docsearch/packages/website/docs/agent-studio/migrate-to-agent-studio.mdx

---
title: Migrate Ask AI to Agent Studio
description: Move an existing Ask AI assistant into Agent Studio and point DocSearch v5 at the new agent.
---

import TabItem from '@theme/TabItem';
import Tabs from '@theme/Tabs';

Ask AI is now part of [Agent Studio](https://www.algolia.com/doc/guides/algolia-ai/agent-studio). Migrate your existing Ask AI assistant, publish the new agent, then point DocSearch at the agent ID.

DocSearch v5 uses Agent Studio as its only AI backend. There's no `agentStudio` flag.

If you're still on DocSearch v4, follow the [v4 migration guide](/docs/v4/v4/migrating-askai-to-agent-studio). To upgrade packages at the same time, see [Migrate from DocSearch v4](/docs/migrating-from-v4).

## Migrate your assistant

### 1. Start the migration in the dashboard

1. Sign in to the [Algolia dashboard](https://dashboard.algolia.com/users/sign_in).
2. Open [Ask AI](https://dashboard.algolia.com/ask-ai).
3. Select your assistant and click **Migrate to Agent Studio**.

The wizard creates a draft Agent Studio agent from your assistant configuration, including the prompt, model, indices, and related settings. After migration, the assistant and agent are independent and don't stay in sync.

### 2. Review and publish the agent

1. Open [Agents](https://dashboard.algolia.com/generativeAi/agent-studio/agents) in Agent Studio.
2. Review the migrated agent.
3. Publish the agent when you're ready to go live.

Copy the **agent ID**. DocSearch calls this value `agentId` in its public API.

### 3. Update your integration

Choose the path that matches how you embed Ask AI today:

- [DocSearch v5](#update-docsearch-v5)
- [Custom Ask AI API](#custom-ask-ai-api-integrations)

Your existing Ask AI assistant keeps serving traffic until Ask AI is fully retired. Switch your client to the Agent Studio agent when you're ready.

## Update DocSearch v5

Pass the Agent Studio **agent ID** as `askAi.agentId`, or as the `askAi` string shorthand. Rename any `assistantId` field to `agentId`.

<Tabs groupId="language" aria-label="Programming language">
  <TabItem value="react" label="React">

Use `DocSearchAI`. Keyword-only `DocSearch` doesn't accept `askAi`.

```tsx title="Search.tsx"
import { DocSearchAI } from '@docsearch/react';
import '@docsearch/css';

export function Search() {
  return (
    <DocSearchAI
      appId="YOUR_APPLICATION_ID"
      apiKey="YOUR_SEARCH_API_KEY"
      indices={['YOUR_DOCSEARCH_INDEX']}
      askAi={{
        agentId: 'YOUR_AGENT_ID',
      }}
    />
  );
}
```

The string shorthand remains supported:

```tsx title="Search.tsx"
<DocSearchAI
  appId="YOUR_APPLICATION_ID"
  apiKey="YOUR_SEARCH_API_KEY"
  indices={['YOUR_DOCSEARCH_INDEX']}
  askAi="YOUR_AGENT_ID"
/>
```

  </TabItem>
  <TabItem value="js" label="JavaScript">

Keep the root `@docsearch/js` import. It renders the AI-capable component:

```js title="load-docsearch.js"
import docsearch from '@docsearch/js';
import '@docsearch/css';

docsearch({
  container: '#docsearch',
  appId: 'YOUR_APPLICATION_ID',
  apiKey: 'YOUR_SEARCH_API_KEY',
  indices: ['YOUR_DOCSEARCH_INDEX'],
  askAi: {
    agentId: 'YOUR_AGENT_ID',
  },
});
```

  </TabItem>
</Tabs>

### Update `searchParameters`

Agent Studio search parameters are keyed by index name. Move any flat Ask AI `searchParameters` under the index:

```diff title="app.js"
 askAi: {
-  assistantId: 'YOUR_ASSISTANT_ID',
+  agentId: 'YOUR_AGENT_ID',
   searchParameters: {
-    filters: 'language:en',
-    attributesToRetrieve: ['title', 'content', 'url'],
+    docs: {
+      filters: 'language:en',
+      attributesToRetrieve: ['title', 'content', 'url'],
+    },
   },
 }
```

Supported keys are `filters`, `attributesToRetrieve`, `restrictSearchableAttributes`, and `distinct`. Don't put `facetFilters` in this object. Put fixed facet conditions in `filters`. For per-request index selection, see [dynamic indices](/docs/agent-studio/dynamic-indices).

### Docusaurus adapter

The adapter requires `themeConfig.docsearch.askAi` as an object with `agentId`. It rejects the string shorthand and the removed `agentStudio` property. See the [Docusaurus adapter guide](/docs/packages/docusaurus-adapter/getting-started).

## Custom Ask AI API integrations

If you call the Ask AI HTTP API yourself instead of using DocSearch, configure your client for Agent Studio instead of `https://askai.algolia.com`.

Don't build new integrations against the Ask AI chat API. Use the Agent Studio APIs:

- [Integrate Agent Studio](https://www.algolia.com/doc/guides/algolia-ai/agent-studio/how-to/integration)
- [Agent Studio API](https://www.algolia.com/doc/rest-api/agent-studio)
- Completions endpoint example:  
  `https://{APPLICATION_ID}.algolia.net/agent-studio/1/agents/{AGENT_ID}/completions`

Authenticate with your application ID and a search-only API key. Prefer the DocSearch configuration above when you embed DocSearch—the SDK wires the Agent Studio transport for you.

## Next steps

After the agent ID is live in DocSearch:

- [Get started with Agent Studio](/docs/agent-studio/getting-started)
- [Dynamic indices](/docs/agent-studio/dynamic-indices)
- [Tools](/docs/agent-studio/tools)
- [Memory](/docs/agent-studio/memory)
- [Prompt suggestions](/docs/agent-studio/prompt-suggestions)
- [Feedback](/docs/agent-studio/feedback)