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.

Apr 9, 2026

General

PromptBeginner5 minmarkdown

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

rule types

Apr 9, 2026

Find agent skills by outcome

mc

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

- Sensitive info detection runs **locally in WASM** — no user data is sent to external services. It is only available in route handlers

**Vercel AI SDK**: Arcjet works alongside the Vercel AI SDK. Call `protect()` before `streamText()` / `generateText()`. If denied

**Multiple models / providers**: Use the same Arcjet instance regardless of which AI provider you use. Arcjet operates at the HTTP layer

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

- `list-requests` — confirm decisions are being recorded

If the user wants a full security review

Start all rules in `DRY_RUN` mode first. Once verified

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

console.warn(Arcjet error:

sensitiveInfoValue: userMessage

detectPromptInjectionMessage: userMessage

return Response.json({ error: Forbidden }

const decision = await aj.protect(req

requested: 1

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

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

Use `tokenBucket()` / `token_bucket()` for AI endpoints — the `requested` parameter can be set proportional to actual model token usage

- JS: `sensitiveInfo({ deny: [EMAIL

Detects jailbreaks

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

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

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

- Sensitive info detection runs locally in WASM — no user data is sent to external services. It is only available in route handlers

Vercel AI SDK: Arcjet works alongside the Vercel AI SDK. Call `protect()` before `streamText()` / `generateText()`. If denied

Multiple models / providers: Use the same Arcjet instance regardless of which AI provider you use. Arcjet operates at the HTTP layer

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

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