Automated README summary
Automatically summarized from the README on 23 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A stocks-only paper-trading experiment where two decision engines, Ferdi and Bodi, each start with $50,000 simulated cash and trade the same five-stock universe under identical data, menus, execution and limits.
How it uses Jev
Ferdi calls TypeSafe /v1/systemone (jev-1.13.0) with captured market evidence (quotes, trend score, ATR, volatility, returns) plus its own portfolio state and the legal action menu. Code sizes positions and enforces limits; the returned choice and conviction gate entries.
Primitives:choice
Technique worth stealing
Give both engines identical captured evidence and legal action menus, then let code size and enforce all limits so only the decision differs.
Try it
Run the TypeScript app with Alpaca paper keys plus TypeSafe and OpenAI keys; see the public scoreboard.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectunclear0.54
- Shows a System One patternnot found in the excerpt0.16
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolnot found in the excerpt0.19
- Top-10 learning shortlist signalnot found in the excerpt0.17
- Is a replica of the modelnot found in the excerpt0.22
- Solves a common problem (0–2)score on a 0–2 scale0.01 / 2
- About JevFound in material0.98
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 23 Oct 2026.