Live data from Interactive Brokers and Finviz, run through a Warren Buffett quality & value scorecard, then an AI analyst writes the honest verdict — bull case, bear case, and what would change its mind. Every run is archived below.
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.
A single symbol — e.g. AAPL, MU, KO — is all that's needed.
Two local command-line tools pull price history from Interactive Brokers and a fundamentals snapshot from Finviz.
Raw figures are typed and run through a config-driven Buffett scorecard — 12 criteria, each pass / warn / fail, weighted into an overall verdict.
A separate panel captures what the Street thinks: analyst target & recommendation, institutional/insider ownership, short interest.
Claude writes the full read — valuation, bull & bear, best-case & black-swan scenarios, near-term catalysts, investor views & credit ratings, plus a swing-trade and a long-term stance — grounded only in the fetched numbers.
Everything is assembled into a self-contained HTML report and published to the history below.
Interactive Brokers supplies the price picture; Finviz supplies the fundamentals. Both are reached through small, read-only local tools — not hosted APIs.
Reached via local read-only CLI → IB Gateway :4002
Nothing leaves the machine · quotes delayed on the paper account
Reached via scraped quote page, cached 1h quote.ashx
~70-metric snapshot · one point in time (trends come from IBKR)
Twelve criteria split business quality from price. Each is scored pass / warn / fail against configurable thresholds and weighted into a 0–100 score and verdict band. The point isn't the number — it's separating "is this a wonderful business?" from "is it cheap?".
Every analysis run, newest first. Click any card to open the full self-contained report.