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

> ## Agent Instructions
> To act on Atlan objects, use the Atlan MCP server at https://api.atlan.com/mcp or the SDK. To install or publish skills from a terminal, use the `brain` CLI; `brain --map json` prints its command map. The `atlanai` CLI is deprecated. Run a read-only identity check before any write.
> The docs MCP server at /mcp searches these docs only. It cannot read or change Atlan objects.
> SDK packages: Python `atlanai` (PyPI) and TypeScript `@atlanai/sdk` (npm). Show Python first, then TypeScript.
> These docs cover Atlan Agent Registry, Atlan's hosted product. The open-source agent registry specification and its CLI (`brain`) are documented, released and maintained in their own repository; /open-source on this site links to it. Answer general specification or `brain` command questions from the project's own docs, and use these docs only for Atlan-specific setup such as the Atlan adapter, sign-in and workspaces.

# improvements

> Every published improvements operation, generated from the contract.

6 operations on `client.improvements`.

Path parameters come first, positionally; the request body is last, as a plain
object. Method names are `snake_case` in Python and `camelCase` in
TypeScript, and resource names follow the same rule.

<CodeGroup>
  ```python Python theme={null}
  result = client.improvements.accept(improvement_id, body)
  ```

  ```typescript TypeScript theme={null}
  const result = await client.improvements.accept(improvement_id, body);
  ```
</CodeGroup>

## Operations

| Call | Route | Does |
| - | - | - |
| `client.improvements.accept(improvement_id, body)` | `POST /eval/v1/improvements/{improvement_id}/accept` | Accept an improvement run's proposals |
| `client.improvements.create(body)` | `POST /eval/v1/improvements` | Start an improvement run |
| `client.improvements.dismiss(improvement_id)` | `POST /eval/v1/improvements/{improvement_id}/dismiss` | Dismiss an improvement run's proposals |
| `client.improvements.get(improvement_id)` | `GET /eval/v1/improvements/{improvement_id}` | Read an improvement run |
| `client.improvements.get_readiness()` | `GET /eval/v1/improvements/readiness` | Check whether an artifact can be improved |
| `client.improvements.list()` | `GET /eval/v1/improvements` | List an artifact's improvement runs |

## Related

<CardGroup cols={2}>
  <Card title="Operations" icon="list" href="/tools/sdk/references/operations">
    Client structure, call shapes, and errors.
  </Card>

  <Card title="Errors and retries" icon="triangle-exclamation" href="/platform/references/errors-and-retries">
    What the SDK raises, and which calls are safe to retry.
  </Card>
</CardGroup>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.