WHY TRUST THE OUTPUT
Trust is a property of the pipeline, not a promise.
Nothing here asks you to take the output on faith. Every verdict is built so you can check it — and so the system can't quietly pretend to know things it doesn't.
Evidence is the filings — nothing else
The evaluator receives targeted sections of SEC EDGAR filings and pre-computed metrics. Those are the entire evidence base. What the model remembers about a company from training is never a source — a missing section becomes an unknown, not a guess.
No source, no claim
Every factual assertion — every trap signal, every line of the thesis — must cite its form, section, and date. A signal that can't name its source is discarded, not shown.
(10-K, Item 1A, 2026-02-12)Unknowns are a feature
When a filing doesn't disclose something the methodology needs, that dimension is marked unknown and the verdict is capped accordingly. Better an honest gap than a confident fabrication.
segment-level margin split not disclosed in source materialsYou see the cost before it runs
Every scan shows its estimated cost up front, and every run reports what it actually spent. Research you can audit includes the bill.
est. 25 candidates · $0.42What this can and can't do
The output is AI-generated research. It can misread a filing; it cannot know what a filing doesn't say; and it never knows anything about you. Treat every verdict as a structured starting point for your own reading — the citations exist so you can do exactly that.
See the discipline applied, end to end
One sample verdict, dissected with every citation visible.