ChatGPT Prompt for Real Estate Analysis: 12 Data Prompts

A good ChatGPT prompt for real estate analysis gives the AI your own listing data, tells it which numbers to calculate, and makes it show the math. That turns a pasted MLS export into a market snapshot, a price per square foot range, and a client brief you can check line by line. The 12 prompts below cover neighborhood markets, comps, competition, and client updates, and they work in ChatGPT, Claude, or Gemini.

These prompts summarize data you supply. They are not an appraisal, a broker price opinion, or investment advice, so verify every figure against your MLS or public records before you share it.

Read the market from your data

1. Neighborhood market snapshot

Here are the sold listings I pulled for [area] from [start date] to [end date]: [listing data]. Calculate the median sold price, price per square foot for each sale and the median, median days on market, and the sale-to-list ratio. Show each calculation and use no data I did not give you.

2. Months of supply check

In [area], [number] homes closed in the last [months] months and [number] are active now. Work out the monthly closing pace and the months of supply, show the formula, and keep pending listings out of both numbers.

3. Sale-to-list and price cut read

From these listings: [listing data], list each sale-to-list ratio and each price cut on active listings as a percent of the original price. Then tell me in two sentences what the pattern suggests about pricing, without labeling the market hot or cold.

4. Outlier finder

Look at these sales: [listing data]. Flag any that stand apart because of condition notes, very long or very short days on market, or a price far from the rest. Recalculate the median price and median price per square foot without them and show both versions.

Place a property among the comps

5. Comp similarity sort

My subject property is [beds/baths, square feet, key features]. Rank these sales by how similar they are on beds, baths, and square feet: [listing data]. Explain each ranking in one line and do not add comps.

6. Price per square foot range

Take the three sales most similar to my subject: [comps]. Apply their lowest and highest price per square foot to [subject square feet] and show the math. Then list the differences this range cannot capture, such as condition, lot, and updates.

7. Active competition check

These are the active and pending listings near my subject: [listing data]. For each, give the list price per square foot, days on market, and any price cut. Tell me where buyers seem to be pushing back. Do not guess sold prices for pendings.

8. Stale listing diagnosis

This listing has been active for [days] days: [listing details]. Compare its list price per square foot and features with these recent sales: [sold data] and give three possible reasons it has not sold, each tied to a number in the data.

Turn the numbers into client work

9. Seller market update

Write a short market update for my seller client using only these results: [market snapshot]. Keep it under [word count] words, lead with the two numbers that matter most for pricing, and end with what we will watch next month.

10. Buyer client brief

Turn this market snapshot: [market snapshot] into a brief for a buyer client looking at [property type] around [price range]. Describe homes and numbers only. Do not describe who lives in the area, schools, or safety, to stay within the Fair Housing Act.

11. Quarter over quarter trend

Here are two sets of sold data for [area]: [last quarter] and [this quarter]. Compare median price, median price per square foot, days on market, and sale-to-list ratio in a small table, show the change for each, and note any change driven by one or two sales.

12. Investor rent check

I am weighing [property] at [price]. Here are the rental listings I found nearby: [rent data with beds, baths, and square feet]. Give the rent range for similar units and the rent per square foot, and say which listings are too different to compare. Use only these listings.

Run the full analysis with one prompt

The flagship Real Estate Market Analysis Prompt: Sales Data to Brief does all of this in one pass: a data check, a sold snapshot with every calculation, months of supply, outliers, where a subject property fits, the competing actives, and a brief for your client. Its example works through a small subdivision with six sales and shows how one as-is sale shifts the medians.

Two habits keep the analysis honest. Paste fresh data each time, because closings after your export will change the numbers. And keep the brief about properties and prices, never about the people in a neighborhood.

Related real estate prompts

Buying a rental? Run the numbers with the rental property deal analyzer and browse more ChatGPT prompts for real estate investors. Agents heading into a listing appointment can use the listing presentation prep prompt and the wider set of ChatGPT prompts for real estate agents. For income properties, see the rent roll to deal screen memo and ChatGPT prompts for commercial real estate. When the analysis turns into a listing, write it with the Fair Housing MLS listing prompt.

Related: ChatGPT prompts for property management and how to write a Fair Housing MLS listing from property facts.

Find more in the Real Estate category, look through Browse, or post your own on Share.