> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tai42.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Author an agent

> Author an agent against the contract.

Author an agent against the `Agent` contract and load it from the manifest.

An agent is an LLM-driven capability registered alongside tools. You implement one interface — the `Agent` contract — and the runtime derives two faces from it: a JSON `run` tool (LLM, MCP, and flow-engine facing) and an in-process `astream` method (API and SSE facing). You write only the `Agent` class; no hand-written tool wrapper.

## Implement the Agent contract

Subclass `Agent`, declare the three class attributes that drive tool generation, and implement `run`. `run` is the primitive; the base class provides a default `astream` that runs once and emits one terminal event, which streaming agents override.

```python myapp/agents.py theme={null}
from pydantic import BaseModel
from tai42_contract.agent import Agent
from tai42_contract.app import tai42_app


class EchoInput(BaseModel):
    text: str


@tai42_app.agents.agent("echo")
class EchoAgent(Agent):
    tool_name = "echo"
    tool_description = "Echo the input text back."
    ToolInput = EchoInput

    async def run(self, *, user_message: str = "", **kwargs) -> str:
        return user_message
```

`ToolInput` is a JSON-able pydantic model of the tool parameters — a non-JSON field fails loudly when its schema is generated. The `@tai42_app.agents.agent(name)` decorator registers the agent and auto-registers its JSON `run` tool.

## Load it from the manifest

Name the module under `agents[]`. Importing it runs the decorator.

```yaml manifest.yml theme={null}
agents:
  - title: my_agents
    module: myapp.agents
    include: []
```

## Run it

<Steps>
  <Step title="List registered agents">
    ```bash theme={null}
    tai agents list
    ```
  </Step>

  <Step title="Stream a run">
    Stream a run one event frame at a time, passing the input as a JSON object.

    ```bash theme={null}
    tai agents run echo --input '{"text":"hello"}'
    ```
  </Step>
</Steps>

<Tip>
  Author a saved variant of an agent — an authored agent — by baking `fixed_kwargs` into a [preset](/concepts/presets) over the agent: `tai presets create`, then run it with `tai agents authored-run`. Which fields you may bake is a **per-field** capability the agent declares. Mark `spec_runnable = True` to make every `ToolInput` field bakeable, or list individual field names in `preset_bakeable_fields` to bake just those. Baking a field the agent does not declare bakeable is rejected at author time with a `400` (see [Author an agent plugin](/guides/authors/agent-plugin) for the gate and its errors).
</Tip>

## See also

* [Agents](/concepts/agents) — the two faces of one `Agent` class.
* [Deep agents](/concepts/deep-agents) — sub-agents, skills, and strategies.
* [Author an agent plugin](/guides/authors/agent-plugin) — ship an agent as a distributable plugin.
* [Python SDK reference](/reference/python-sdk) — the `Agent` contract surface.