Real estate · Listing descriptions · Case
@staceywalterss: a listing description aimed at one buyer type; buyer personas with Claude
On the first day with Claude, the agent pasted in a random listing from their market and gave it a role and a target: act as the listing agent, write a property description for a young family, keep it warm and specific. The prompt was saved to reuse. Reported result: Says the draft beat half their own MLS listings (no number).
@staceywalterss
Real estate agent · market not stated · first day using Claude
Tool ClaudePublished 2026-07-09Sells anything? Promotes a service
- A listing from her market + role prompt
- Claude
- Description for a young family
- Task
- A listing description aimed at one buyer type; buyer personas.
- Tool
- Claude.
- What they did
On the first day with Claude, the agent pasted in a random listing from their market and gave it a role and a target: act as the listing agent, write a property description for a young family, keep it warm and specific. The prompt was saved to reuse. The agent then gave Claude the preferences of their top three buyers and asked for full personas: where they spend time and what would put them off. Note that this was one hour of use, not a tested workflow.
- Result
The agent says the description was better than half of their own listings already on the MLS. No number is given.
Self-reported; not verified.- Where it goes wrong
- Not mentioned in the source.
- Conflict of interest
- Promotes a service The second half of the video promotes Trolto, a service that the agent says writes neighbourhood blogs and built their website. The research notes flag it as a likely sponsored segment.
- Source
- TikTok @staceywalterss · published 9 Jul 2026
- Watch the video — the listing prompt is at 0:04–0:19; the promo starts at 0:42. TikTok has no time links.
Act as a listing agent. Write me a property description, this home, targeting a young family. Warm and specific.
Published 2026-07-09 · rewritten in our words from the video · #stacey-walters
More from this task

Shares numbersYouTube2025-09-03
Brad Cohen
Brad used to sit down with his notes from the listing appointment and the MLS sheet and spend about half an hour on each description.
ChatGPT → custom GPT · ~30 min → ~2 min per description; 7 listing deliverables in minutes · self-reported

Shares numbers2023TikTok2023-05-21
@kalachejackson_realtor
The agent copies all the property information from a Zillow page, pastes it into ChatGPT and types "Write an MLS description for this house." If the first draft is too basic the agent clicks "regenerate response" and takes the second one.
ChatGPT (2023) · Draft in under 30 seconds · self-reported

CautionTikTok2026-10-14
@chriswhartonrealtor
The agent took real photos of the kitchen and backyard from one of his own recent listings and asked ChatGPT to "improve" them, then to go further.
ChatGPT (images) · No number; a warning
Related: All listing descriptions cases · Claude for real estate agents · Real estate report
← Back to Listing descriptions · How we collect cases
