Home · Blog · 5 AI Tricks for CRE
Field Notes · Vol. 1

The signals were always there. THE OVERLAP
IS THE DEAL.

What I'm building, why it keeps breaking, and 5 ways you can use Claude in your CRE practice tomorrow morning.

A market leaks before it moves.

For the past several months I've been attempting — and "attempting" is the generous word — to build my own AI for commercial real estate. Not a chatbot wrapper. The actual thing.

It started with a theory. Events in a market produce a signal that affects property value. At the level of perception, that's already true. Utility permits, new construction, new tenants, capital flows, building codes, sidewalk repairs, who's hiring on the corner — these come up in every negotiation I've ever sat in. We just don't quantify them. We let them live in our heads and call it "feel for the market."

So the theory goes like this: those signals overlap. And where they overlap, they aggregate into something none of us — brokers, owners, lenders, developers — can see yet. A property is already becoming more valuable before the market notices.

"That difference — between what the market sees and what's already true — is the delta we call opportunity."

That's the core of Signal Intelligence. The conversation layer is called SID — short for Signal Intelligence Database. It's fed by 9 engines. Each one is a neural network mapping other neural networks, comprised of hundreds of programs and agents working in concert.

Each engine has its own algorithm and its own data-scoring mechanism — auditing every input for accuracy and provenance, then scoring it on how well it validates against the rest of the system. It takes some serious tweaking. And REALLY dense data.

And it all runs on data anyone can access from a public source. (It might take an open records request — but it's there.)

The math is giving me PTSD flashbacks
to high school calculus.

The algorithms and scoring engines are the part that's bending my brain. The work itself is something different — cognitively draining, yes. But also energizing.

Broken edge functions. The same parcel rescored a dozen times. Engines I built crashing on the test runs. Auth flows that strip path components when Supabase normalizes against the URL allow list. A Markov chain that did exactly what I told it to and still gave me the wrong answer.

And then — small signs of it working.

An early sell signal here. A tenant site selection there. A handful of predictions floating in the queue.

Most of them are wrong.

Some are still unproven.

It's painful to watch one be wrong. It's twice as energizing when one is right. And then it's painful again — because I didn't act quick enough.

That's the loop. Brokering deals by day. Building by night. Watching the system get a little smarter every week, and watching the math get a little less terrifying.

I'm telling you this not to complain. I'm telling you because I think people on LinkedIn keep posting "5 AI hacks!" carousels and pretending the work is easy. It isn't. The interesting work — the part that's actually new — is hard, slow, and nobody hands you a pre-built prompt for it.

The data monopoly is the next big risk to our business.

Our industry's reliance on a small number of major data providers is creating a dangerous monopoly. It's only going to get more expensive. The same vendors that sold us subscriptions are the ones training the models that will eventually compete with us.

We need to find ways to protect our own data and still play in the same market. That's why I make it a point to only use data anyone can get from a public source. It's slower. It takes more work. But it's defensible — and it's ours.

"I'm not looking to replace the broker. I'm looking to empower one."

Own your data. Amplify it with public data. Use a system that does the heavy lifting for you. That's the play.

My vision for this is a tool that gives you the pulse of the market for any perspective or any client need — and presents it in a way that's easy to understand and easy to share. (Still working on the easy-to-understand part.)

The point of the system is to empower brokers for meaningful conversations and meaningful work — backed by data that supports your creativity and your judgement. Not replaces it.

The deal is still the easy part. The hard part is knowing which deal to chase. That's just my 2 cents on where I'm coming from.

Now — here's the part I promised.

5 ways to use Claude in your CRE practice
tomorrow morning.

You don't need an engineering team. You don't need to learn Python. You need a paid Claude or ChatGPT account and the willingness to copy-paste a prompt. Here's what I'm using every week.

Trick 01 · Tour Debrief

Voice notes → tour report your client actually reads.

You walk a property, fire 4 minutes of voice notes into your phone, paste the transcript into Claude. It comes back as a tour report — pros, cons, fit score, three follow-up questions for your client. Tour debrief that used to take 45 minutes now takes 4.

Prompt
You are my CRE associate. Below are voice notes from a tour of [property] for [client and use]. Write a tour debrief: (1) summary, (2) 3 strengths, (3) 3 concerns or unknowns, (4) fit score 1–10 with reasoning, (5) 3 follow-up questions I should ask the listing broker. Tone: direct, broker-to-broker.

