Client engagement
Lead triage and custom offer generation
Problem
A real estate operator was sorting inbound leads by hand, then building offer terms one deal at a time. Two hours of work before a single number reached a seller. The bottleneck was not deal flow. It was the operator.
Built
An intake pipeline that scores and routes incoming leads against the operator's own criteria, then generates customized offer structures for the ones that clear. The judgment stayed with the operator. The typing did not.
Underwriting time per deal
What I would do differently
Started it sooner. On this build I would layer in light CRM functionality from the start instead of leaving it for later.
Shipped to paying users
Offer structuring and LOI generation
Problem
Investors stall at the offer. They can find a property and still not know what to send, so nothing gets sent. Every deal dies in the gap between interest and paper.
Built
A tool that takes a property and produces three viable offer structures, including seller financed terms, then generates the letter of intent. In daily use by paying members of my education company.
What I would do differently
We did add the light CRM on this one. What I would change is pulling in customer feedback sooner instead of building in a vacuum. The feedback surfaced corner cases we had not considered and made the tool much better.
Internal AI stack
Call transcription and retrieval agent
Problem
Hundreds of hours of recorded coaching calls held answers nobody could find. The knowledge existed and was functionally unsearchable.
Built
A Whisper transcription pipeline feeding an assistant that answers member questions from what was actually said on those calls, with the source. Not a chatbot bolted onto a FAQ. Retrieval over real proprietary material.
What I would do differently
Build in fault monitoring for the scheduled job. It ran for six months, then a backend billing issue stopped the transcription, and nothing alarmed on that failure, so it sat broken for a while before we caught it.