Automated README summary
Automatically summarized from the README on 21 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A native Cordis plugin for DeepSeek Harness that implements AWS's AI-DLC methodology (Inception, Construction, Operations) with human gates, per-commit audit artifacts, and an automated decision layer for gate questions.
How it uses Jev
The decision model is consulted first on gate decisions; if its confidence clears the risk-band bar (C0/C1 0.60, C2 0.85, C3 0.95), the verdict is applied as AUTO-APPROVED/AUTO-REJECTED during a veto window, otherwise escalated to the human with the recommendation attached. Six classes are never automated.
Primitives:choicescore
Technique worth stealing
Triage-first: consult the model before the human, apply only above a risk-band confidence floor, and always surface the applied verdict with a veto window.
Try it
dsh plugin --profile desktop add D:\path\to\dsh-aidlc, then restart the profile.
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 projectnot found in the excerpt0.29
- Shows a System One patternunclear0.51
- Describes handling uncertaintynot found in the excerpt0.24
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.95
- Top-10 learning shortlist signalnot found in the excerpt0.17
- Is a replica of the modelunclear0.41
- Solves a common problem (0–2)score on a 0–2 scale1.07 / 2
- About JevFound in material0.84
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 21 Oct 2026.