STRATEGY LAB

Thirteen frameworks built in. Yours is number fourteen.

Fork any built-in strategy into your own copy, edit its screening criteria, and run it through the same EDGAR-grounded pipeline. Your filters are your own editorial choices — applied impersonally to the whole universe, never to you.

THE DERIVE FLOW

Fork it. The original stays intact.

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 from scratch — an empty screen against the same universe. Either way the built-ins are untouched: a starting point, not a ceiling.

THE WORKBENCH

Iterate like a regression suite

Shown: a derived strategy 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 strategies get the same EDGAR grounding, the same citation enforcement, the same honest unknowns, and the same Gemstone / Geode / Sediment vocabulary as the thirteen built-ins.

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

The screen is yours to direct.

Fork a built-in or start from an empty screen — same universe, same discipline.

Request invite

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 · NO TRACKING COOKIES