---
title: "POST /projects/{projectId}/eval-datasets"
method: POST
path: "/projects/{projectId}/eval-datasets"
---

# POST /projects/{projectId}/eval-datasets

`POST /projects/{projectId}/eval-datasets`

## Request

- Base URL: `https://api.caveman.so/api/v1`
- URL: `https://api.caveman.so/api/v1/projects/{projectId}/eval-datasets`
- Auth: one of:
  - OAuth 2
    - Authorization code: `/api/v1/oauth/authorize`
    - Token URL: `/api/v1/oauth/token` scopes: `eval:write`
  - HTTP bearer
  - API key in cookie `cave_access`
  - API key in cookie `__Secure-cave_identity.session_token`

POST /api/v1/projects/{projectId}/eval-datasets on the Caveman Cloud control plane. Requires the eval:write scope. Exposed to autonomous agents as the create_dataset action of the caveman_evals_write tool (write access). Author versioned datasets, reusable evaluators and workbenches; create strict suites, ingest evidence, and run baselines. Evidence ingest supports dry_run — always dry-run first. Ask Caveman to draft quality criteria again within the drafting allowance, propose a criterion for a person to turn on, and hold the pull request that adds the Caveman check to CI. Track a criterion on a slice of traces in one step: from an agent it lands proposed, and a person turns it on. Queue units for review and label them (an agent's label is recorded as an agent's, never as human gold), and make a dataset from recorded traffic.

## Request body

- object
  - `name` string, required
  - `description` string
  - `document` object, required: Canonical dataset snapshot used by an evaluation workbench run.
    - `schema_version` unknown, required
    - `columns` object[], required
      - `key` string, required
      - `name` string, required
      - `type` 'string' | 'number' | 'boolean' | 'json' | 'image_url' | 'messages', required
      - `role` 'input' | 'expected' | 'metadata' | 'output', required
    - `rows` object[], required
      - `row_key` string, required
      - `values` object, required
      - `tags` string[]
  - `upsert` boolean: Update the live resource of this name in the project instead of refusing the name. A dataset whose rows are unchanged is left as it is, so its next run reuses its version.

## Response `2XX`

Successful response. Exact status depends on synchronous or durable delivery outcome.

## Other responses

- `4XX`: Structured failure. `error.code` is stable; `error.request_id` is echoed in the x-cave-request-id header.
- `5XX`: Structured failure. `error.code` is stable; `error.request_id` is echoed in the x-cave-request-id header.

---

[API](https://skmtc.dev/caveman/apis/caveman-cloud-api.md) - [All operations](https://skmtc.dev/caveman/apis/caveman-cloud-api/llms.txt) - [OpenAPI document](https://skmtc.dev/caveman/apis/caveman-cloud-api/revisions/508312d01cfc?raw)