Safety Filter

Moderation card with a rose shield icon, category label, severity pill, and the reason the output was blocked.

Harassmenthigh

Response blocked for containing targeted insults.

New here? Read the installation guide.

Import & use
import { Ai30 } from "@/components/beste/piece/ai30";

<Ai30
  category="Harassment"
  reason="Response blocked for containing targeted insults."
  severity="high"
/>

More AI pieces

View all AI
Guardrailsactive
PII redactionToxicityPrompt injection

Guardrail Badge

Safety guardrail card with an emerald shield, active status pill, and a row of enabled policy tags.

"where is my order?"

order_status
87%
shipping_eta
9%
refund_request
4%

Intent Classifier

Intent ranking panel with the raw user input quoted above and a list of candidate labels with confidence bars.

Research Copilot4 tools

Searches papers and drafts literature reviews on request.

Assistant Card

Catalog card for a configured assistant with a tone-filled bot tile, name, short description, and the tool count.

Weekly summary
  • Onboarding ships to GA on Tuesday
  • Pricing experiment lifts conversion by 14%
  • Two critical bugs filed, one already patched
Synthesized from 3 documents

AI Summary

Summary card with a violet sparkle header, bullet list of key points, and a source attribution below.

ts
const slug = (s: string) =>
  s.toLowerCase().replace(/\s+/g, '-');

Generated Code

AI code output card with a language tag, copy and regenerate actions, and a monospace block below.

System prompt

You are a concise copywriter. Reply in 2 sentences max and avoid em dashes.

System Prompt

Dashed-border card with a violet scroll icon, uppercase label, and an edit button for the system instructions.