---
title: "Get Test Run"
method: GET
path: "/v1/test-runs/{jobId}"
tags: ["Test Runs"]
---

# Get Test Run

`GET /v1/test-runs/{jobId}`

## Request

- Base URL: `https://api.sigmamind.ai`
- URL: `https://api.sigmamind.ai/v1/test-runs/{jobId}`
- Auth: API key in header `X-API-Key`

Retrieves the full details of a single test run by jobId, scoped to the specified batch and agent. Returns the test case name, execution status, expected and actual outcomes, and transcript details.

## Path parameters

- `jobId` string, required

## Query parameters

- `batchId` string, required
- `agentId` string, required

## Response `200`

OK

- TestCaseRunResponse: List of items for the current page. Contains up to 'size' number of records.
  - `batchId` string: The unique identifier of the batch run this simulation attempt belongs to.
  - `workspaceId` string: The unique identifier of the workspace under which this simulation attempt was created.
  - `agent` AgentResponse: Agent assigned to handle all calls in this campaign. Contains the agent's ID, name, and current status. All contacts in the campaign's contact list will be called using this agent.
    - `name` string: The display name of the assigned agent.
    - `agentId` string: The unique identifier of the agent within the system.
    - `status` 'Live' | 'Testing' | 'Disabled': The current operational status of the agent.
  - `testCase` TestCaseResponse
    - `testCaseId` string: The unique identifier of the test case.
    - `label` string: A human-readable name or label for the test case, used to identify it in reports and dashboards.
    - `agent` AgentResponse: Agent assigned to handle all calls in this campaign. Contains the agent's ID, name, and current status. All contacts in the campaign's contact list will be called using this agent.
      - `name` string: The display name of the assigned agent.
      - `agentId` string: The unique identifier of the agent within the system.
      - `status` 'Live' | 'Testing' | 'Disabled': The current operational status of the agent.
    - `workspaceId` string: The unique identifier of the workspace under which this test case was created.
    - `llmModel` string: The LLM model used to generate Agent responses during the simulation.
    - `mockData` MockDataResponse[]: The list of mock variables and their simulated values that were used to substitute for real external data sources during the simulation.
      - `variableName` string: The name of the variable that was substituted with mock data during the simulation.
      - `value` string: The simulated value that was assigned to the variable for the duration of the test run.
    - `mockToolData` MockToolDataJSON[]: Bindings from agent tool aliases to mock tool responses. May include resolved mock name and statusCode for the UI.
      - `toolAlias` string, required: Tool alias on the agent that this mock should satisfy during simulation.
      - `mockToolDataId` string, required: Public identifier of the mock tool data library record.
      - `name` string: Display name of the linked mock (resolved on read for the UI).
      - `statusCode` integer: HTTP status code of the linked mock (resolved on read for the UI).
    - `userPrompt` string: The prompt that defined the persona and intent of the simulated user, driving the user-side messages throughout the conversation.
    - `attempt` integer: The number of times this test case was configured to run as independent simulation attempts.
    - `successCriteria` string[]: Ordered goals used to evaluate the agent after each simulation run.
  - `jobId` string: The unique identifier of this individual simulation attempt within the batch run.
  - `chatId` string: The unique identifier of the chat session generated during this simulation run.
  - `createdDate` string, date-time: The UTC timestamp indicating when this simulation run was initiated.
  - `completedDate` string, date-time: The UTC timestamp indicating when this simulation run was completed.
  - `isSuccessful` boolean: Indicates whether the Agent met the success criteria during this simulation run.
  - `remarks` string: A plain-language explanation of why a goal failed. This is the root cause, separate from which goals passed or failed.
  - `criteriaResults` object: Pass or fail for each success criterion. Keys are the criterion text in list order. Values are Pass or Fail.
  - `conversation` ConversationResponse[]: The full transcript of the conversation between the simulated user and the Agent during this simulation run.
    - `role` string: The role of the participant who sent this message in the simulation. Indicates whether the message was generated by the simulated user or the Agent.
    - `content` string: The message content produced by the participant for this turn in the conversation.

## Other responses

- `400`: Bad Request
- `401`: Unauthorized
- `403`: Forbidden
- `404`: Not Found
- `500`: Internal Server Error

## Changes

- **2026-11-06** `783c9e4c5126`: 1 breaking, 1 info
  - the `testCase/successCriteria` response's property type changed from `string` to `array` for status `200`
  - added the optional property `criteriaResults` to the response with the `200` status
- **2026-11-03** `64c0435b10eb`: 1 info
  - added the optional property `testCase/mockToolData` to the response with the `200` status

[Operation history](https://skmtc.dev/sigmamind/apis/sigmamind-apis/changes/v1/test-runs/:jobId/get.md)

---

[API](https://skmtc.dev/sigmamind/apis/sigmamind-apis.md) - [All operations](https://skmtc.dev/sigmamind/apis/sigmamind-apis/llms.txt) - [OpenAPI document](https://skmtc.dev/sigmamind/apis/sigmamind-apis/revisions/783c9e4c5126?raw)