Kyle Tran
Real Estate Finance · Applied Analytics · AI
USC B.S. Real Estate Development · Minor, Finance & Applied Analytics
An agent I built reads 400 sources a week. I edit what survives. Mondays, 10 AM PT.
Free · Every claim sourced
412 feeds swept every Monday at 23:00 UTC — RSS, APIs, filings.
Embeddings dedupe roughly 2,100 items down to ~220 distinct stories.
CRE-relevance weighting ranks stories; the top 22 survive to draft.
Claude drafts all three sections with citations back to source.
I read every line, cut what does not hold up, and send it myself.
The whole pipeline runs on a scheduled GitHub Action: async Python fetches and dedupes the week's sources, embeddings land in Postgres via pgvector for clustering, and Claude drafts each section with citations back to source. I read every line before it ships — the agent proposes, I decide.
July 23, 2026 · 15 stories