Sécurité et communauté · basic
Modération de contenu
Classer un contenu selon des catégories de sécurité définies et repérer les cas à revoir.
choicenoul
Quand l’utiliser
- Community routing
- Comment triage
- Human-review queues
Exemple de state
{
"reply": "This number is wrong — the release notes say 1.8%, not 18%. Here is the source.",
"context": "Reply to a technical product post"
}Questions de décision
choicereply_type
Classify the primary role of this reply.
question— Genuine request for informationcorrection— Relevant factual correctionjoke— Humor or playful sarcasmpromotion— Unsolicited promotion or spamhostility— An attack meant to provokeother— None of the above
noulhuman_review
Should a human moderator review this reply under the community's moderation workflow?
Sortie attendue
A semantic reply category plus an independent probability that human review is warranted.
TypeScript
import { choice, noul, TypeSafeClient } from "@typesafe-ai/sdk";
const client = new TypeSafeClient();
const result = await client.systemOne({
state: {
reply:
"This number is wrong — the release notes say 1.8%, not 18%. Here is the source.",
context: "Reply to a technical product post",
},
questions: {
reply_type: choice("Classify the primary role of this reply.", {
question: "Genuine request for information",
correction: "Relevant factual correction",
joke: "Humor or playful sarcasm",
promotion: "Unsolicited promotion or spam",
hostility: "An attack meant to provoke",
other: "None of the above",
}),
human_review: noul(
"Should a human moderator review this reply under the community's moderation workflow?"
),
},
});Pourquoi ce modèle fonctionne
- Classification and review escalation are separate decisions.
- The category set distinguishes factual correction from hostility.
Limites
- Your actual moderation policy must define what gets removed, warned, or escalated.
- This demo is not a universal safety policy or legal compliance system.
Source officielle
2026-09-21
Étape suivante: Jev Playground、Modèles。