> ## Documentation Index > Fetch the complete documentation index at: https://docs.devtune.ai/llms.txt > Use this file to discover all available pages before exploring further. # Get Agent Picks starter test > Returns the project’s latest Agent Picks starter test as it runs: its status (queued, running, completed, failed or cancelled), when it was created and completed, planned vs completed runs, and each run’s request, agent and model, status, recorded sandbox attempts and, once classified, its pick (a tool_key, or built_its_own and the other outcomes). A failed or cancelled test keeps its runs. A project with no starter test returns test null and empty runs. These are per-run results, not rates; install rates come from the summary once the test completes. Any parameter is refused with 400. Needs the Agent Picks feature; without it the request is refused with 403. ## OpenAPI ````yaml /openapi.json get /projects/{projectId}/agent-picks/starter-test openapi: 3.1.0 info: title: DevTune API version: 2.0.0 description: >- API for programmatic access to your AI visibility data, webhook subscriptions, and automation workflows. Use this API to integrate DevTune data into CI/CD pipelines, BI tools, AI agents, and operational systems. servers: - url: https://devtune.ai/api/v2 description: Production security: - bearerAuth: [] paths: /projects/{projectId}/agent-picks/starter-test: get: summary: Get Agent Picks starter test description: >- Returns the project’s latest Agent Picks starter test as it runs: its status (queued, running, completed, failed or cancelled), when it was created and completed, planned vs completed runs, and each run’s request, agent and model, status, recorded sandbox attempts and, once classified, its pick (a tool_key, or built_its_own and the other outcomes). A failed or cancelled test keeps its runs. A project with no starter test returns test null and empty runs. These are per-run results, not rates; install rates come from the summary once the test completes. Any parameter is refused with 400. Needs the Agent Picks feature; without it the request is refused with 403. operationId: getAgentPicksStarterTest parameters: - name: projectId in: path required: true schema: type: string format: uuid responses: '200': description: Agent Picks starter test content: application/json: schema: type: object properties: data: $ref: '#/components/schemas/AgentPicksStarterTestData' meta: $ref: '#/components/schemas/Meta' required: - data - meta '400': $ref: '#/components/responses/BadRequestError' '401': $ref: '#/components/responses/UnauthorizedError' '403': $ref: '#/components/responses/ForbiddenError' '404': $ref: '#/components/responses/NotFoundError' '429': $ref: '#/components/responses/RateLimitExceededError' components: schemas: AgentPicksStarterTestData: type: object properties: test: type: - object - 'null' description: The project’s latest starter test; null when it has none. properties: id: type: string format: uuid status: type: string enum: - queued - running - completed - failed - cancelled category_id: type: string format: uuid created_at: type: string format: date-time completed_at: type: - string - 'null' format: date-time planned_runs: type: integer minimum: 0 description: Every run the test queued. completed_runs: type: integer minimum: 0 description: Runs with status completed. environment: type: - object - 'null' properties: name: type: string framework: type: - string - 'null' required: - name - framework required: - id - status - category_id - created_at - completed_at - planned_runs - completed_runs - environment runs: type: array description: >- The test’s runs by request (add, recommend, hosted) then agent. Empty when there is no test. A failed or cancelled test keeps its runs. items: type: object properties: id: type: string format: uuid intent: type: string description: >- add (build it), recommend (recommend one) or hosted (hosted service). request: type: string description: The request the agent was given. agent: type: string model: type: string status: type: string enum: - queued - running - completed - failed - cancelled outcome: type: - string - 'null' description: >- installed, built_its_own, no_provider, other_tool, none or unclassified; null until the run is classified. tool_key: type: - string - 'null' description: >- The installed tool; null for every other outcome and before classification. other_tools: type: array items: type: string description: >- For other_tool: the packages and hosts the run added that no tool in the test names. sandbox_attempts: type: integer minimum: 0 description: >- Sandboxes the run started, as recorded; 0 before its first starts. required: - id - intent - request - agent - model - status - outcome - tool_key - other_tools - sandbox_attempts tools: type: - array - 'null' description: >- The tools the test ran with, as recorded when it was queued, with a display name and logo domain to label each tool_key. The labels can reflect catalogue edits made since; the list of tools does not. Null for a test queued before tests recorded their tools, whose tool list is unknown; empty when there is no test. items: type: object properties: tool_key: type: string display_name: type: string brand_domain: type: - string - 'null' required: - tool_key - display_name - brand_domain required: - test - runs - tools Meta: type: object properties: timestamp: type: string format: date-time projectId: type: string format: uuid Error: type: object properties: error: type: string message: type: string reason: type: string description: >- Why the request was refused, for an error with more than one cause, such as a refused content-draft start. status: type: integer required: - error - message - status responses: BadRequestError: description: Bad request content: application/json: schema: $ref: '#/components/schemas/Error' UnauthorizedError: description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error' ForbiddenError: description: Forbidden content: application/json: schema: $ref: '#/components/schemas/Error' NotFoundError: description: Not found content: application/json: schema: $ref: '#/components/schemas/Error' RateLimitExceededError: description: Rate limit exceeded headers: X-RateLimit-Limit: $ref: '#/components/headers/X-RateLimit-Limit' X-RateLimit-Remaining: $ref: '#/components/headers/X-RateLimit-Remaining' X-RateLimit-Reset: $ref: '#/components/headers/X-RateLimit-Reset' content: application/json: schema: $ref: '#/components/schemas/Error' headers: X-RateLimit-Limit: description: Maximum requests per window schema: type: integer X-RateLimit-Remaining: description: Requests remaining in current window schema: type: integer X-RateLimit-Reset: description: Unix timestamp when the window resets schema: type: integer securitySchemes: bearerAuth: type: http scheme: bearer description: >- API key with dtk_live_ prefix. Obtain it from API Keys in the account sidebar. New keys start with all supported scopes selected for the chosen project, and you can narrow them to specific read/write scopes as needed. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.