Automated README summary
Automatically summarized from the README on 3 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Go web app for small D2C brands facing payment disputes. It ingests CSV exports of disputes, orders, shipments, messages and refunds, then recommends fight, refund or request one document, and drafts a verified response for the merchant.
How it uses Jev
Jev answers six yes/no questions about each customer conversation with calibrated probabilities: return offered, return refused, fault admitted, refund promised, receipt confirmed, AI instruction attempt. A Go truth table (yes ≥0.7, no ≤0.3) plus records yields a second opinion shown beside the agent's verdict; disagreement is flagged for a person. Jev never picks the verdict.
Primitives:choice
Technique worth stealing
Judgments from Jev, decisions in code: a calibrated model supplies probabilities, a deterministic truth table turns them into a verdict.
Try it
go run ./cmd/chargeback (replayed sample, no key); set LIVE_AI=true and TYPESAFE_API_KEY for live Jev.
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 excerpt0.08
- Shows a System One patternunclear0.47
- Describes handling uncertaintyunclear0.40
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.80
- Top-10 learning shortlist signalnot found in the excerpt0.17
- Is a replica of the modelnot found in the excerpt0.08
- Solves a common problem (0–2)score on a 0–2 scale1.02 / 2
- About JevFound in material0.88
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 Nov 2026.