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

# Read what a run produced

> One row per case: what the worker did, what it read to get there, and the verdict if it has been scored. A row with `error` set is a case whose session could not run — it produced nothing to judge, and is counted apart from the worker performing badly.



## OpenAPI

````yaml /api/statisfy-api.openapi.json get /v1/evaluations/runs/{run_id}/results
openapi: 3.1.0
info:
  description: >-
    The agent-first Statisfy API. Authenticate with an API key (`Authorization:
    Bearer stfy_live_…`), then call `GET /v1/meta/capabilities` to discover
    every operation and its schemas.
  title: Statisfy API
  version: 1.0.0
servers:
  - url: https://api.statisfy.com
    description: Production
security: []
paths:
  /v1/evaluations/runs/{run_id}/results:
    get:
      tags:
        - evaluations
      summary: Read what a run produced
      description: >-
        One row per case: what the worker did, what it read to get there, and
        the verdict if it has been scored. A row with `error` set is a case
        whose session could not run — it produced nothing to judge, and is
        counted apart from the worker performing badly.
      operationId: evaluations_list_results
      parameters:
        - description: The run, from POST /v1/evaluations/runs.
          in: path
          name: run_id
          required: true
          schema:
            type: string
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ResultsResponse'
          description: Successful Response
      security:
        - HTTPBearer: []
components:
  schemas:
    ResultsResponse:
      properties:
        data:
          items:
            $ref: '#/components/schemas/Result'
          title: Data
          type: array
      title: ResultsResponse
      type: object
    Result:
      properties:
        case_id:
          title: Case Id
          type: string
        defer_reason:
          anyOf:
            - type: string
            - type: 'null'
          title: Defer Reason
        deferred:
          default: false
          description: >-
            The worker handed the thread to a human instead of answering.
            Reactive runs only.
          title: Deferred
          type: boolean
        error:
          anyOf:
            - type: string
            - type: 'null'
          description: >-
            The session's own failure. Distinct from a failing verdict: this
            case produced nothing to judge.
          title: Error
        id:
          title: Id
          type: string
        judged_by:
          anyOf:
            - type: string
            - type: 'null'
          title: Judged By
        output:
          anyOf:
            - additionalProperties: true
              type: object
            - type: 'null'
          description: >-
            What the worker did, in the shape its mode produces. Proactive:
            `acted`, any `drafts` it composed, and its own `summary`. Reactive:
            `answered`, the `reply` text, the two ways a reply can be withheld —
            `held_by_guardrail` (the platform stopped it) and `no_reply` (the
            worker judged the thread needed none) — and `loop_in`: the part of
            the ask handed to a person while the reply goes out (`note` for
            them, a follow-up `draft` they finish, and the guardrail's `flag` on
            it), null when nothing was left for a person. A `loop_in` is a
            hand-off as much as `deferred` is. Results recorded before loop-ins
            were (16 Nov 2026) have no `loop_in` key: there, its absence does
            not mean nobody was looped in.
          title: Output
        passed:
          anyOf:
            - type: boolean
            - type: 'null'
          description: null means nobody has scored this one yet.
          title: Passed
        reason:
          anyOf:
            - type: string
            - type: 'null'
          title: Reason
        scores:
          anyOf:
            - additionalProperties: true
              type: object
            - type: 'null'
          title: Scores
        tool_calls:
          anyOf:
            - items:
                additionalProperties: true
                type: object
              type: array
            - type: 'null'
          description: >-
            What it read to get there — the evidence a verdict about grounding
            has to be checked against.
          title: Tool Calls
        trace_id:
          anyOf:
            - type: string
            - type: 'null'
          title: Trace Id
        turns:
          anyOf:
            - type: integer
            - type: 'null'
          title: Turns
      required:
        - id
        - case_id
      title: Result
      type: object
  securitySchemes:
    HTTPBearer:
      scheme: bearer
      type: http
      description: >-
        An API key, sent as `Authorization: Bearer stfy_live_…`. See
        [Authentication](/rest-api/authentication) for how to get one and which
        scopes it needs.

````

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