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

# Human in the loop

> Let the agent ask a clarifying question, or hand control back and forth.

`clarify` is the only planning knob. By default (`clarify=false`) the agent infers
reasonable defaults and executes without asking. Set `clarify=true` when a human is present
and a missing answer would materially change the work.

| Value   | Agent behavior                                                                |
| ------- | ----------------------------------------------------------------------------- |
| `false` | Plan, infer defaults, and execute without asking. The default for automation. |
| `true`  | Allow **one** blocking planning question before execution.                    |

<CodeGroup>
  ```python Python theme={"theme":{"light":"github-light","dark":"github-dark"}}
  from autumn_sdk import AutumnClient

  client = AutumnClient()
  result = client.run(
      "Build a list of fintech companies",
      clarify=True,   # may ask one question, e.g. geography or target count
  )
  print(result.output)
  ```

  ```typescript TypeScript theme={"theme":{"light":"github-light","dark":"github-dark"}}
  import { AutumnClient } from "autumn-sdk";

  const client = new AutumnClient();
  const result = await client.run("Build a list of fintech companies", { clarify: true });
  console.log(result.output);
  ```
</CodeGroup>

## Review, then continue

A common pattern: run the first part, let a human review the rows, then continue the same
task with corrections.

```python Python theme={"theme":{"light":"github-light","dark":"github-dark"}}
client = AutumnClient()

task = client.tasks.create("Find Series A fintech companies in the US")
rows = client.tasks.output(task.id)["rows"]

# ... human reviews rows ...

client.tasks.continue_(task.id, "Drop anything past Series A and add the CEO name column")
```

Because the `task_id` is durable, you can interleave agent turns and human review as many
times as you need. See [Follow-up tasks](/docs/guides/follow-up).

## Guidance

* For background automation, keep `clarify=false`.
* Use `clarify=true` only when the user is present.
* When continuing after review, restate the current goal as a clear instruction rather than
  passing the user's raw words.