ai/docs/07-reference/01-ai-sdk-core/15-agent.mdx

AI SDK by Vercel - The AI Toolkit for TypeScript and JavaScript

---
title: Agent (Interface)
description: API Reference for the Agent interface.
---

# `Agent` (interface)

The `Agent` interface defines a contract for agents that can generate or stream AI-generated responses in response to prompts. Agents may encapsulate advanced logic such as tool usage, multi-step workflows, or prompt handling, enabling both simple and autonomous AI agents.

Implementations of the `Agent` interface—such as `ToolLoopAgent`—fulfill the same contract and integrate seamlessly with all SDK APIs and utilities that expect an agent. This design allows users to supply custom agent classes or wrappers for third-party chains, while maximizing compatibility with AI SDK features.

## Interface Definition

```ts
import { ModelMessage } from '@ai-sdk/provider-utils';
import { ToolSet } from '../generate-text/tool-set';
import { Output } from '../generate-text/output';
import { GenerateTextResult } from '../generate-text/generate-text-result';
import { StreamTextResult } from '../generate-text/stream-text-result';

export type AgentCallParameters<CALL_OPTIONS, TOOLS extends ToolSet = {}> = ([
  CALL_OPTIONS,
] extends [never]
  ? { options?: never }
  : { options: CALL_OPTIONS }) &
  (
    | {
        /**
         * A prompt. It can be either a text prompt or a list of messages.
         *
         * You can either use `prompt` or `messages` but not both.
         */
        prompt: string | Array<ModelMessage>;

        /**
         * A list of messages.
         *
         * You can either use `prompt` or `messages` but not both.
         */
        messages?: never;
      }
    | {
        /**
         * A list of messages.
         *
         * You can either use `prompt` or `messages` but not both.
         */
        messages: Array<ModelMessage>;

        /**
         * A prompt. It can be either a text prompt or a list of messages.
         *
         * You can either use `prompt` or `messages` but not both.
         */
        prompt?: never;
      }
  ) & {
    /**
     * Abort signal.
     */
    abortSignal?: AbortSignal;
    /**
     * Timeout in milliseconds. Can be specified as a number or as an object with a totalMs property.
     * The call will be aborted if it takes longer than the specified timeout.
     * Can be used alongside abortSignal.
     */
    timeout?: number | { totalMs?: number };
    /**
     * Callback that is called when each step (LLM call) is finished, including intermediate steps.
     */
    onStepFinish?: ToolLoopAgentOnStepFinishCallback<TOOLS>;
  };

/**
 * An Agent receives a prompt (text or messages) and generates or streams an output
 * that consists of steps, tool calls, data parts, etc.
 *
 * You can implement your own Agent by implementing the `Agent` interface,
 * or use the `ToolLoopAgent` class.
 */
export interface Agent<
  CALL_OPTIONS = never,
  TOOLS extends ToolSet = {},
  OUTPUT extends Output = never,
> {
  /**
   * The specification version of the agent interface. This will enable
   * us to evolve the agent interface and retain backwards compatibility.
   */
  readonly version: 'agent-v1';

  /**
   * The id of the agent.
   */
  readonly id: string | undefined;

  /**
   * The tools that the agent can use.
   */
  readonly tools: TOOLS;

  /**
   * Generates an output from the agent (non-streaming).
   */
  generate(
    options: AgentCallParameters<CALL_OPTIONS, TOOLS>,
  ): PromiseLike<GenerateTextResult<TOOLS, OUTPUT>>;

  /**
   * Streams an output from the agent (streaming).
   */
  stream(
    options: AgentStreamParameters<CALL_OPTIONS, TOOLS>,
  ): PromiseLike<StreamTextResult<TOOLS, OUTPUT>>;
}
```

