter ask if they’ve gone quiet. It’s not ‘automation’ in the sense of ‘I set it and forgot it.’ It’s automation in the sense of ‘the right next move is already waiting, I just have to approve it or not.’
The third is the content calendar. It doesn’t publish the same generic post on the same day every week. It reads the market and picks the right one for the week, then schedules it across all the right channels for you. A big local event coming up? The calendar reads the event listing, captures the relevant details, and schedules a targeted post about it. A slow week with nothing happening? It picks a popular, evergreen local topic and schedules that instead. It goes through your own blog posts and repurposes your best-performing ones as video, then schedules the video out to the right places.
How You Set It Up
Here’s the honest version, because we’re all in the same business. We didn’t go out and learn a new coding language — we just opened Claude and searched for ‘real estate agent skills,’ and it handed us a list of integrations other agents had already built and shared. We didn’t build anything from scratch. We just picked the ones that matched what we actually do every day — and that’s the key, because there’s no point in paying a developer to build something you’re never going to use.
The first one saves the most common question we get: ‘Is this listing still active?’ We used to open up Realtor.com or Zillow and search for the address, and now the skill just asks Claude, ‘Is this listing still active?’ and it answers with a source link — the current status, pulled live, every single time. It’s the same question, asked the same way, and it works across every property we’ve thrown at it so far.
The second one is a shortcut for our own website. We run on a custom setup — not a franchise template — and there were always a handful of pages that were stubborn about updating themselves automatically. The skill connects to our site and tells the right page to refresh its own content, so a new posting goes out the next time the schedule runs, instead of sitting in a needs-approval pile. That’s the other half that doesn’t get talked about: a skill isn’t a feature you add to your business — it’s a connection you build between the tools you already have. You’re not signing up for a new platform; you’re telling your existing tools to talk to each other in a way they never could on their own.
The third one is the one that surprised us the most, and it’s the opposite of both of them. We run a lot of experiments — a new landing page, a different headline, a different image — and usually there’s a notebook somewhere with a list of what needs to be tracked and whether it actually made a difference. That notebook is always the first thing to go stale, because it depends on someone remembering to go back and update it. The skill connects to the experiment’s own analytics and pulls the actual numbers instead of a memory of what you thought happened. If something is converting, it proves it with the right graph — not a suggestion, not a guess, not a headline you wrote.
How It Gets You Found
Here’s the mistake we see agents make once they start automating anything: they assume ‘built-in’ means ‘get found.’ There is no automatic connection between a skill you add to Claude Code and Google indexing the answers it produces — or anything else that actually gets you found. That part is the other half of the job, and it’s the half almost nobody talks about.
The way you actually get found from any of this is still the same three ways, picked up by the same three engines: Google, the AI answers systems, and the map.
The skill checks two things every single day: whether you have new content to promote, and whether any of your existing pages have dropped their ranking for the search phrase that matters most. That’s what keeps you sharp across your whole website. That’s it — those two checks, run on a schedule, are what keep you sharp across your whole website, not one heroic effort every few months.
The old way to do that was a mix of Google Search Console monitoring, rank-tracking, and maybe a separate tool watching your traffic sources — three different dashboards, three different bills. With Claude Code, the check becomes one scheduled job that runs on your own machine, costs nothing extra, and you look at it the same way you’d look at your phone — a quick scan in the morning, and you know exactly what needs attention today.
Nobody outside your own team ever sees it, and that’s the piece that actually matters for anything built on your own infrastructure: you own the data, you own the timeline, and you own the decision about what is actually an emergency worth a call versus something that just gets folded into next week’s regular review.
The AI answers systems — ChatGPT, Gemini, Perplexity, and the others — pick up from your content the same way: by finding a question asked in plain English that your content answers directly, then quoting your answer back to the person asking.
What It Frees You Up To Do
The real value isn’t in any one of these, it’s in what they let you stop doing. The skill that checks a title or signs a closing document works the same at 9 PM as it does at 9 AM, without anyone staying late to be the one who’s awake when the attorney’s office finally answers.
They stop handing out their personal phone number to every seller who asks ‘who’s going to be at the actual showing.’
And they stop losing sleep over which lead follow-up item got dropped last week. The pipeline review skill runs the same schedule every week, without anyone remembering to open it. So a team that used to run on one person’s memory now runs on the skills’ memory, and the owner gets their time back for the relationships and the strategy, instead of being a juggler.
