Vercel AI SDK

Build Vercel AI tools for one authenticated Authlane user and stream a model response.

Load a user-scoped ToolSet and pass it directly to the Vercel AI SDK in your server runtime.

Prerequisites

pnpm add @authlane/sdk @authlane/ai ai zod

Derive userId from your trusted SaaS session before calling this function.

Implement the workflow

import { vercelAI } from '@authlane/ai/vercel';
import { Authlane } from '@authlane/sdk';
import type { ModelMessage } from 'ai';
import { createTextStreamResponse, streamText, toTextStream } from 'ai';

const authlane = new Authlane({
  apiKey: process.env.AUTHLANE_API_KEY!,
});

export async function answer(userId: string, messages: ModelMessage[]) {
  const user = authlane.user(userId);
  const { data: tools, error } = await user.tools.list({
    adapter: vercelAI({ approval: 'write-and-destructive' }),
  });
  if (error) {
    return Response.json({ error }, { status: error.statusCode ?? 400 });
  }

  const result = streamText({ model: 'openai/gpt-5-mini', messages, tools });
  return createTextStreamResponse({ stream: toTextStream({ stream: result.stream }) });
}

Expected result

tools is a Vercel AI ToolSet containing only effective connected tools for this user. Read tools run normally. Vercel AI receives needsApproval: true for write and destructive tools.

Handle errors

Handle the SDK tuple before calling streamText. Generated tools return fixed redacted execution errors to the model.

Security boundary

The capability read issues no credentials. Each invoked callback obtains a fresh access-only lease and calls the provider from this process; provider traffic never passes through Authlane.

Next step

Apply production hardening to the surrounding route.