09·AI / ML·Passion project
Footing
A white-label AI co-pilot for US luxury brokerages, expanding from a Miami-Dade proof of concept toward a nationwide layer over the MLS, CRM, and public records a brokerage already runs. Code complete; the hosted backend is currently offline.
ResultCode complete over three real public and first-party data sources, live in Miami-Dade before the hosted Ollama backend went unreachable.
[ Ask about this build ]01Discover
Why it exists.
A brokerage's actual stack already covers most of what an agent needs: MLS, CRM, county records, inbox. The friction isn't missing data. It's that each source lives behind its own login and its own mental model, so an agent context-switches all day instead of just asking a question. Another data source would be commoditised the moment it shipped; the MLS bundle already sells that.
Footing (renamed from Infinity Broker 2026-09-09) wraps that answer in a white-label demo a brokerage can put its own name on: the same agent loop, reskinned per team, over the brokerage's own inventory and leads.
Solo build, expanding from a Miami-Dade proof of concept toward a nationwide market. Code complete over three real data sources - county GIS parcels, the Property Appraiser, and a CRM - and was live before the hosted backend went unreachable.
02Define
The brief.
Give a US luxury brokerage one plain-language interface over the MLS, CRM, and public records it already pays for, instead of selling another data feed.
03Develop
What it took
Skills behind it.
Primary discipline plus the support stack.
Skills demonstrated
- AI & Machine LearningPrimary
Self-hosted Qwen3 fine-tune driving the multi-tool agent loop, kept reliable with per-tool result pinning and a loop break.
- Prompt EngineeringSecondary
Honesty as a layered contract: the system prompt sets it, deterministic code enforces it.
- Backend EngineeringSecondary
Serverless tool loop on Vercel; Neon Postgres for leads and hourly alerts; county GIS, appraiser, and RESO integrations; a Bedrock backend written but not yet provisioned.
- Product StrategySecondary
Repositioned from another data feed to the orchestration layer, then from a Miami-Dade demo to a nationwide one - the interface is the product.
- Frontend EngineeringSupporting
The white-label demo a brokerage can put its own name on, honest fallbacks included.
Develop · Notes
The build, in full.
How it came together and the decisions on the record - kept off this page so the case study stays a read, not a scroll.
Read the full build notes04Deliver
What shipped.
Code complete over three real public and first-party data sources, live in Miami-Dade before the hosted Ollama backend went unreachable. Deterministic honesty guardrails keep it accurate (every figure traced to a real tool result, all arithmetic server-side), backed by a regression suite pinning every fabrication found in live stress-testing. Nationwide expansion (Florida, North Carolina, Wisconsin importers) is written but not yet loaded. The county sources were queried live against Miami-Dade's own endpoints rather than imported as a snapshot, and the CRM inventory behind the demo is generated sample data, not a brokerage's book.
Everything but MLS asking prices ran on real data: county records, CRM, the agent loop itself, not a mocked dataset standing in for a source that isn't connected. That code is complete; the hosted backend that served it is currently offline. The remaining gap, a brokerage's own RESO credentials for live MLS asking prices, was never about the build itself.
By the numbers
Honesty-guardrail tests
of 425 total across 17 test files
Data sources integrated
County GIS parcels, the Property Appraiser, a CRM; none reachable while the backend is offline
Warm response
chip suggestions decoupled
Frames
Selected from the work.
6 frames
01Landing page, live demo open 02CRM pipeline, in use 03CRM dashboard 04Per-listing page, honest no-photo fallback 05Mobile chat 06The same product as amber text on a 1983 luggable, because the interface is language
See also
AI / ML
Barnes Dubai LLM
A domain-tuned language model for a Dubai brokerage, answering in seconds the market-comparison brief that used to take an analyst an afternoon.
AI / ML
Data Centre
BARNES Dubai's internal data tooling: an entity-centric valuation platform and AVM, absorbed into a broker tool over ~840,000 ownership records.