NOTES: [paste voice transcript]
Pairs with: sales:call-summary
Trick 02 · LOI Smell Test

Paste an inbound LOI. Get the truth in plain English.

Drop the LOI in. Claude flags every clause that deviates from market, every silent omission (op-ex stops? assignment? exclusives? holdover?), and translates the lawyer-speak into "what they really mean." 30 seconds of clarity before you respond.

Prompt
Review this LOI as if you're a tenant-rep broker reviewing for me. (1) List all material business terms in a clean table. (2) Flag every clause that's tenant-unfavorable vs. market in [city/asset class]. (3) Call out anything notably MISSING (op-ex stops, assignment, exclusives, holdover, options, TI). (4) Give me one paragraph in plain English of what the landlord is actually trying to do.

LOI: [paste]
Pairs with: legal:review-contract
Trick 03 · Cold Outreach

Outreach that doesn't sound like an AI wrote it.

Give Claude one prospect's LinkedIn URL plus their company website. It writes outreach that references something specific they actually said or did — not "I noticed you're a leader in your industry." The difference is the difference between a reply and a delete.

Prompt
Write a 90-word cold email from me ([your name + role]) to [prospect name] at [company]. Mine these for one specific, recent thing they said or did: [LinkedIn URL] + [company URL]. Lead with that — no "I noticed you're a leader." Then connect it to one specific way I help [their type of company]. Close with a soft ask: 15 minutes next week. Tone: peer, not vendor.
Pairs with: sales:draft-outreach
Trick 04 · Comp Sheet From Scratch

Messy comps in. Clean side-by-side out.

Paste 3+ recent lease comps in any format — PDFs, listing screenshots, broker emails, CoStar exports. Claude normalizes them into a clean side-by-side table, calls out the outlier, and writes you the talking point for your next pricing conversation.

Prompt
Below are 3+ lease comps in mixed formats. (1) Normalize into a side-by-side table: address, SF, $/SF, term, escalations, TI, free rent, NER. (2) Calculate effective rent for each. (3) Call out the outlier and explain why. (4) Give me one talking point I can use to position MY listing at [target rate].

COMPS: [paste anything]
Works in plain Claude — no skill required.
Trick 05 · Counter-Offer Coach

The hour of negotiation prep, in 90 seconds.

Tell Claude the deal terms, both sides' positions, and what each side cares about most. It drafts the counter, the rationale you'll use to defend it, and three concessions you can give if they push back. The negotiation prep that used to take a quiet hour, now done before your next call.

Prompt
Negotiation coaching. DEAL: [property, parties, term sheet]. THEIR LAST ASK: [what they sent]. WHAT THEY CARE ABOUT MOST: [TI, free rent, term length, etc]. WHAT MY CLIENT CARES ABOUT MOST: [same]. Output: (1) draft counter-offer, (2) 1-paragraph rationale I'll use to sell it, (3) 3 concessions ranked by give-up cost, (4) 1 trap to watch for in their next response.
Works in plain Claude — no skill required.
Bonus · The Builder Move

Stop copy-pasting. Save it as a Skill.

The meta-trick. If you find yourself running the same prompt every Monday — that's a Skill. Claude (and now ChatGPT) can save your repeatable workflow so next time you just type one command and it runs. This is the move that turns Claude from "chatbot" into "operations team." It's how I built my own monthly leasing report.

Prompt to start
I want to build a custom Skill in Claude that runs my [workflow name]. Walk me through it: (1) what the Skill should do, (2) the exact prompt template, (3) what inputs it asks me for, (4) what output format it returns. Then save it.
Pairs with: Claude's Skills feature in Cowork mode.

The deal is the easy part.

These five tricks won't replace your judgement. They'll buy you time to use it. That's what AI in CRE actually is, today, in 2026 — not a replacement for the broker, but a buyback of the hours we waste on busy work.

The signals are already there. We just need to teach the system to see them.

The build itself

See what I'm actually building.

Signal Intelligence is the platform behind everything in this post — a CRE intelligence engine built on data anyone can pull from a public source. Brokers, owners, lenders. Currently invite-only while we harden the core. Get on the waitlist.

Visit signalintelligence.app
Live · 312,295 parcels indexed · Oklahoma