Automated README summary
Automatically summarized from the README on 3 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
InboxPilot is a Python tool for founders overwhelmed by email. It reads Gmail (read-only), decides urgency, category, and reply need, and only acts when confident; otherwise it produces a morning digest with suggested actions.
How it uses Jev
For each email, one Jev call evaluates three parallel questions: urgency (yes/no + probability), category (pick one of 5), and needs_reply (yes/no + probability). The returned probabilities gate auto-labeling (category confidence ≥ 0.85 and decisive urgency) and auto-archiving (noise only, confidence ≥ 0.95 and decisive urgency); uncertain emails go to the digest.
Primitives:choicescore
Technique worth stealing
Escalate ambiguous cases to a human digest instead of guessing, using calibrated confidence thresholds.
Try it
./inboxpilot demo
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 material0.87
- Shows a System One patternFound in material0.80
- Describes handling uncertaintyFound in material0.77
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolunclear0.56
- Top-10 learning shortlist signalnot found in the excerpt0.26
- Is a replica of the modelnot found in the excerpt0.07
- Solves a common problem (0–2)score on a 0–2 scale1.13 / 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 3 Oct 2026.