---
title: "List evaluations"
method: GET
path: "/agents/{agent_id}/evaluations"
tags: ["Evaluations"]
---

# List evaluations

`GET /agents/{agent_id}/evaluations`

Returns a cursor-paginated list of evaluation results for a specific agent, newest first.
Only completed and failed evaluations are returned (transient states like queued/in_progress are excluded).

Each evaluation includes the grade, criteria pass/fail results, extracted data points, applied tags, and sentiment analysis.

## Path parameters

- `agent_id` string, required

## Query parameters

- `page_size` integer
- `cursor` string
- `grade` 'pass' | 'needs_review' | 'needs_attention'

## Response `200`

Paginated list of evaluation results.

- object
  - `evaluations` EvaluationResult[]
    - `evaluation_id` string — Unique ID of this evaluation.
    - `interaction_id` string — ID of the interaction that was evaluated.
    - `agent_id` string — ID of the agent.
    - `created_ts` string, date-time — When the evaluation was created.
    - `status` 'completed' | 'failed' — Terminal status of the evaluation.
    - `grade` 'pass' | 'needs_review' | 'needs_attention' — Overall grade computed from criteria, sentiment, and call outcome.
    - `call_successful` 'success' | 'failure' | 'unknown' — Whether the agent's call/task was successful.
    - `sentiment` 'positive' | 'neutral' | 'negative', nullable — Detected sentiment of the interaction (null if sentiment analysis is disabled).
    - `summary` string, nullable — One or two sentence narrative of what happened in the interaction.
    - `criteria_results` object[] — Per-criterion pass/fail results with rationales.
      - `id` string
      - `name` string
      - `type` 'prohibited_action' | 'prohibited_words' | 'voice_tone' | 'other'
      - `priority` 'needs_review' | 'needs_attention'
      - `result` 'success' | 'failure' | 'unknown'
      - `rationale` string
    - `data_results` object[] — Extracted data point values from the conversation.
      - `id` string
      - `name` string
      - `data_type` 'string' | 'boolean' | 'integer' | 'number'
      - `value` unknown
    - `applied_tags` string[] — Tags applied to this evaluation.
  - `next_cursor` string, nullable — Pass this value as the `cursor` query parameter to fetch the next page. Null when there are no more results.

## Other responses

- `400` — Invalid grade parameter.
- `401` — Unauthorized — missing or invalid credentials.
- `403` — Forbidden — insufficient permissions on this agent.

---

[API](https://skmtc.dev/gumloop/apis/public-api.md) · [All operations](https://skmtc.dev/gumloop/apis/public-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/gumloop/public-api/revisions/115f2d6ce387/schema)