Automated README summary
Automatically summarized from the README on 25 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
jeff-act lets users run allowed actions from a YAML catalog by describing them in natural language, and turns a database schema into safe parameterized queries. It is for developers who want typed, code-executed automation without model-generated text.
How it uses Jev
Jev makes choice decisions: first over all actions plus none, then one choice per argument over candidates code found plus not stated. For free arguments, a local model proposes values and Jev checks each with a yes/no. In JevQuery, Jev picks table, filter column, operator, value, order, limit, and columns. Results drive a ranked fallback ladder and parameterized SQL.
Primitives:choicescore
Technique worth stealing
Use Jev as a closed-set picker over code-found candidates, never as a text generator, so only allowlisted actions and bound parameters run.
Try it
go install github.com/saembit/jeff-act/cmd/jeff-act@latest; export TYPESAFE_API_KEY=...; jeff-act act examples/home.yaml "turn the porch light off"
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 projectFound in material0.96
- Shows a System One patternFound in material0.84
- Describes handling uncertaintynot found in the excerpt0.16
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.93
- Top-10 learning shortlist signalFound in material0.63
- Is a replica of the modelnot found in the excerpt0.07
- Solves a common problem (0–2)score on a 0–2 scale1.45 / 2
- About JevFound in material0.99
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 25 Oct 2026.