Connect through text

Before we built anything, I wanted to address a conversation that keeps coming up. What should I be using AI for? I don't think that's the right question. Look at your business first. Where do you want to grow, and what's keeping you from getting there? Then decide whether AI is the right tool to close that gap. Sometimes it is. Sometimes it isn't.

Then we got to work. I opened a chat with more than thirty prompts in it, three fictional clients, newsletters, Instagram captions, all of it mixed together. I asked it for a listing presentation for one of those clients. It came back basic. It left out my last name. It recommended a CMA that was never created. That's what happens when your AI pulls from a cluttered desk.

So I built a project for that same client, live, in both Claude and ChatGPT. Same request, same client. The difference wasn't close.

In this episode:

• Why I name projects after the client, not the address, so a sale and a purchase can live in one place
• What goes into a client project: simple instructions, my Voice Foundation files, my branding and logos, the public record sheet, and the market analysis I ran myself
• Why you still run the comps. You're the one explaining them to your client
• What happened when Claude didn't have a file it needed: it stopped and asked instead of making something up
• The difference between AI's built-in memory and an operating file you wrote on purpose
• How client information bleeds across a long chat, and how projects keep it contained

Next week: real solutions I've built for real estate agents, starting with what they needed in their business.

Get the Voice Foundation plugin here:

https://www.agentslearnai.com/voice-foundation/

Learn more about consulting and Creative Authority here:

agentslearnai.com

Connect through text

Most real estate agents use ChatGPT the same way. They open a new chat, paste in the details on a house, and ask for a listing description. Or they keep one long chat going for months and wonder why it stopped sounding like them.

Here's what's happening. As a chat gets longer, the AI stops going back to the top to reread the context you gave it. It works mostly from the last few exchanges. So the voice examples you loaded at the beginning get buried, like one rolled-up piece of paper on a desk covered in coffee cups and clutter. The AI grabs whatever's closest, fills the gaps with generic realtor content from across the internet, and your voice starts to erode.

The fix is already built into both Claude and ChatGPT. It's called Projects, and most agents aren't using it. In this episode I walk through how I organize mine: one project per client, not per property, so a client's sale and their next purchase live in the same folder. Every new chat inside that project reads the instructions and files again, and that's what keeps the output consistent and sounding like you.

And once your work is organized this way, a lot of the paid "AI employee" tools start to look unnecessary. They're folders with instructions. So are Projects, and they come with the plan you already pay for.

In this episode:

• Why long chats lose your context and drift toward generic output
• A simple way to picture your AI workspace: the cluttered desk and the organized desk
• Why I set up projects by client instead of by property
• What goes in a project: instructions, your Voice Foundation, and client files like tax records, listing agreements, walkthrough notes, and offers
• The difference between AI's built-in memory and intentional operating context
• Scheduling a weekly client update email from inside a project

Next up: a full walkthrough building a project around a mock listing consultation.

Get the Voice Foundation, as a free worksheet or the full Claude plugin, and learn more at agentslearnai.com

Connect through text

Seventy percent of agents who use AI use it for exactly one thing: writing listing descriptions. That's the finding from a survey of around 500 high-producing agents at the most tech-forward brokerages in the country. Not the laggards. The top performers.

In this episode, Matt Goldman and Paul Carlson, President of Five Star Real Estate, dig into why that number is so low, and what the other 99% of AI's capability actually looks like when you put it to work.

Matt talks through the real tools he's built for his own business. A mileage tracker he needed for one tax season and will never use again. A three-market comparison built from a single prompt for a client weighing Grand Rapids against Denver and Ogden. A buyer consultation follow-up that turns rough notes into a personal email. A listing consultation tool that prices out a seller's repair list. And a monthly referral marketing system that runs without a prompt.

The bigger argument underneath all of it: you've been forced to rent seven to ten tools to do what one can do, and none of them fit, because none were built for you. The fix isn't a better subscription. It's building the thing yourself, around the specific client in front of you.

They close on the two moves that matter most right now for any agent whose business feels quiet: build your database, and build a follow-up system that's actually custom to your people.

Learn More at Agentslearnai.com