> ## 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 run evidence > Inspect a run owned by the account, project and test together. Includes queued, running, failed, cancelled and completed runs. Request and job text are withheld; request_withheld and job_withheld distinguish withheld snapshots from absent ones; pick is null without a classification. Events are recorded observations ordered by seq then id, not inferred causes or proof of a working integration. not_retained means there are no retained events, including before a running run records them. Raw commands, error text, provider prompts and artifacts are withheld. URLs show only their HTTP origin. Search terms, file paths and unknown runtime tool names are withheld with explicit indicators. Packages must match the configured tool catalog. Requires Agent Picks and visibility.read. limit defaults to 50, maximum 100. Pass the returned next_cursor verbatim as cursor with the same filters until has_more is false. Detail pagination is inside evidence; list pagination is at the top level. Invalid parameters or a cursor for another scope return 400. Reads cannot start, cancel or change a run. ## OpenAPI ````yaml /openapi.json get /projects/{projectId}/agent-picks/tests/{testId}/runs/{runId} 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/tests/{testId}/runs/{runId}: get: summary: Get Agent Picks run evidence description: >- Inspect a run owned by the account, project and test together. Includes queued, running, failed, cancelled and completed runs. Request and job text are withheld; request_withheld and job_withheld distinguish withheld snapshots from absent ones; pick is null without a classification. Events are recorded observations ordered by seq then id, not inferred causes or proof of a working integration. not_retained means there are no retained events, including before a running run records them. Raw commands, error text, provider prompts and artifacts are withheld. URLs show only their HTTP origin. Search terms, file paths and unknown runtime tool names are withheld with explicit indicators. Packages must match the configured tool catalog. Requires Agent Picks and visibility.read. limit defaults to 50, maximum 100. Pass the returned next_cursor verbatim as cursor with the same filters until has_more is false. Detail pagination is inside evidence; list pagination is at the top level. Invalid parameters or a cursor for another scope return 400. Reads cannot start, cancel or change a run. operationId: getAgentPicksRun parameters: - name: projectId in: path required: true schema: type: string format: uuid - name: testId in: path required: true schema: type: string format: uuid - name: runId in: path required: true schema: type: string format: uuid - name: limit in: query schema: type: integer minimum: 1 maximum: 100 default: 50 - name: cursor in: query schema: type: string maxLength: 2000 responses: '200': description: Agent Picks operational evidence content: application/json: schema: type: object properties: data: $ref: '#/components/schemas/AgentPicksRunDetail' 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: AgentPicksRunDetail: type: object additionalProperties: false required: - run - context - pick - evidence properties: run: type: object additionalProperties: false required: - id - test_id - test_kind - test_status - agent - model - repetition - status - created_at - started_at - completed_at - early_stopped - wall_ms - has_error properties: id: type: string format: uuid test_id: type: string format: uuid test_kind: type: string test_status: type: string enum: - queued - running - failed - cancelled - completed agent: type: string model: type: string repetition: type: integer status: type: string enum: - queued - running - failed - cancelled - completed created_at: type: string format: date-time started_at: type: - string - 'null' completed_at: type: - string - 'null' early_stopped: type: boolean wall_ms: type: - number - 'null' has_error: type: boolean context: type: object additionalProperties: false required: - environment - request - request_withheld - job_withheld - intent - job - classifier_version - agent_timeout_sec properties: environment: anyOf: - type: object additionalProperties: false required: - id - slug - name - framework properties: id: type: string slug: type: string name: type: string framework: type: - string - 'null' - type: 'null' request_withheld: type: boolean job_withheld: type: boolean request: type: - string - 'null' intent: type: - string - 'null' job: type: - string - 'null' classifier_version: type: - string - 'null' agent_timeout_sec: type: - number - 'null' pick: anyOf: - type: object additionalProperties: false required: - outcome - tool_key - tool_display_name - tool_brand_domain - confidence - classifier_version - decided_by - tool_packages - tool_packages_withheld - other_tools - other_tools_withheld - diff_truncated properties: outcome: type: string tool_key: type: - string - 'null' tool_display_name: type: - string - 'null' tool_brand_domain: type: - string - 'null' confidence: type: - number - 'null' classifier_version: type: string decided_by: type: - string - 'null' tool_packages_withheld: type: boolean tool_packages: type: array items: type: string other_tools_withheld: type: boolean other_tools: type: array items: type: string diff_truncated: type: boolean - type: 'null' evidence: type: object additionalProperties: false required: - availability - items - pagination properties: availability: type: string enum: - recorded - not_retained - end_of_trail items: type: array items: type: object additionalProperties: false required: - id - seq - kind - url - status_code - recorded_at - observed_at - detail properties: id: type: string format: uuid seq: type: integer kind: type: string enum: - search - fetch - read - command - install - write url: type: - string - 'null' status_code: type: - number - 'null' recorded_at: type: string observed_at: type: - number - 'null' detail: type: object additionalProperties: false required: - queries - path - packages - source - method - exit_code - failed - command_withheld - text_withheld - packages_withheld properties: queries: type: array items: type: string path: type: - string - 'null' packages: type: array items: type: string source: type: - string - 'null' method: type: - string - 'null' exit_code: type: - number - 'null' failed: type: - boolean - 'null' text_withheld: type: boolean packages_withheld: type: boolean command_withheld: type: boolean pagination: type: object additionalProperties: false required: - has_more - next_cursor - limit properties: has_more: type: boolean next_cursor: type: - string - 'null' limit: type: integer minimum: 1 maximum: 100 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.