HOW IT WORKS

Two stages, from the whole universe to a cited verdict

Every framework 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.

STAGE 1 · SCREEN

Filter the universe

Each framework declares a fixed set of quantitative filters — return on capital, balance-sheet strength, payout coverage, whatever its published tradition 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.

EDIT SCREEN: 15-POINT QUALITATIVE
1 · Select Metrics 2 · Configure 3 · Name & Save
CATEGORY
Size
Profitability
Leverage
Growth
Valuation
Dividend
Composite
Filing
Dilution
Exclusions
Momentum
Exception
METRICS
Market Cap (min)
Market Cap (max)
Revenue TTM (min)
SELECTED (8)
Market Cap (min)
ROIC (min)
Gross Margin (min)
Revenue Growth 3y CAGR (min)
R&D Spend Non-Zero
SBC / Revenue (max)
Sector Exclusion
Quality Flag Exclusion
8 metric(s) selected Cancel Next
SECTIONS PROVIDED TO THE EVALUATOR
[10-K Item 1 — Business][10-K Item 1A — Risk Factors][10-K Item 7 — MD&A][10-K Item 8 — Financial Statements] [8-K Item 2.02 — supporting]
These headers are the evaluator's citation vocabulary. Only provided sections and pre-computed metrics count as evidence — memory of a company is never a source. Missing sections become unknowns.
STAGE 2 · EVALUATE

Read the filings

Survivors go to the framework'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 frameworks from the Strategy Lab run through the same two stages.

THE RESULT

One of three verdicts on framework fit

Framework fit means how well the company's filings satisfied the screening and evaluation criteria of the framework you selected — the strength of that match. It is not a recommendation to buy, sell, or hold anything, and not a prediction of returns.

GEMSTONE
Strong match to the framework
GEODE
Partial match — turn it over yourself
SEDIMENT
No match — a turned-over stone
GENERAL-PURPOSE STRATEGY

General Analysis

Ten frameworks each express a published tradition, organized under the lenses. General Analysis is not one of them — it is the general-purpose strategy, for portfolio holdings and one-off company reads when you want the evidence organized before choosing a discipline.

A framework screens a universe of companies. General Analysis evaluates one named company, so there is nothing to screen out — it skips Stage 1 and goes straight to the filings read. Same engine, same filing sections, same citation rules, same honesty about gaps — without a framework's scoring rubric. It belongs to no lens, because it is not a framework.

  • ASSESSMENT Prose grounded in the filings it was given — every figure traces to the 10-K, and the countervailing items get named alongside the strengths.
  • FRAMEWORK SCORES Four dimensions — risk profile, business quality, earnings quality, financial strength — each scored 0–5 on how well the provided filing sections support it. Every claim behind a score must cite the filing it came from; where the filings are silent, the dimension is marked unknown instead of scored on inference. A framework score describes how well the analysis is supported by the cited filings — it is not a rating of the company or a level of conviction in any action.
  • CONFIDENCE A roll-up of the same idea: how well-supported the overall analysis is by the cited filings. Missing sections and unverifiable claims lower it. It is not a rating of the company or a level of conviction in any action.
  • INSUFFICIENT DATA Sections the evaluator wasn't given become named unknowns, not silent guesses — the honesty-about-gaps rule made visible.
  • AI TRANSPARENCY Every card names the model that wrote it and carries the AI and NOT ADVICE marks.
SMPL GEODE TURN IT OVER
SAMPLE, INC
CONFIDENCE High
SCORE 16 / 20

Sample, Inc presents as a mid-sized established operator with a total framework score of 16 — clearing many, but not all, of the conditions for the top tier of this general analysis. Per the 10-K filed February 12, 2026, revenue grew from $3.8 billion in 2023 to $5.1 billion in 2025, and operating cash flow of $810 million exceeds net income of $505 million — evidence of sustained profitability across the full three-year filing record. The most material countervailing item is capital intensity: $760 million of property and equipment purchases in 2025, roughly double the 2023 level. No restatement, going-concern, or auditor-change signal was found in the provided sections.

FRAMEWORK SCORES
Risk Profile 3/5
Business Quality 4/5
Earnings Quality 5/5
Financial Strength 4/5
INSUFFICIENT DATA
10-Q for the most recent interim quarter was not provided; current-period liquidity cannot be confirmed beyond the December 31, 2025 10-K.
Recent 8-K filings (trailing 12 months) were not provided; executive-departure activity and material-event disclosures cannot be assessed.
Segment-level margin detail was not fully provided in the truncated filings, limiting cross-segment earnings-quality verification.
ai transparency · claude-sonnet-4-6 AI NOT ADVICE

Recreation of the app's results card. "Sample, Inc" is a fictional company — illustrative data only.

See a whole verdict, taken apart

The workhorse page: one sample output, annotated part by part.

CLOSED PILOT

Request your beta invite.

RockTurners is in an invite-only pilot. Join the list and we'll email you an invite with access when a spot opens.

EMAIL USED ONLY TO SEND YOUR INVITE · SEE OUR PRIVACY POLICY