## Core Properties & Methods

| Name         | Type                                             | Description                                                         |
| ------------ | ------------------------------------------------ | ------------------------------------------------------------------- |
| `version`    | `'agent-v1'`                                     | Interface version for compatibility.                                |
| `id`         | `string \| undefined`                            | Optional agent identifier.                                          |
| `tools`      | `ToolSet`                                        | The set of tools available to this agent.                           |
| `generate()` | `PromiseLike<GenerateTextResult<TOOLS, OUTPUT>>` | Generates full, non-streaming output for a text prompt or messages. |
| `stream()`   | `PromiseLike<StreamTextResult<TOOLS, OUTPUT>>`   | Streams output (chunks or steps) for a text prompt or messages.     |

## Generic Parameters

| Parameter      | Default | Description                                                                |
| -------------- | ------- | -------------------------------------------------------------------------- |
| `CALL_OPTIONS` | `never` | Optional type for additional call options that can be passed to the agent. |
| `TOOLS`        | `{}`    | The type of the tool set available to this agent.                          |
| `OUTPUT`       | `never` | The type of additional output data that the agent can produce.             |

## Method Parameters

Both `generate()` and `stream()` accept an `AgentCallParameters<CALL_OPTIONS, TOOLS>` object with:

- `prompt` (optional): A string prompt or array of `ModelMessage` objects
- `messages` (optional): An array of `ModelMessage` objects (mutually exclusive with `prompt`)
- `options` (optional): Additional call options when `CALL_OPTIONS` is not `never`
- `abortSignal` (optional): An `AbortSignal` to cancel the operation
- `timeout` (optional): A timeout in milliseconds. Can be specified as a number or as an object with a `totalMs` property. The call will be aborted if it takes longer than the specified timeout. Can be used alongside `abortSignal`.
- `onStepFinish` (optional): A callback invoked after each agent step (LLM/tool call) completes. Useful for tracking token usage or logging.

## Example: Custom Agent Implementation

Here's how you might implement your own Agent:

```ts
import { Agent, GenerateTextResult, StreamTextResult } from 'ai';
import type { ModelMessage } from '@ai-sdk/provider-utils';

class MyEchoAgent implements Agent {
  version = 'agent-v1' as const;
  id = 'echo';
  tools = {};

  async generate({ prompt, messages, abortSignal }) {
    const text = prompt ?? JSON.stringify(messages);
    return { text, steps: [] };
  }

  async stream({ prompt, messages, abortSignal }) {
    const text = prompt ?? JSON.stringify(messages);
    return {
      textStream: (async function* () {
        yield text;
      })(),
    };
  }
}
```

## Usage: Interacting with Agents

All SDK utilities that accept an agent—including [`createAgentUIStream`](/docs/reference/ai-sdk-core/create-agent-ui-stream), [`createAgentUIStreamResponse`](/docs/reference/ai-sdk-core/create-agent-ui-stream-response), and [`pipeAgentUIStreamToResponse`](/docs/reference/ai-sdk-core/pipe-agent-ui-stream-to-response)—expect an object adhering to the `Agent` interface.

You can use the official [`ToolLoopAgent`](/docs/reference/ai-sdk-core/tool-loop-agent) (recommended for multi-step AI workflows with tool use), or supply your own implementation:

```ts
import { ToolLoopAgent, createAgentUIStream } from "ai";

const agent = new ToolLoopAgent({ ... });

const stream = await createAgentUIStream({
  agent,
  messages: [{ role: "user", content: "What is the weather in NYC?" }]
});

for await (const chunk of stream) {
  console.log(chunk);
}
```

## See Also

- [`ToolLoopAgent`](/docs/reference/ai-sdk-core/tool-loop-agent) &mdash; Official multi-step agent implementation
- [`createAgentUIStream`](/docs/reference/ai-sdk-core/create-agent-ui-stream)
- [`GenerateTextResult`](/docs/reference/ai-sdk-core/generate-text)
- [`StreamTextResult`](/docs/reference/ai-sdk-core/stream-text)

## Notes

- Agents should define their `tools` property, even if empty (`{}`), for compatibility with SDK utilities.
- The interface accepts both plain prompts and message arrays as input, but only one at a time.
- The `CALL_OPTIONS` generic parameter allows agents to accept additional call-specific options when needed.
- The `abortSignal` parameter enables cancellation of agent operations.
- This design is extensible for both complex autonomous agents and simple LLM wrappers.