Train Claude Code like a new analyst to build CMAs and listing presentations, with a compliance check before any deck goes out
Conor Doyle, CFA, co-founder of Six Ten Associates, a two-agent commercial and residential team at Keller Williams Main Line serving Philadelphia, its suburbs and the Jersey Shore (licensed in 2025 after J.P. Morgan's private bank and REIT investing), on the Real Estate AI Flash podcast
Claude Code, trained on a year of his own CMAs and listing-presentation feedback, drafts CMAs in his format, suggests what data each one needs and saves every correction he makes as a rule for next time. A separate compliance check reviews each deck for the right New Jersey and Pennsylvania license and marketing details before it goes out.
Claude $17/mo billed annually ($20 monthly); free plan available; he says he's up to $200 a month on Claude
Advanced · or we do it from $149/mo
Claude, Claude Code, Bright MLS
The problem
When he moved into brokerage he no longer had a team to make slides, presentations and models, and he couldn't afford to hire an analyst. Commercial CMAs need data that is easy to find in Philadelphia but thin at the Jersey Shore.
What happened
He says it often catches things in documents or listing descriptions that he missed, such as a lease maturity or a new lease signed, and that because it records each correction, it now asks "Did I miss this?" or fixes the issue up front. He still pulls comps himself and corrects it when price per unit or cap rate comes out too high or too low, and its suggestions are sometimes bad, such as a cap rate on a vacant turnaround building. No time or money figures are given. Owner-told.
Quoted in the source: Conor Doyle, CFA, co-founder, Six Ten Associates. Source: Real Estate AI Flash, Ep 143: How AI Gives Every Agent a Team of Experts (Rajeev Sajja with Conor Doyle) (2026-10-07) · Added 2026-10-19.
How to set it up yourself
- What Six Ten Associates does: Conor Doyle fed his past CMAs and listing-presentation feedback into Claude Code (his "CMA agent"). A data agent suggests what each CMA needs, he sources and cleans that data himself, and a compliance agent checks New Jersey and Pennsylvania license and marketing details before a deck goes out.
- Give Claude Code your past CMAs and presentations plus notes on which ones worked and which questions sellers asked. Ask it to describe your format and sections back to you before it drafts anything new.
- For each listing, ask it what data a strong CMA needs, keep the suggestions you agree with, pull the comps yourself and paste them in with the prompt below. Check every figure; when something is wrong (a cap rate on a vacant building, say), tell it the correct rule and ask it to save that rule to memory.
- Write a short compliance checklist for each state or city you market in (license numbers, brokerage name, required wording) and have Claude check every deck against it before you send it.
Copy-paste prompt
You are my CMA analyst. Subject property: {ADDRESS}, {PROPERTY TYPE}, {CONDITION}. Comps I pulled: {COMP DATA}. Notes from the listing photos: {PHOTO NOTES}. Using only this data, place the subject on the comp range for price per unit, and for cap rate only if it produces income; if it is vacant or needs work, show renovation cost and upside instead. Never invent comps, rents, figures or license numbers; write MISSING where data is absent. Then check the deck against {COMPLIANCE CHECKLIST}. Output: 1) value range table, 2) details in the documents I may have missed, 3) compliance issues, 4) questions for me.One short email a day: 3 new AI use cases from real small businesses, each with its source and setup steps, plus a Tool of the Day. Free, no spam, unsubscribe anytime.
Tools used
Claude
AI assistant for writing, long documents, analysis and coding help.
From $17/mo billed annually ($20 monthly) (checked 2026-10-18)
Visit site →Some tool links may be affiliate links. Disclosure
Checked prices: Claude: from $17/mo billed annually ($20 monthly) (verified 2026-10-18)
Rather not do it yourself?
We'll set this up in your tools, in your voice, tested. $149/mo with setup included (6-month minimum), or $497 pay-once. Satisfaction guarantee: we'll fix it until it works. Pay-once setups: or we refund your setup fee. $149/mo plan: cancel in the first 30 days and we refund your first month. Terms. We reply within 1 business day.
Get this set upRelated for Real estate
Draft a month of real estate social posts with ChatGPT and repurpose the winners
Each evening ChatGPT drafted 20 to 30 short Threads posts, which he scheduled; the best performers became Canva quote cards, then 30 to 6…
ChatGPT
Canva AI (Magic Studio)TThreadsWrite listing descriptions with ChatGPT and keep the agent's voice
The broker uses the free ChatGPT to draft property listings and other mundane writing, then edits for accuracy and SEO.
ChatGPTUse ChatGPT for listing copy, client follow-ups and market reports
ChatGPT drafts listing descriptions, personalised follow-ups using past conversations with each client, and neighbourhood market reports …
ChatGPTCanva AI (Magic Studio)Running something like this in your business? Submit your use case and we'll credit you with a link.
Get 3 new AI use cases every morning
One email every morning: 3 new AI use cases from real small businesses, each linked to its source, plus a Tool of the Day. Free. No spam, unsubscribe anytime. Privacy