Automated README summary
Automatically summarized from the README on 18 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An experimental TypeScript CLI for Salesforce admins: it audits whether manual Setup steps were done, or performs them in the browser, for steps with no Metadata API coverage.
How it uses Jev
In `run`, Jev chooses every click: given the indexed controls that really exist on the current Setup page, it returns the operation and control to use (one request per action). In `audit`, Jev judges whether the Setup Audit Trail record confirms the requested change, returning a calibrated probability used for the exit code.
Primitives:choicescore
Technique worth stealing
Judge the agent's work by Salesforce's own Setup Audit Trail record, not by the agent's word.
Try it
npm install && npm run build; set TYPESAFE_API_KEY and LLM_API_KEY in .env; run `sf-autopilot audit` or `run`.
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-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
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 material0.83
- Shows a System One patternFound in material0.63
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersunclear0.57
- Is a runnable toolFound in material0.71
- Top-10 learning shortlist signalnot found in the excerpt0.30
- Is a replica of the modelnot found in the excerpt0.10
- Solves a common problem (0–2)score on a 0–2 scale0.99 / 2
- About JevFound in material0.97
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 18 Oct 2026.