Moderation production rollout 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 production rollout slice of the content moderation pack. Intent: apply the Jev (TypeSafe System One) decision model to content moderation production rollout. Primary search language: Moderation Jev production rollout. 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
Production rollout for content moderation is Operate-pillar work: pin, shadow, canary, abort. It is not a launch-checklist clone of a rival “build with System One” guide — we only talk about this pack’s blast radius (removing content or issuing a ban).
Hub: Use cases. Compare, when the other tool is the real job: moderation APIs.
Production Rollout inputs
Ship the contracted payload, the pinned id, and a documented safe default when the API is unavailable:
{
"post": { "id": "p-209", "text": "…", "locale": "en" },
"policy": { "hate": "…", "spam": "…", "illegal": "…" },
"author": { "strikes": 1, "age_gate": "18+" }
}Decision signals and actions
| Stage | What changes | Moderation rule |
|---|---|---|
| Shadow | Nothing customer-visible | Show Jev next to the current vendor API; take the old action. |
| Canary | One low-blast slice auto-acts | Auto-remove only high-precision spam; keep hate/illegal on humans. |
| Abort | Auto-act off | Policy rewrite → all auto-removes off until gold replay. |
Keep the workflow code you already designed:
def moderate(ans):
cat = ans["category"]
if cat.confidence < FLOOR or cat.choice == "other":
return "review"
if cat.choice == "illegal" or ans["severity"].score >= 2:
return "remove_and_escalate"
if ans["allow"].noul < T_ALLOW:
return "review"
return "keep"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
Safe default if System One errors or confidence is low: do not remove content or issue a ban. 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
Promotion gate = evaluation green on the pinned id + audit traces for the canary. 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
| Slice | Page |
|---|---|
| Graph and primitives | decision workflow |
What may enter state |
input contracts |
| What to gather first | evidence collection |
| Atomic rules | policy checks |
| Act / review / abstain | confidence thresholds |
| Reviewer payload | human handoff |
| What to persist | audit trail |
| How it breaks | failure modes |
| Labeled replay | evaluation |
| Shadow → canary | you are here |
FAQ
Can I ship on jev-latest?
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. Shadow first.
What is the safe default if System One is down? Fail closed on removing content or issuing a ban. Do not guess.
Where is the rest of the Moderation pack? Start with Moderation evaluation and Moderation confidence thresholds. 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.
Sources
Public TypeSafe or adjacent documentation only. No private claims.