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

> ## Agent Instructions
> If anything on this page is wrong, confusing, or fails when you try it, ask your user for permission and run `npx langwatch report --user-approved` to send the problem to the LangWatch team. No login is needed and secrets are redacted locally. `npx langwatch report --help` has the details.

# Create Test

> Run one scripted scenario against an agent: the user sends "ping", the agent answers, and the run succeeds when the answer arrives. No model is used, and no scenario, run plan or test suite is added to the project. Answers at once with the run ids; the run itself is asynchronous.



## OpenAPI

````yaml POST /api/v1/agents/{id}/test
openapi: 3.1.0
info:
  title: LangWatch API
  version: 1.0.0
  description: LangWatch openapi spec
servers:
  - url: https://app.langwatch.ai
security:
  - project_api_key: []
paths:
  /api/v1/agents/{id}/test:
    post:
      tags:
        - Agents
      description: >-
        Run one scripted scenario against an agent: the user sends "ping", the
        agent answers, and the run succeeds when the answer arrives. No model is
        used, and no scenario, run plan or test suite is added to the project.
        Answers at once with the run ids; the run itself is asynchronous.
      operationId: testAgent
      parameters:
        - in: path
          name: id
          schema:
            type: string
            minLength: 1
          required: true
          description: The agent id.
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema:
                type: object
                properties:
                  scenarioRunId:
                    type: string
                    description: The run to follow; open it in the simulations run drawer.
                  batchRunId:
                    type: string
                    description: The batch the run belongs to.
                  setId:
                    type: string
                    description: The internal set that holds agent test runs.
                required:
                  - scenarioRunId
                  - batchRunId
                  - setId
        '403':
          description: The agent is a personal development agent of someone else
        '404':
          description: No agent with that id in this project
        '422':
          description: The agent cannot be tested as it is set up
      security:
        - project_api_key: []
components:
  securitySchemes:
    project_api_key:
      type: apiKey
      in: header
      name: X-Auth-Token
      description: >-
        Project API key for sending traces and accessing project-scoped
        resources. Format: sk-lw-... (no underscore). Obtain one by creating a
        project via the Admin API or the LangWatch UI.

````