If you’re like most agents we talk to, you’re trying to run your business on what amounts to a handful of apps — a CRM, a follow-up sequence built into that CRM, maybe a separate marketing automation tool, and then a handful of others for individual tasks like a signature platform or a transaction management system. The problem with that setup isn’t just that it’s complicated to keep straight. It’s that every one of those apps is running the same way — you open it, you find the right screen, you do the same few things you always do, one after the other, and then you close it and move on.
None of that is particularly efficient, and it’s certainly not what people mean when they talk about ‘working smarter,’ not harder.
So let us be clear, up front, about what this actually is. This is not about adding another app to your stack. It’s about, effectively, replacing several of the apps you’re already using with something that works a different way — a way that, honestly, is more like how you already think about your business than the CRM or the marketing automation tool ever were.
Before we get into what that actually looks like, there’s something important to understand about how all of this works, technically. You do not need to be a programmer to use any of this. You do not need to install anything on your own computer. You do not need to ask an assistant or a tech person to set up a ‘workflow’ for you.
You open a chat window — on your phone, at a coffee shop, at 9 PM, after the kids are in bed — and you type out, in plain English, exactly what you want. You want a follow-up sequence built for a specific kind of lead. You type that out. You want a post drafted for your blog. You type that out. And the system, working behind the scenes, sets up and runs the actual automation for you. It builds the sequence, drafts the post, whichever one you asked for, and then hands it back to you, complete, the next time you open the window — usually within a few minutes, sometimes within seconds, depending on what you asked for.
That’s the whole point: you stop opening 4 or 5 different apps and navigating to 4 or 5 different screens to do 4 or 5 different tasks. You type one request, in one window, and let the automation handle the rest.
Where to Start
If you want to connect with us and see exactly how we’re using this in our own business — not a demo, our actual setup — the booking link is in the description. We offer a free 30-minute strategy call; it’s the same call we give to agents who partner with us.
And if you’d rather start tinkering yourself, the free starter skills are open-source on GitHub — that link’s in the description too. Clone it, try it, own it.
We’re Al and Victoria Pinder, husband-and-wife ICON agents at eXp Realty. We run every piece of this stack in our own business, every single day. We’ll tell you honestly what’s worth it and what’s not.
Frequently Asked Questions
What is Claude Code and how does it differ from other AI tools?
Claude Code is a tool that runs automated tasks on its own schedule in the background, delivering finished content without you having to open it or tell it what to do next. Unlike chatbots you type questions into or template-based generators, it works continuously alongside your business and hands you results every time you check in.
Do I need to know how to code to use Claude Code?
No, you don’t need to know how to code or install anything on your computer. You simply open a chat window and type out in plain English what you want—like ‘check my numbers’ or ‘draft a blog post’—and the system builds and runs the automation for you, handing back complete results within minutes or seconds.
What are the main ways Claude Code is used in a real estate business?
The four main uses are: automated daily check-ins that email you a digest of your numbers on a schedule, watchlist monitors that notify you the moment a new listing matches your criteria, follow-up sequences that adjust based on client engagement, and content calendars that pick and schedule the right posts based on local events and market conditions. Each one works by connecting your existing tools so they talk to each other automatically.
If you’re building a real estate brand on trust — referrals, repeat clients, people who know you and come back to you — you know your biggest challenge isn’t getting the listing. It’s staying top of mind between transactions, proving you’re still sharp and worth the call when someone asks your name to a friend.
Here’s how to pull live local search questions into your content calendar in 20 minutes, so you’re always writing what your market is actually asking Google this week. You connect Google’s own tools, through Claude Code, to pull live, local question data into a format you can actually read, instead of a graph you have to interpret. You’re not searching keywords. You’re listening to your market.
If you’re a few years into this business, closing a steady handful of deals a year, and you’ve already built or bought a few AI tools to help — a follow-up sequence, a posting schedule, something like that — this is your next logical move. You’ve felt the frustration of wanting a specific instruction followed and getting a generic answer instead. This is how you finally bridge that gap, and it’s actually doable if you can write an email. If you’re pushing for more volume, more consistency, and you’re already stretching your hours thin trying to get everything done, this is what lets you stop flying by the seat of your pants. You set the standard once, in plain English, and from then on every piece of generated content follows it. Same if you’re building a distinct brand — this is how you ensure every piece of content sounds like it came from the same person, the same voice, the same vision, instead of a generic script. And if you’re experimenting with different content formats, different audiences, this is what lets you quickly try one tone on one group and swap it out for something completely different next week, without rebuilding anything. One instruction manual, one experiment at a time, and you can see exactly what’s working before you invest another hour into it.
