From ticker to verdict
Each report is produced by the same six-step pipeline. The data and scoring are deterministic; the judgment is written by Claude, grounded strictly in the fetched numbers.
Input a ticker
A single symbol — e.g. AAPL, MU, KO — is all that's needed.
Fetch the data
Two local command-line tools pull price history from Interactive Brokers and a fundamentals snapshot from Finviz.
Normalize & score
Raw figures are typed and run through a config-driven Buffett scorecard — 12 criteria, each pass / warn / fail, weighted into an overall verdict.
Sentiment read
A separate panel captures what the Street thinks: analyst target & recommendation, institutional/insider ownership, short interest.
AI analyst narrative
Claude writes the full read — valuation, bull & bear, best-case & black-swan scenarios, a catalyst timeline, investor views & credit ratings, plus a swing-trade and a long-term stance — grounded only in the fetched numbers.
Archive the report
Everything is assembled into a self-contained HTML report and published to the archive.