ユースケース
Each page is a real request shape you can run in the playground.
Support ticket routing
Classify urgency, team and tone on every inbound ticket before it hits a queue.
Refund policy check
Ask whether a refund was requested and whether the written policy supports it.
Tool-call risk gate
Score a proposed agent tool call before it touches production data.
Model routing
Pick a cheap or expensive model from the task, not from a hardcoded list.
Content moderation
Decide allow, review or remove, and flag real threats separately.
Lead scoring
Score fit and buying stage from a pricing-page form in one request.
Email and lead triage
Sort inbound email into billing, support or sales and mark what is due today.
Résumé screening
Check must-haves and score overall fit without inventing experience.
Code review risk
Flag diffs that should not merge without a security pass.
Context compaction
Decide which facts still matter when an agent conversation is compressed.
Ad and landing teardown
Name the hook, check the CTA and score the ad for a developer audience.
LLM prompt guardrail
Detect jailbreaks and choose answer, refuse or escalate before the model replies.