What It Actually Does
Here’s the part that actually matters, if you’re not a technical person: you don’t need to understand any of the underlying code to do this. You run a few commands in the terminal — which just means opening a window and typing them, the same way you’d type a Google search — and the model does the work of learning from your own content. It runs on your own computer, not in the cloud, so there’s no monthly fee and your data stays local. And it’s not a black box: you can open it up and look at exactly what it’s doing, change how it works if you want, without needing to know how machine learning works under the hood.
If you’re technical and want to know more, the source code is open and you can clone it and build it yourself. It’s built on top of Hugging Face’s Transformers library, and the License to Share terms mean you can use it in a commercial setting and even in something you charge for, as long as you share the improvements you make. If you want help setting it up or aren’t sure where to start, we do a free 15-minute call — that link’s in the description, along with a free starter guide so you can look it over on your own first. Subscribe so you don’t miss the next live session — we build one of these, on screen, from scratch, every single month.
How You Set It Up
Here’s how we did it, and why you don’t need to be technical to run it.
We didn’t code any of this. We’re not data scientists. We just opened up a free tool, pointed it at the examples we wanted it to learn from, and told it what kind of question to watch for.
It runs on your own computer — no monthly fee, no portal subscription. If you want to run it all day every day, you buy a license for that specific job, and it costs whatever you and the developer agree on — we’ve seen prices from $50 to $500, depending on the size of the job.
The way we set this up, a non-technical person could run it on their own machine. You open the app, load the saved settings, and hit start — it runs the whole process, downloads the finished model, and tells you when it’s done.
If you’d rather watch it work than read about it, there’s a free 15-minute version of this on screen now. The full version, running the whole thing from scratch, is in the description — that one’s a little longer, because we didn’t skip any steps.
Before you build anything, run a smaller preview version first to make sure it’s actually useful.
If you want to try this yourself and you’re not sure where to start, the free starter skills are in the description — that’s the version you saw on screen, and it runs on your own machine right now, no cost. The version that runs unattended overnight and emails you the results when it’s done is the one we charge for, because it saves you hours of your own time.
We’re Al and Victoria Pinder, husband-and-wife ICON agents at eXp Realty — and we run this in our own business every single day. If you want to watch us build the next one, subscribe so you don’t miss the next live session — we’ll see you in the next one.
How It Gets You Found
Here’s the actual question Google gets asked, over and over, by agents in every market: how do I show up when someone in my area searches for an agent online.
Right now, there are 2 ways that question gets answered.
The first is the old way, and it’s the one most agents are chasing. You publish a lot of content — blog posts, videos, guides — targeting the keywords you want to rank for, and you cross your fingers hoping Google sees your site as an authority on local real estate.
That used to be enough, but it’s getting harder every year. Google’s AI is getting better at understanding what a real local expert is, and the bar for what counts as a real local site keeps rising.
The second way is the new way, and it’s the one we’re showing you today. Instead of publishing content and hoping you rank, you actually train the AI, on your own machine, with your own data, so the answers it gives are pulled from your real experience instead of a generic list.
When someone in your area searches for an agent, the AI answers the question with you as the recommended agent — not a generic list, not a paid placement, you.
And here’s the part nobody tells you: whether it’s Google or ChatGPT or Claude, the same principle applies. It’s always the same question, asked in different ways: who’s a real local expert, and what do they actually do.
With a model like this, you’re answering that question yourself, with your own data, instead of hoping someone else’s algorithm gets you right.
If you’re thinking of your niche or your market and wondering if this applies to you specifically — it does. A model like this is just as useful for an agent who works a small, defined area as it is for someone who covers a larger region.
In fact, one of the ways we’ve seen agents use this is to build a separate model for each town or neighborhood they serve, so the recommendations get even sharper.
Before you call this too technical, remember what it actually is. It’s a smart assistant you teach by showing it examples — what a real local question looks like, what a real local answer looks like, what a real local agent sounds like.
You don’t need to be a programmer to run it. You run it from the command line the same way you’d open any app on your computer, and you teach it the same way, every time, by showing it examples.
