Quickstart

Block a fake API key and tokenize an email in an AI SDK route in under five minutes.

Build an AI SDK route that blocks secrets before they reach a model and tokenizes email, then restores it at egress for your UI.

What you will build

A server route that:

Rejects prompts containing a fake Stripe test key with PolicyViolationError.
Tokenizes customer@example.com in the outbound prompt.
Restores the email in the HTTP response at a trusted egress boundary.

Install

pnpm add @tailrace/core @tailrace/ai-sdk ai @ai-sdk/openai

ai@^5 must be installed alongside @tailrace/ai-sdk.

Create Tailrace

Zero configuration blocks secrets and tokenizes common PII.

import { createTailrace } from "@tailrace/core";
import { withAiSdk } from "@tailrace/ai-sdk";

export const tailrace = withAiSdk(createTailrace());

Wrap the model

Use the wrapped model with any AI SDK API (generateText, streamText, agents).

import { openai } from "@ai-sdk/openai";
import { generateText } from "ai";

const workflowId = crypto.randomUUID();

const model = tailrace.model(openai("gpt-4o"), {
  agent: "demo",
  workflowId,
});

const { text } = await generateText({
  model,
  prompt: userPrompt,
});

Tailrace scans the prompt in transformParams before the provider is called.

Trigger a block

Send a prompt containing a fake test key (never use real secrets in examples):

const prompt = "Use key sk_test_51FakeKeyForTailraceTests000FAKE to call the API.";

Expected: PolicyViolationError - the call aborts and the provider is never contacted.

policy blocked entity "api_key" via rule "entities.api_key"

Catch it in your route and return 422:

import { PolicyViolationError } from "@tailrace/core";

try {
  await generateText({ model, prompt });
} catch (err) {
  if (err instanceof PolicyViolationError) {
    return Response.json(
      { error: { type: "policy_violation", entity: err.decisions[0]?.entity } },
      { status: 422 },
    );
  }
  throw err;
}

Seeing the block is the payoff. The secret never leaves your process.

Tokenize, then restore

Send a prompt with only an email:

const prompt = "Please email customer@example.com about the invoice.";
const { text } = await generateText({ model, prompt });
// text contains <EMAIL_xxxxxxxx> - what the model saw

Restore at egress before returning to the client:

const restored = await tailrace.restore(text, {
  boundary: { kind: "egress", sink: "ui" },
  identity: { agent: "demo" },
  workflowId,
});

return Response.json({ text: restored.output });
// "Please email customer@example.com about the invoice."

Detokenization only runs at egress. Calling restore at a model boundary throws.

Runnable example

From the Tailrace monorepo:

pnpm --filter example-nextjs-ai-sdk dev

Open http://localhost:3000 and try Run A and Run B.

Where next

Protect PII in the AI SDK - tools, streaming, workflow IDs
Boundaries - model, tool, egress mental model
AI SDK reference - wrapModel, options, streaming modes

Quickstart

On this page