Turn a fresh CMA into a calm, data-backed price-reduction email for sellers, and give every agent a shared brand-voice doc
Jaime Peca, team lead and partner on the Driscoll Peca team (The Real Brokerage, about eight agents and three staff) outside Ottawa, Canada, on the Real Estate AI Flash podcast
She pulled the listing's MLS sheet, ran a new CMA on 30-day sold data, and gave both to an AI assistant along with the hard conversation she needed to have; it drafted a detailed email explaining the numbers. She also wrote a brand-voice document (how the team speaks, what it does and doesn't say, no emoji blasts or em dashes) that every agent loads into the AI tool they use.
ChatGPT Free $0; Go $8/mo; Plus $20/mo · or Claude Pro $17/mo billed annually ($20 monthly)
Easy · or we do it from $149/mo
Varies
The problem
In a slow market, listings sat overpriced and sellers weren't hearing her when she raised price. Writing an email with the data that didn't feel emotional took at least an hour.
What happened
She says the email would have taken her at least an hour to put together, and after she sent it the seller agreed to a $100,000 price reduction. She now keeps an hour every Thursday for agents to bring their AI questions. Self-reported.
Quoted in the source: Jaime Peca, team lead, Driscoll Peca team (The Real Brokerage). Source: Real Estate AI Flash EP 123: How Jaime Peca Built AI Without a Tech Background (Rajeev Sajja) (2026-05-20) · Added 2026-10-18.
How to set it up yourself
- What the Driscoll Peca team did: a new CMA from 30-day sold data plus the listing's MLS sheet went into an AI chat with the price conversation she needed to have, and it drafted the seller email. Agents also load a shared brand-voice document into whichever AI tool they use. The tool behind the email isn't named in the part of the episode we read.
- Write the brand-voice doc once: who you serve (for her team, rural homes with wells, septics and acreage, not city condos), words you use and avoid, no emojis or em dashes, your sign-off. In ChatGPT, select New project in the sidebar and paste it under ••• > Project settings (in Claude: Projects > New project, then the project instructions).
- For each stale listing, export the MLS sheet and a CMA of comparable sales from the last 30 days and paste them with the prompt below into that project. Check every number and address against the MLS before sending; the decision stays with the seller.
- Send it from your own email and follow up with a call. Save the emails that worked in the project as examples, so the next one starts closer to your voice.
Copy-paste prompt
Using our brand voice, write an email to {SELLER NAMES} about their listing at {ADDRESS}, on the market {DAYS ON MARKET} days at {LIST PRICE}. Data: MLS sheet {MLS SHEET}; CMA of sales in the last 30 days {CMA}; showings and feedback {FEEDBACK}. Explain calmly what the sold data says, what staying overpriced costs them and two options ({OPTION 1}, {OPTION 2}). No pressure language and no blame, under 250 words. Use only the numbers provided.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.
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
Have Claude sweep your CRM each morning and draft follow-ups for leads you'd forget
A Claude-based assistant pulls Follow Up Boss leads, notes and deals, scores each lead A–D using the Keller Williams model, drafts a pers…
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…
Have AI draft replies to tenant maintenance requests and suggest the vendor, with staff approving
n8n workflows draft each reply to a tenant maintenance request, pull out details (unit, issue, photos, access), suggest a vendor type and…
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