STRATEGY LAB

Ten frameworks built in. Yours is number eleven.

Fork any built-in framework into your own copy, describe a screen in plain language, or paste a methodology you wrote elsewhere — then edit its screening criteria and run it through the same EDGAR-grounded pipeline. Your filters are your own editorial choices, applied uniformly across the whole universe of companies.

THE DERIVE FLOW

Fork it. The original stays intact.

Forking copies a built-in framework into your own editable version — you can adjust its screening criteria without changing the original.

BUILT-IN · READ-ONLY
Deep Value (Net-Net)
criteria v3.3 · frozen
— DERIVE →
YOUR COPY · EDITABLE
Net-Net, Tighter Discount
your criteria · your cadence
— RUN →
SAME PIPELINE
Stage 1 → Stage 2 → verdict
cited · gaps flagged

Or start another way. Describe the companies you look for in plain language and the Lab composes the filters, the scoring rubric and the filing list, ready to review. Paste a methodology document you wrote elsewhere and the importer maps it onto the catalog, showing what it kept and what it left out. Or begin with an empty screen against the same universe. Every path ends in a readiness checklist that says what will run before a scan spends anything. Either way the built-ins are untouched: a starting point, not a ceiling.

THE WORKBENCH

Iterate like a regression suite

Shown: a derived framework with generic values. Built-in prompt bodies and complete criteria sets are never displayed on this site.

Sample Screen
sec_edgar_two_stage · claude-sonnet-4-6

Iterate on this strategy: set up a test basket, pre-screen the universe to find candidates (Stage 1), then deep dive the ones worth a closer look (Stage 2). Results land below.

1
Pre-screen the universe Stage 1 · free, no AI cost

Filter the full universe down to securities worth a deeper look. Runs against the warm XBRL cache — no SEC fetches.

Passers are ranked and the top 20 advance to the deep dive — adjust with Edit screen.

Show near-misses 25 View history Warm cache now
Edit screen Run pre-screen
2
Deep dive Stage 2 · uses AI credits

Dry-run the full pipeline on your test basket or the pre-screen's advancers: reads EDGAR filings on each candidate to turn over the rocks that look valuable.

Run against Test basket (0) ▾
DEEP DIVE WITH MODEL
(strategy default) ▾

Engine choice affects speed and run cost, not the research methodology or what a verdict means.

Edit prompt Run deep dive
3
Test basket

Tickers you expect the strategy to pass or reject — your regression suite.

No test tickers yet — Add ticker to start the basket.

Add ticker Save basket
Pre-screen (Stage 1) Deep dive (Stage 2) Historical replay Fitness History
No runs yet
Run a pre-screen or deep dive above — results appear here.
AI-generated research — not investment advice.
WHAT YOU CAN EDIT

Your criteria, the whole universe

Stage 1 filter criteria — thresholds, metrics from the filter catalog — plus scan cadence and universe scope. Every filter screens companies on your criteria; nothing about the screen refers to you.

Tighten the net-net discount
Raise the ROIC floor
Require insider buying on top of a value screen
SAME PIPELINE, SAME DISCIPLINE

The rigor isn't a built-in-only feature

Derived frameworks get the same EDGAR grounding, the same citation enforcement, the same honest unknowns, and the same Gemstone / Geode / Sediment vocabulary as the ten built-in frameworks.

COST TRANSPARENCY
Every scan shows its estimated cost before it runs.
est. 25 candidates · $0.42

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