> ## Documentation Index
> Fetch the complete documentation index at: https://docs.novu.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Connect AI SDK to Slack

> Add @novu/framework/ai-sdk to an existing app, connect Slack, and return generateText from onMessage. Same handler works on Teams, WhatsApp, Telegram, and email.

Connect a [Vercel AI SDK](https://ai-sdk.dev/) agent to Novu Connect. Return `generateText()` from `onMessage`; Novu delivers the reply on Slack. After you add other providers, the same handler serves Teams, WhatsApp, Telegram, and email.

This guide uses **Slack** first and assumes an existing Node.js app. Examples use OpenAI or Anthropic via the AI SDK.

<Note>
  Starting from scratch? See [Scaffold with the CLI](#scaffold-with-the-cli).
</Note>

## Prerequisites

* A [Novu account](https://dashboard.novu.co)
* Node.js 22+
* An existing app (Next.js, Express, Hono, or similar)
* A Slack workspace where you can install apps
* An `OPENAI_API_KEY` or `ANTHROPIC_API_KEY` (or another [AI SDK provider](https://ai-sdk.dev/providers/ai-sdk-providers) key)

## Connect an existing app

<Steps>
  <Step>
    ## Create the agent and connect Slack

    In the [Novu dashboard](https://dashboard.novu.co):

    1. Go to **Agents** → **Create agent**.
    2. Under **Custom code**, pick **AI SDK**.
    3. Set **Agent name** and **Identifier** (your code must use the same identifier).
    4. Select **Slack**, generate a [Slack App Configuration Token](https://api.slack.com/apps), paste it, and finish the install / Allow flow.

    The token is used once to create the Slack app. Novu does not store it. Screenshots: [Create a Slack app](/agents/channels/slack#create-a-slack-app).

    Alternatively run `npx novu connect`, choose **AI SDK** and **Slack**, and skip creating a starter project when prompted.
  </Step>

  <Step>
    ## Install packages

    <Tabs>
      <Tab title="OpenAI">
        ```bash theme={null}
        npm install @novu/framework ai @ai-sdk/openai
        ```
      </Tab>

      <Tab title="Claude">
        ```bash theme={null}
        npm install @novu/framework ai @ai-sdk/anthropic
        ```
      </Tab>
    </Tabs>

    Add to `.env.local` (or your app env file):

    ```bash theme={null}
    NOVU_SECRET_KEY=your-novu-secret-key
    OPENAI_API_KEY=sk-...   # or ANTHROPIC_API_KEY
    ```

    Copy `NOVU_SECRET_KEY` from **API Keys** in the dashboard.
  </Step>

  <Step>
    ## Add the handler

    Create `app/novu/agents/<your-identifier>.ts` (or the equivalent path). Match `agent('...')` to the dashboard **Identifier**.

    <Tabs>
      <Tab title="OpenAI">
        ```typescript theme={null}
        import { agent, toModelMessages } from '@novu/framework/ai-sdk';
        import { openai } from '@ai-sdk/openai';
        import { generateText } from 'ai';

        export const supportBot = agent('support-bot', {
          onMessage: async (_message, ctx) =>
            generateText({
              model: openai('gpt-4o'),
              instructions: 'You are a helpful support agent. Keep answers short.',
              messages: toModelMessages(ctx.history),
            }),
        });
        ```
      </Tab>

      <Tab title="Claude">
        ```typescript theme={null}
        import { agent, toModelMessages } from '@novu/framework/ai-sdk';
        import { anthropic } from '@ai-sdk/anthropic';
        import { generateText } from 'ai';

        export const supportBot = agent('support-bot', {
          onMessage: async (_message, ctx) =>
            generateText({
              model: anthropic('claude-sonnet-4-20250514'),
              instructions: 'You are a helpful support agent. Keep answers short.',
              messages: toModelMessages(ctx.history),
            }),
        });
        ```
      </Tab>
    </Tabs>

    Export it from your agents index:

    ```typescript theme={null}
    export { supportBot } from './support-bot';
    ```

    `toModelMessages(ctx.history)` already includes the current inbound message. Returning `generateText(...)` delivers the reply. Do not call `ctx.reply()` on this path.
  </Step>

  <Step>
    ## Add the bridge route

    For Next.js, create `app/api/novu/route.ts`:

    ```typescript theme={null}
    import { serve } from '@novu/framework/next';
    import { supportBot } from '../../novu/agents';

    export const { GET, POST, OPTIONS } = serve({
      agents: [supportBot],
    });
    ```

    For Express, Hono, and other servers, see [Connecting your app](/agents/custom-code-agent/connecting-your-app).
  </Step>

  <Step>
    ## Run locally and message Slack

    ```bash theme={null}
    npx novu dev --port 4000
    ```

    Or `npm run dev:novu` if that script exists. Keep the process running.

