jevbooks

← All projects

account-intel-jev-layers

NickKostovny/account-intel-jev-layers

Typed judgments from Jev over site text, job titles, publications, and news.

Automated README summary

Automatically summarized from the README on 6 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

Stage 4 of Invert's account-intelligence pipeline. Uses Jev (TypeSafe) to make typed judgments on site text, job titles, publications, and news, plus an automated source check for site verdicts. For analysts building account briefs.

How it uses Jev

Jev answers typed questions (Choice, Noul, Score) about site status, functions, modality, job families, publication relevance, and news triggers. State is site text with verdict words stripped and roster names scrubbed. Code combines answers into verdicts (KEEP, FLAG, GAP, DROP, CLOSED, REVIEW) and labels.

Primitives:choicescorenoul

Technique worth stealing

Use Jev's typed probabilities to combine multiple atomic questions into a single verdict, with source checks on disagreements.

Try it

Run python3 jev_site_profile.py all, then other jev_* scripts as in README.

View on GitHub

Start using Jev: API key and your first request →

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 material0.84
  • Shows a System One patternnot found in the excerpt0.24
  • Describes handling uncertaintynot found in the excerpt0.07
  • Reports measured numbersnot found in the excerpt0.29
  • Is a runnable toolnot found in the excerpt0.39
  • Top-10 learning shortlist signalnot found in the excerpt0.36
  • Is a replica of the modelnot found in the excerpt0.17
  • Solves a common problem (0–2)score on a 0–2 scale1.12 / 2
  • About JevFound in material0.98
Signals
Jev is core to the project0.84Shows a System One pattern0.24Describes handling uncertainty0.07Reports measured numbers0.29Is a runnable tool0.39Top-10 learning shortlist signal0.36Is a replica of the model0.1700.51Solves a common problem (0–2)1.12 / 2012

no-judgment band (0.40–0.60)

Design patterns
Scorecard0.98Questionnaire0.94Traffic light0.93Grey zone0.93Funnel0.86Check-up0.40Inspection0.39Ghostwriter0.34Viewfinder0.33Question bank0.30Blind review0.2200.51

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 6 Oct 2026.