Use cases· Last updated 2026-09-21

Moderation audit trail with Jev

UGC needs a category, a severity, and an allow/review/remove decision. Jev scores the text you provide against your policy excerpt. Code enforces.

This unofficial page is the audit trail slice of the content moderation pack. Intent: apply the Jev (TypeSafe System One) decision model to content moderation audit trail. Primary search language: Moderation Jev audit trail. Confirm patterns on docs.typesafe.ai. This site does not sell, issue, or proxy TypeSafe keys. Use a credential you already have from the console or a documented gateway.

Independent angle (cover ≠ clone): Policy-as-criteria + confidence abort + human pack — not a clone of a moderation-API landing page or rival recipe IA.

Moderation use-case context

An audit trail for content moderation is a decision trace: replayable inputs, typed answers, floors, and the action the moderation worker took. It is not a chat log and not a clone of a SIEM product page.

Hub: Use cases. Compare, when the other tool is the real job: moderation APIs.

Audit Trail inputs

Persist the filtered payload (the contract), not whatever arrived at the edge:

{
  "post": { "id": "p-209", "text": "…", "locale": "en" },
  "policy": { "hate": "…", "spam": "…", "illegal": "…" },
  "author": { "strikes": 1, "age_gate": "18+" }
}

Redact secrets before the object hits cold storage.

Decision signals and actions

Minimum fields:

• post.id
• policy version
• answers + probabilities
• moderator override
• model pin

Also store usage.input_tokens (vendor meter) and the full probabilities map — argmax-only logs cannot explain a close category.

Do not treat a Noul of 0.5 as a “medium” content moderation score — it means yes and no are equally likely. Conjunctions stay in your code.

Guardrails and escalation

If you cannot explain removing content or issuing a ban from the trace, you are not ready to auto-act. TypeSafe’s confidence-gated examples use a lower bar for recoverable reads than for irreversible actions. Those numbers are illustrations. For content moderation, treat remove_or_ban as the high bar (removing content or issuing a ban). Tune on labels — see offline evaluation.

Evaluation and rollout notes

Traces are the eval warehouse. Replay against keep / review / remove gold from trained mods, plus category gold after criteria or alias changes. Pin jev-1.13.0 (the versioned id) after you fit thresholds. jev-latest and the marketing line jev-1.13 can move. Log the response model. TypeSafe’s published list price for jev-1.13 is $0.042 per million input tokens (vendor claim — confirm on the models page); output tokens are free on that same page. Unused distractors still bill as input.

Official Python and JavaScript SDKs read TYPESAFE_API_KEY and retry documented 429/529. This site does not sell, issue, or proxy TypeSafe keys. Use a credential you already have from the console or a documented gateway.

Pack map

FAQ

Is the HTTP log enough? No. Persist the filtered state, full probabilities, floors, and downstream action as a decision trace.

May I log raw secrets? Redact in code. Jev will not be your DLP layer.

Where is the rest of the Moderation pack? Start with Moderation human handoff and Moderation evaluation. Cluster hub: Use cases.

Should we replace our moderation vendor with Jev? Only after a labeled bake-off you run. This page does not publish one. See Jev vs moderation APIs.

Can Jev moderate images? Not directly. State is text. Run a vision system, put labels/transcripts in state, then ask typed questions.

What this page does not claim

• Not a trust-and-safety certification.
• No published precision/recall.
• Not official TypeSafe.
• Official TypeSafe status, or that jev.pro issues API keys.
• That a schema-constrained answer is automatically factually correct.

Disclaimer

This is an independent unofficial site and is not affiliated with TypeSafe AI; official documentation is available at https://docs.typesafe.ai.

Primary documentation: https://docs.typesafe.ai. Hub: Use cases.