What It Means For You
If you’re pushing for volume, this turns a 40-hour job into a 20-minute review. You watch the highlights instead of reading every single output, and you get the same guarantee: the model answered what you actually asked, or you get your money back.
If your business runs on relationships, this is how you stop losing ground online to someone who just types faster. Every question gets the same thoughtful answer, crafted in your voice, while you’re out doing what only you can do.
And if you’re building a brand, this is your brand’s brain, working for you, at $0 a month, for as long as you want to run it. Every reply is on-brand, because you built the brand into the model yourself. You own your best asset, instead of renting it from a platform that could change the rules tomorrow.
What It Frees You Up To Do
The real value isn’t the model itself — it’s what it frees you up to do.
If you’re like most agents we talk to, your business runs on relationships: repeat clients, referrals, the people who already know you.
But staying top-of-mind in a niche means consistent, relevant content, and creating that takes hours you don’t have — hours you’re currently spending on approvals, follow-up, and admin.
This points the hours you were spending on content back at the business, and the content itself is sharper because it’s actually drawn from what you do every day, instead of a generic template.
If you’re building a brand around a specific market or a specific kind of property, this is how you finally start sounding like an expert in that space, instead of a template, and it’s your own voice — you’re the one who approved every single statement before it went out.
CTA
Here’s the honest version of where this stands.
The free, open-source tools we’ve described here are real, they’re running in our own business right now, and you can deploy them yourself if you’re comfortable with technology — there’s a free starter guide in the description, and we run a free public workshop every month where we set it up live.
If you want help actually putting this into your business, that’s what we do with our private clients.
We’ll look at what you’re already doing, show you how we’ve applied this in our own business, and build something like this — tailored to your niche, your audience, and your content goals — as one of our regular, ongoing projects.
What To Do First
THE PROSPERITY AGENT — EPISODE 29
What this episode is for, in plain English. If you’re a few years into this business and you’ve gotten pretty good at the transaction side of things — the listing, the showing, the closing — you might be thinking about how to get to the next level. More volume, more consistency, a real business instead of a job. One way to do that is to build your own AI helper, something that works with your own data and your own leads, instead of a generic tool that answers everyone’s questions the same way. Today we’re going to show you how to do that, specifically with something called LoRA, which is a way to teach an AI model by changing just a tiny part of it — the part that applies to your business, your market, your leads. If you’re technical, you’ve probably heard of it. If not, don’t worry — we’re going to explain it in plain English, the same way we explain everything on this channel. And we’re going to show you, step by step, how to actually do it on your own machine, with your own data, while we watch. WHO THIS IS FOR, AND WHO THIS IS NOT FOR. This episode is for agents who are a few years into the business, closing 6 to 8 deals a year or more, and want to build something like this themselves instead of hiring it out. If you’re brand new, or you only do a handful of deals a year, this probably isn’t the right place to start — build your pipeline first, then add the AI on top. And if you’re the type of agent who prefers to call a vendor and have them do the technical work for you, that’s totally legitimate — there are plenty of people who offer this as a service. But if you like to understand what’s actually happening under the hood, and you want to be the one driving the machine instead of renting access to it, this is your episode. WHAT THIS BUILD ACTUALLY IS, AND WHAT IT’S NOT. It’s not a generic chatbot — it’s your voice, your expertise, your brand, running on your own machine.
Where to start
If you want to run this on your own machine — not just watch us do it on YouTube — we’d love to talk. We offer a free 15-minute call.
We’ll look at what you’re already using 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.
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, husband-and-wife ICON agents at eXp Realty, and we run every piece of this stack in our own business, every week.
Frequently Asked Questions
Do I need to be technical to set this up?
No. You don’t need to understand the underlying code to run this. You open a terminal window and type commands the same way you’d type a Google search, and the model does the work. If you’re not sure where to start, there’s a free starter guide in the description and a free 15-minute call available to help you.
How much does this cost to run?
The free, open-source version runs on your own computer with no monthly fee and your data stays local. If you want it to run unattended overnight and email you results, that’s the version you pay for, with prices ranging from $50 to $500 depending on the size of the job.
What does this actually do for my real estate business?
It pulls live local search questions into your content calendar so you’re writing what your market is actually asking Google. Instead of publishing generic content and hoping to rank, you train the AI with your own data so it answers questions with you as the recommended local expert, using your voice and experience instead of a template.
