Work / Market analysis
CASE 002 / REAL ESTATE / CMA

AI comparative market analysis

Realtors need comparative market analyses to win listings, and doing one properly takes hours of pulling comps, checking photos, and writing it up. I built the AI system that generates them automatically: live MLS data in, a polished report out, with a feedback loop so agents can revise a report by simply replying to an email.

2MLS APIs integrated
~37production tickets shipped
LLM+CVtext and image analysis
e2eemail-reply revision loop
RoleLead AI & Automation Engineer
Timeline2025 - present
IndustryReal estate / proptech
TypeAI pipeline, live

The challenge

A CMA is only useful if it is both fast and right. The raw material lives in MLS systems with messy, inconsistent data; the photos matter as much as the numbers; and a first draft is rarely the final one, because the agent knows things about the property the data does not show. So the system had to pull live MLS data, judge listing photos like a human would, produce a report a realtor is proud to send, and then take corrections without anyone touching a workflow.

The approach

A layered pipeline: MLS data comes in through n8n, an LLM prompt chain and a computer-vision classifier turn it into analysis, the report goes out as HTML or PDF, and email replies feed revisions back in. Prompts live in a portal so they can be tuned without redeploying anything.

SYSTEM ARCHITECTURE// cma pipeline
Sources
MLS APIsRepliers, Cornerstone
Ingestion
n8n workflowsfind-MLS, comparables, cleansing
extractor APIproperty details, address validation
AI
LLM prompt chainanalysis + narrative
image classifiercomputer vision, Cloud Run
Delivery
CMA reportHTML / PDF
Feedback
email repliesrevision requests, applied automatically
Prompt ops
prompt portalmanage prompts without redeploys

What I built

Results

liveMLS data in every report
1 replyto revise a report
autoQA via bulk workflow tests
in-chatwired into the Agent Assistant

What used to be hours of manual comp-pulling is now a request: the system fetches live MLS data, reads the photos, writes the analysis, ships the report, and takes corrections by email. It runs as part of the realtor Agent Assistant, on a stack of n8n, LLMs, Cloud Run, and Supabase.

Want a system like this, built to last?

Book a free call. You will leave with a clear plan for your own AI automation, whether or not we work together.

Book a free call