> ## 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 an experiment and its setup

> Create an evaluations experiment. Send a setup to start from, or send none and get a blank workbench with one inline dataset. The slug it answers with is what every other experiment endpoint takes.



## OpenAPI

````yaml POST /api/v1/experiments
openapi: 3.1.0
info:
  title: LangWatch API
  description: LangWatch openapi spec
  version: 1.0.0
servers:
  - url: https://app.langwatch.ai
security:
  - project_api_key: []
paths:
  /api/v1/experiments:
    post:
      tags:
        - Experiments
      summary: Create an experiment and its setup
      description: >-
        Create an evaluations experiment. Send a setup to start from, or send
        none and get a blank workbench with one inline dataset. The slug it
        answers with is what every other experiment endpoint takes.
      operationId: postApiExperiments
      requestBody:
        required: false
        content:
          application/json:
            schema:
              type: object
              properties:
                name:
                  description: >-
                    Name for the experiment. A draft name is picked when
                    omitted.
                  type: string
                  minLength: 1
                state:
                  description: >-
                    Setup to start from. Omit for a blank workbench with one
                    inline dataset.
                  type: object
                  propertyNames:
                    type: string
                  additionalProperties: {}
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema:
                type: object
                properties:
                  id:
                    type: string
                    description: Identifier of the created experiment
                  slug:
                    type: string
                    description: Slug to address the experiment by
                  version:
                    type: number
                    description: Version of the saved setup, starting at 1
                required:
                  - id
                  - slug
                  - version
                additionalProperties: false
        '400':
          description: >-
            The setup did not match the schema
            (experiment_invalid_workbench_state) or points at something that no
            longer exists (experiment_workbench_missing_reference)
          content: {}
      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.

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.