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
Mailroom keeps a Gmail mailbox sorted: deterministic rules label, archive, trash expired codes, and mark old promotions read; leftover Primary-tab mail goes to Jev. For people who want a readable, undoable filing policy.
How it uses Jev
Jev answers five narrow typed questions per email over metadata (headers, labels, snippets), never bodies. Code finds candidates and applies thresholds; Jev's probabilities pick category, window, intent, and graded relevance, shown in the UI. It also grades receipts and decides sender-by-sender.
Primitives:choicescorenoul
Technique worth stealing
Code owns the workflow and thresholds; the model answers atomic typed questions over metadata, with every probability shown instead of a hidden verdict.
Try it
pnpm install && pnpm db:push, fill .env.local, pnpm dev, sign in, add a TypeSafe key, press Preview.
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 projectnot found in the excerpt0.38
- Shows a System One patternFound in material0.87
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.67
- Top-10 learning shortlist signalnot found in the excerpt0.29
- Is a replica of the modelnot found in the excerpt0.02
- Solves a common problem (0–2)score on a 0–2 scale1.14 / 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 23 Oct 2026.