    DM or @mention the bot in Slack. The reply should come from your model in the same thread.

    If nothing comes back:

    * Confirm the tunnel process is still running.
    * Confirm the agent identifier in code matches the dashboard.
    * Confirm your model API key is set.
    * Confirm Slack install completed and you are messaging the correct bot.
  </Step>
</Steps>

## Tool approval

Gate a tool so the turn pauses for Approve / Deny in Slack:

```typescript theme={null}
import { agent, toModelMessages } from '@novu/framework/ai-sdk';
import { openai } from '@ai-sdk/openai';
import { generateText, tool } from 'ai';
import { z } from 'zod';

export const supportBot = agent('support-bot', {
  onMessage: async (_message, ctx) =>
    generateText({
      model: openai('gpt-4o'),
      messages: toModelMessages(ctx.history),
      tools: {
        issueRefund: tool({
          inputSchema: z.object({ orderId: z.string() }),
          needsApproval: true,
          execute: async ({ orderId }) => refund(orderId),
        }),
      },
    }),
});
```

See [Tool approval](/agents/custom-code-agent/building-blocks/tool-approval) and the [AI SDK reference](/agents/custom-code-agent/frameworks/ai-sdk#automatic-tool-approval).

## Scaffold with the CLI

If you do not have an app yet:

```bash theme={null}
npx novu connect
```

Choose **AI SDK**, name the agent, authenticate the model, choose **Slack**, and accept the starter project. Then run `npm run dev:novu`.

For an existing codebase, use [Connect an existing app](#connect-an-existing-app) instead.

## FAQ

<AccordionGroup>
  <Accordion title="Which channels work with an AI SDK agent?">
    Slack, Microsoft Teams, WhatsApp, Telegram, and email. One handler covers all of them after you link providers. See [Channels overview](/agents/channels/overview).
  </Accordion>

  <Accordion title="Does Novu run my AI SDK code?">
    No. Your app serves the bridge endpoint. Novu forwards the inbound event and conversation context, then delivers whatever the handler returns.
  </Accordion>

  <Accordion title="How do I pass conversation history to the model?">
    Use `toModelMessages(ctx.history)`. Do not append the inbound `message` again. The current message is already included.
  </Accordion>

  <Accordion title="Where is the adapter API documented?">
    [AI SDK reference](/agents/custom-code-agent/frameworks/ai-sdk): return types, tools, MCP, streaming edits, and `onError`.
  </Accordion>
</AccordionGroup>

## Set this up with an AI assistant

<Prompt description="Connect my Vercel AI SDK agent to Slack with Novu" icon="plug" actions={["copy", "cursor"]}>
  # Connect a Vercel AI SDK agent to Slack with Novu Connect

  Follow [https://docs.novu.co/agents/get-started/ai-sdk](https://docs.novu.co/agents/get-started/ai-sdk)

  ## Goal

  Add Novu bridge + AI SDK handler to this repo and connect Slack. Prefer the existing project over scaffolding a new one.

  ## Rules

  ALWAYS:

  * Match `agent('id')` to the Novu dashboard agent Identifier
  * Use `toModelMessages(ctx.history)` for conversation context
  * Keep handlers channel-agnostic
  * Follow the project's package manager and TypeScript conventions

  NEVER:

  * Hardcode API keys
  * Call `ctx.reply()` when returning `generateText()` (Novu delivers the result)
</Prompt>

## Next steps

<Columns cols={2}>
  <Card icon="sparkles" href="/agents/custom-code-agent/frameworks/ai-sdk" title="AI SDK reference">
    Adapter API: tools, approval, MCP, and onError.
  </Card>

  <Card icon="hash" href="/agents/channels/slack" title="Slack">
    Slack capabilities and setup links.
  </Card>

  <Card icon="rocket" href="/agents/custom-code-agent/going-to-production" title="Going to production">
    Deploy the bridge and disable local tunneling.
  </Card>

  <Card icon="link" href="/agents/get-started/langchain" title="Connect LangChain">
    Same flow with @novu/framework/langchain.
  </Card>
</Columns>