Compare a subject property against 3–8 comps. Summarize where the subject stands on price/sqft, days on market, condition adjustments. Flags outliers. Informational read for the listing agent or buyer's agent; not a substitute for a CMA or formal appraisal.

Comparable Property Analyzer

Sanity-check a list price (or buyer offer) against 3–8 comps in 60 seconds, before opening a formal CMA.

What it does

You feed the AI a subject property and a few recent comps. It returns: 1. Subject snapshot 2. Comps table sorted by relevance with $/sqft and condition vs subject 3. Median + range $/sqft, implied subject value range 4. Adjustments to consider (renovation, view, lot, location) 5. Outliers flagged (>25% off median, weird DOM) 6. Reasonable price range 7. What's missing in your data

When to use it

Pre-listing meeting prep — get a fast read before the homeowner conversation.
Buyer-side: vetting whether the asking price is defensible.
Mid-listing price adjustment — has the market moved since you priced?
Teaching a new agent how to think about comps.

When NOT to use it

As a substitute for the formal CMA you prepare for the seller (it isn't one).
As a USPAP appraisal (it isn't one).
For unique properties (custom homes, large acreage, historic) where automated comp logic is weak. Trust your appraiser.
For commercial properties — this skill is residential-tuned.

Setup

None. Pure AI prompt.

Invocation

@comparable-property-analyzer
SUBJECT: 412 Oak St, 3bd/2ba, 1650sqft, 0.25ac, built 1962, recent kitchen reno (2023), targeting list $499K
COMPS:
  - 425 Oak St: 3/2, 1700sqft, sold $495K, 30 days ago, 0.1mi away, dated kitchen
  - 1208 Maple Ave: 3/2, 1580sqft, sold $475K, 45 days ago, 0.3mi away, similar condition
  - 350 Elm Pl: 3/2, 1750sqft, sold $525K, 12 days ago, 0.4mi away, fully renovated
  - 1102 Oak St: 3/2, 1620sqft, active $510K, listed 8 days, 0.05mi away, similar condition
  - 287 Pine Ridge: 3/2, 1700sqft, sold $410K, 75 days ago, 1.2mi away, needs work
QUESTION: is $499K defensible or am I leaving money on the table?

What it won't do

Recommend a specific list price (gives a range; you decide).
Speculate about future market direction.
Invent comp data you didn't provide.
Characterize neighborhoods by demographic.