ListingPrompt / Guides
Real estate field guideChatGPT prompts for realtors
You don't need a hundred prompts. You need a handful that cover the work you repeat every week, and you need them written well enough that the first draft is usable. These eight come straight from the ListingPrompt playbooks, each tied to a real task in an agent's week.
Copy them into a ChatGPT project or a note on your phone, fill the [brackets], and adjust the tone to your own voice.
1. Listing description
"You are a real estate copywriter. Write a 150-word MLS listing description for: [beds/baths/sqft/address/features]. Lead with the strongest feature, use concrete sensory details, avoid Fair Housing violations, and end with a call to schedule a showing. Then give 3 headline options under 60 characters." See the full listing description guide.
2. A week of social posts from one listing
"Using this listing description: [paste], create a 7-day social plan: 1 Instagram carousel outline (6 slides), 2 Reels hooks with 15-second scripts, 2 Facebook posts, 1 LinkedIn post for agent network, 1 'just sold'/'open house' teaser. Include hashtags (max 8) and a CTA for each." More in the social media guide.
3. Speed-to-lead follow-up
"A new lead came in: [name, property viewed, price, source, message]. Write (1) a text message under 300 characters, (2) a short email, and (3) a 4-touch follow-up sequence over 10 days. Sound like a helpful local agent, ask one easy question, never pushy." See lead follow-up with AI.
4. Neighborhood guide
"Research [neighborhood, city] for home buyers. Cover: commute times to [hub], schools (cite sources), parks, dining, typical home prices (cite date and source), and upcoming developments. Format as a 1-page guide with headings. List all sources at the end so I can verify each claim." This one works best in a tool with web search, such as Perplexity.
5. Virtual staging brief
"Stage this empty [room type] in [modern farmhouse / Scandinavian] style, keep walls, windows, floors and dimensions unchanged, natural daylight, realistic furniture scale." Always label the result as virtually staged. The full playbook is on the homepage.
6. Buyer consultation prep
"I'm meeting buyers: [names, budget, pre-approval status, must-haves, timeline]. Create a 30-minute consultation agenda, 10 discovery questions, a plain-English explanation of the buying process in [state], and likely objections with responses." Afterwards, paste your meeting transcript and ask for a buyer profile and next steps.
7. Monthly market update
"Here are this month's stats for [area]: [median price, DOM, inventory, sold count vs last year]. Write a 250-word homeowner newsletter: one headline insight, what it means for sellers and buyers, one local tip, and a soft CTA for a free home value estimate." See the market update guide.
8. Contract and disclosure explainer
"Explain this [inspection report / purchase agreement section] to a first-time buyer in plain English: [paste]. Highlight the 5 items that matter most, deadlines, and questions they should ask their attorney or inspector. Add a note that this is not legal advice." See explaining contracts with AI.
How to get better answers from any of these
Give the model facts, not adjectives. Tell it the length and the format. Ask it to list the facts it used so you can check them. And save the prompts that work in a ChatGPT project or custom GPT so you aren't retyping them every time.
Save it as a reusable assistant
Retyping prompts is where most agents give up. In ChatGPT, create a project or custom GPT for this task, paste the prompt into its instructions, and add one or two examples of output you were happy with. In Claude, a project with the same instructions does the job. From then on you only paste the facts. Keep a short note of what you changed each time you edit the instructions, so you can go back if a change makes the drafts worse.
A two-minute review checklist
Before anything AI-drafted leaves your hands, run through the same five checks. Is every fact, number and feature in the draft something you supplied or can verify? Does it describe the property and the service rather than the kind of person who should buy? Is it the right length for where it's going: MLS field, text message, email or caption? Does it sound like you, or like an ad? And does it include anything your brokerage or state requires, such as brokerage name, license number or a staging disclosure? If any answer is no, fix it or ask the model for a revision with that specific instruction.
Keep a running list of the fixes you make most often. After a week or two, add them to the prompt itself. That's how a generic prompt becomes your prompt, and it's the single biggest improvement you can make to AI output.
Before you use it
Every prompt on this site is a starting point, not a finished product. AI drafts fast, but you are the licensed professional: check every fact against the MLS and your own notes, keep Fair Housing rules in mind, and follow your brokerage's and your state's advertising rules. Treat the output as a first draft from a quick junior assistant who has never seen the property.
Frequently asked questions
- What is the best ChatGPT prompt for real estate agents?
- The one you'll reuse weekly. For most agents that's the listing description prompt and the lead follow-up prompt, because those tasks repeat constantly.
- Is it safe to paste client information into ChatGPT?
- Share only what the task needs, check your brokerage's policy, and review the data settings of the tool you use. Avoid pasting financial documents or anything you'd not want stored.
- Do these prompts work in Claude or Gemini?
- Yes. They're plain instructions, so any capable chat assistant will follow them.