Dossiers · 929 published · 917 with a kill line · 8 archetypes · 40 themes

Thesis. Kill line. Catalyst. Per ticker.

Each dossier compresses thirty days of news, four quarters of earnings transcripts, and narrative-cluster classification into one read: thesis, kill line, archetype, conviction, catalyst calendar. Generated by a frontier model, dated, and graded against the line it published.

In brief

FrontierPicks publishes 929 per-ticker equity research dossiers written by a frontier language model and re-read on a rolling cycle — the live book every trading day, the full 929-name corpus inside 8 sessions. 917 of the 929 published dossiers carry the full shape — a dated thesis and the exact level that ends it. The other 12 are listed rather than hidden: 11 are waiting on a first read, and 1 publishes no kill line. The full shape is a thesis, the archetype the name is behaving as, its next dated catalyst, and — the part that matters — the kill line, the exact price or event that would prove the pick wrong. 28 names are on the live book and 243 are under active research; the most-covered themes are AI datacenter infrastructure, Precision biotech & therapeutics, AI enterprise software.

Watch lists

Hot — momentum board → Hot stocks crypto exchange and stablecoin stocks 7 precision biotech stocks 4 AI compute stocks 4 neocloud GPU compute stocks 4 managed care and health-services stocks 5 medtech stocks 4

Conviction mix

Supreme 17 · 2%
High 49 · 5%
Medium 330 · 36%
Low 522 · 56%
None 11 · 1%

Archetype mix

Compounder 128 · 14%
Cyclical recovery 121 · 13%
Theme leader 63 · 7%
Special situation 256 · 28%
Earnings inflection 226 · 25%
Retail squeeze 52 · 6%
Defensive 72 · 8%

Freshness · last analysed

≤ 7 days 740 · 80%
≤ 30 days 189 · 20%

conviction highmediumlownone

929 shown

No dossiers match your filters.

Held

Watchlist

243

Recently exited

Dormant

630

Common questions

What is a FrontierPicks dossier?

A per-ticker research note written by a frontier language model: the current thesis, the archetype the name is trading as, the next dated catalyst, and an explicit kill line — the price level or event that would prove the pick wrong. Every dossier is dated and rewritten as the facts change.

How many stocks does FrontierPicks cover?

929 US tickers have a dossier right now. 917 of the 929 published dossiers carry the full shape — a dated thesis and the exact level that ends it. The other 12 are listed rather than hidden: 11 are waiting on a first read, and 1 publishes no kill line. Coverage is earned rather than fixed: a name gets a dossier when the model has something to say about it beyond the price trend. The 56 names the model holds, has just exited, or that sit in a theme it is currently calling accelerating are re-read every trading day — every one of them was read in the current session. The wider 873-name coverage universe cycles behind them: its median name was last read 3 sessions ago, and no dossier is more than 8 sessions old.

Is AI-generated stock research reliable?

It should be judged the way any research is judged — on whether its stated confidence holds up against outcomes. FrontierPicks is built to make that measurable: every pick publishes a kill line before the outcome is known and is graded mechanically against it, and the resulting calibration record is recomputable from the published data rather than asserted. It is research to evaluate, not advice; no performance claim is made.

How often are the dossiers updated?

On a rolling cycle, not uniformly. The 56 names the model holds, has just exited, or that sit in a theme it is currently calling accelerating are re-read every trading day — every one of them was read in the current session. The wider 873-name coverage universe cycles behind them: its median name was last read 3 sessions ago, and no dossier is more than 8 sessions old. The model re-reads a covered name against fresh price, filing and news data and rewrites the dossier when the facts move; each page shows its own last-updated date rather than a sitewide timestamp, so the cadence is checkable name by name.