> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.vapi.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.vapi.ai/_mcp/server.

# Generate Improvement Suggestions

POST https://api.vapi.ai/eval/simulation/run/{id}/item/{itemId}/generate

Generates AI suggestions for improving the assistant or squad's system prompt, tools, and scenarios, based on the specified run item.

Reference: https://docs.vapi.ai/api-reference/simulation-runs/simulation-run-controller-generate-suggestions

## Authentication

- `Authorization` header (bearer token, required) — Authenticate server-side requests with a private Vapi API key. Create or copy a key from the [Vapi Dashboard](https://dashboard.vapi.ai) and send it in the `Authorization` header as `Bearer <token>`. Keep private API keys out of client-side code and public repositories.

## Request

### Path parameters

- `id` (string, required) — The unique identifier of the simulation run.
- `itemId` (string, required) — The unique identifier of the run item.

### Query parameters

- `force` (string, required) — Set to the string `true` to regenerate improvement suggestions even if they already exist.
- `persist` (string, optional)

## Examples

**Response**

```json
{}
```