In my last AI Marketing System course, Lorraine shared something that should make every agent uncomfortable. After using AI to look through her past emails she found 7 people in her own sphere who had mentioned buying or selling in the next couple of years. Then she ran a property search on the past clients and realized one had a pending sale. With another agent.
Lorraine is a great agent which means she's also a busy one. And that's the problem - the clients you lose aren't the ones you forgot. They're the ones you were going to call next week.
Here's this weekend’s workflow. Three steps, 15 minutes, and you'll know who in your sphere needs to hear from you on Monday.
Step 1 | Option 1: Search Your Past Emails
Connect AI directly to your email - no exporting, no spreadsheets:
Claude — Connect your Google account in Settings
ChatGPT — Connect Google Gmail app or other email tool
Gemini — Connect your Google Workspace account
Then ask it this:
Search my email conversations for anyone who has mentioned, even casually: buying, selling, or investing in real estate. Moving, relocating, or changing jobs. Life changes that trigger moves - new baby, engagement, divorce, kids leaving, retirement, complaints about their space or commute. Asking me for market advice or neighborhood opinions.
For each person, give me their name, what they said, when they said it, how urgent it seems (now / next 12 months / 2+ years).
Step 1 | Option 2: Audit Your Past Deals List
I’ve heard from many agents that their brokerages are not allowing them to connect their email so here is another option. Export your closings from the last 5 years - just closings, not your whole CRM. Remove any private information, upload the deal data and ask it this:
Rank these past clients by likelihood of a near-term move based on: ownership duration (5–7 years is prime), property type (condos turn over faster), life stage signals (first-time buyers who may have outgrown the home, empty nesters), and purchase price vs. likely equity gain. Rank them by likelihood to move in the next year and provide a personalized reason to reach out.
Step 2: Property Check
Before you reach out, use AI to search every address on Zillow and Redfin. You can also do the search yourself on the MLS.
Active or Pending - You're late but call anyway. They might be unhappy with their agent, and you re-establish the relationship for next time.
Recently Sold - They moved but reach out anyway since they need an agent wherever they land.
Off-market - They're still yours to win.
Step 4: Send 5 Messages
Then ask it to write the intros for your follow-ups:
Write a short email to [NAME] who [bought/mentioned CONTEXT]. Keep it warm, not salesy. Reference something specific — the neighborhood, the market, what they told me. End with a soft question. Under 75 words. No subject line that sounds like marketing.
Five personalized emails. Five minutes. None of them start with "Hope you're doing well!"
The Math
8–10% of homeowners move in any given year. On a list of 75 past clients, that's 6–9 people moving — whether you know about it or not. Do nothing and maybe 2–3 call you. Run this monthly and you catch half before they call someone else.
At $12,000 average commission, that's $36,000–$48,000 in GCI from 20 minutes of work - from people who already know your name.
This is one of the sphere systems we build in my AI Marketing course that starts March 23rd. Visit the page to see almost 60 testimonials from past students and sign up for the next session.
-Matt
