> Fetch clean Markdown by appending `.md` to any page URL under https://signalwire.com/docs or requesting it with the HTTP header `Accept: text/markdown`. The root index at https://signalwire.com/docs/llms.txt lists the available documentation indexes.

# amazonBedrock

> Connect a call to an Amazon Bedrock AI agent.

[ai]: /docs/server-sdks/reference/typescript/relay/call/ai

Connect the call to an Amazon Bedrock AI agent. Similar to
[`ai()`][ai] but uses Amazon Bedrock as
the LLM backend.

## **Parameters**

**`prompt`** `unknown | undefined`

The prompt configuration for the Bedrock agent.

---

**`SWAIG`** `Record<string, unknown> | undefined`

SWAIG configuration for tool/function definitions.

---

**`aiParams`** `Record<string, unknown> | undefined`

AI parameters for the Bedrock session.

---

**`globalData`** `Record<string, unknown> | undefined`

Data accessible to the AI and SWAIG functions.

---

**`postPrompt`** `Record<string, unknown> | undefined`

Post-prompt configuration.

---

**`postPromptUrl`** `string | undefined`

URL to receive the post-prompt result.

---

## **Returns**

`Promise<Record<string, unknown>>` -- Server response confirming the Bedrock session.

## **Example**

```typescript {13}
import { RelayClient } from '@signalwire/sdk';

const client = new RelayClient({
  project: process.env.SIGNALWIRE_PROJECT_ID!,
  token: process.env.SIGNALWIRE_API_TOKEN!,
  contexts: ['default']
});

client.onCall(async (call) => {
  await call.answer();

  // Start an Amazon Bedrock AI agent
  const result = await call.amazonBedrock({
    prompt: { text: 'You are a helpful assistant.' },
    aiParams: { barge_confidence: 0.02 },
  });
});

await client.run();
```

> Connect a call to an Amazon Bedrock AI agent.