HOW IT WORKS
Two stages, from the whole universe to a cited verdict
Every strategy runs the same way: a fixed quantitative screen narrows the field, then an AI evaluator reads the survivors' filings. Nothing is personalized — the same company gets the same verdict for every subscriber.
Filter the universe
Each strategy declares a fixed set of quantitative filters — return on capital, balance-sheet strength, payout coverage, whatever its published framework requires. They run against the SEC EDGAR operating universe, identically every time.
Near-misses aren't discarded silently: the screen keeps the rationale for every company that dropped out, one filter from passing.
Read the filings
Survivors go to the strategy's evaluation prompt — frozen, versioned, identical for everyone. The evaluator cross-references the pre-computed metrics against the filing text: the metrics say what, the filings say why and whether it's durable.
The output is the structured verdict you saw dissected on Anatomy of a verdict: scored dimensions, trap signals with sources, unknowns, and a tier.
Your derived strategies from the Strategy Lab run through the same two stages.
One of three verdicts on framework fit
General Analysis
Twelve strategies express a published tradition. The thirteenth, General Analysis, is the house lens: a methodology-neutral read of the filings for when you want the evidence organized before choosing a discipline.
Same engine, same citation rules, same honesty about gaps — without a framework's scoring rubric. It doesn't appear on the lens pages because it isn't one.
APP SCREENSHOT — GENERAL ANALYSIS OUTPUT
Annotated capture pending · state without price columns · current vocabulary only
See a whole verdict, taken apart
The workhorse page: one sample output, annotated part by part.