Find agent skills by outcome

Vercel AI SDK: Arcjet works alongside the Vercel AI SDK. Call protect() before streamText() / genera...

return a plain error response instead of calling the AI SDK.

- Starting a stream before calling protect() — if the request is denied mid-stream

the client gets a broken response. Always call protect() first and return an error before opening the stream.

Streaming responses: Call protect() before starting the stream. If denied

return the error before opening the stream — don't start streaming and then abort.

Multiple models / providers: Use the same Arcjet instance regardless of which AI provider you use. A...

independent of the model provider.

- list-requests — confirm decisions are being recorded

filter by conclusion to see blocks

Start all rules in DRY_RUN mode first. Once verified

promote to LIVE.

Adapt the response format to your framework (e.g.

res.status(429).json(...) for Express).

console.warn(Arcjet error:

decision.reason.message);

return Response.json({ error: Forbidden }

{ status: 403 });

detectPromptInjectionMessage: userMessage

// injection detection

requested: 1

// tokens to deduct for rate limiting

const decision = await aj.protect(req

{

sensitiveInfoValue: userMessage

// PII scanning

Pass the requested parameter at protect() time to deduct tokens proportional to model cost. For exam...

deduct 1 token per message

Set characteristics to track per-user: [userId] if authenticated

defaults to IP-based.

Use tokenBucket() / token_bucket() for AI endpoints — the requested parameter can be set proportiona...

directly linking rate limiting to cost. It also allows short bursts while enforcing an average rate

Arcjet rules run before the request reaches your AI model — blocking prompt injection

PII leakage

Detects jailbreaks

role-play escapes

Check for an existing shared Arcjet client (see /arcjet:protect-route for full setup). If none exist...

set one up first with shield() as the base rule. The user will need to register for an Arcjet account at https://app.arcjet.com then use the ARCJET_KEY in their environment variables.

Read https://docs.arcjet.com/llms.txt for comprehensive SDK documentation covering all frameworks

rule types

Secure AI/LLM endpoints with layered protection: prompt injection detection

PII blocking

description: Protect AI chat and completion endpoints from abuse — detect prompt injection and jailb...

block PII and sensitive info from leaking in responses

Visual symbol table — per ELV system (CCTV

FAS

Add AI protection