# AI and automations API

> AI automations, evaluations with test cases and runs, and conversation summaries.

Source: https://developer.kustomer.com/api/ai

Server: `https://api.kustomerapp.com/v1` · 19 operations

This category describes endpoints related to Kustomer AI and Automations.

AI and Automations provide intelligent capabilities for automating customer interactions, generating responses, and analyzing conversations in Kustomer. The evaluations endpoints allow you to test and validate your AI automations with test cases and runs.

**Note:** The AI Agents feature must be enabled in your subscription to use these endpoints.
Requests return 403 Forbidden when the feature is disabled.

To learn more, see the Kustomer Help Center.

## Automations

An AI automation is an AI agent built in Kustomer, such as one that answers customers in chat or one that helps your team with their work. The API lists them so you can find an agent's ID, mainly to test it with evaluations; building and editing agents happens in Kustomer.

- [List AI automations](https://developer.kustomer.com/api/ai/list-ai-automations.md): `GET /v1/ai/automations`
- [Get AI automation by ID](https://developer.kustomer.com/api/ai/get-ai-automation-by-id.md): `GET /v1/ai/automations/{automationId}`

## Evaluations

An evaluation is a test suite for one AI agent. It holds test cases, each a customer message plus a description of a good answer; running the evaluation sends every case to the agent, has an AI judge mark each answer pass or fail, and gives the agent a score from 0 to 100.

- [List evaluations for an automation](https://developer.kustomer.com/api/ai/list-evaluations-for-an-automation.md): `GET /v1/ai/automations/{automationId}/evaluations`
- [Create an evaluation](https://developer.kustomer.com/api/ai/create-an-evaluation.md): `POST /v1/ai/evaluations`
- [Get evaluation by ID](https://developer.kustomer.com/api/ai/get-evaluation-by-id.md): `GET /v1/ai/evaluations/{evaluationId}`
- [Update an evaluation](https://developer.kustomer.com/api/ai/update-an-evaluation.md): `PUT /v1/ai/evaluations/{evaluationId}`
- [Delete an evaluation](https://developer.kustomer.com/api/ai/delete-an-evaluation.md): `DELETE /v1/ai/evaluations/{evaluationId}`
- [Run an evaluation](https://developer.kustomer.com/api/ai/run-an-evaluation.md): `POST /v1/ai/evaluations/{evaluationId}/run`

## Evaluation Test Cases

An evaluation is a test suite for one AI agent. It holds test cases, each a customer message plus a description of a good answer; running the evaluation sends every case to the agent, has an AI judge mark each answer pass or fail, and gives the agent a score from 0 to 100.

- [List evaluation test cases](https://developer.kustomer.com/api/ai/list-evaluation-test-cases.md): `GET /v1/ai/evaluation-testcases`
- [Create an evaluation test case](https://developer.kustomer.com/api/ai/create-an-evaluation-test-case.md): `POST /v1/ai/evaluation-testcases`
- [Get evaluation test case by ID](https://developer.kustomer.com/api/ai/get-evaluation-test-case-by-id.md): `GET /v1/ai/evaluation-testcases/{testCaseId}`
- [Update an evaluation test case](https://developer.kustomer.com/api/ai/update-an-evaluation-test-case.md): `PUT /v1/ai/evaluation-testcases/{testCaseId}`
- [Delete an evaluation test case](https://developer.kustomer.com/api/ai/delete-an-evaluation-test-case.md): `DELETE /v1/ai/evaluation-testcases/{testCaseId}`

## Evaluation Runs

An evaluation is a test suite for one AI agent. It holds test cases, each a customer message plus a description of a good answer; running the evaluation sends every case to the agent, has an AI judge mark each answer pass or fail, and gives the agent a score from 0 to 100.

- [List evaluation runs](https://developer.kustomer.com/api/ai/list-evaluation-runs.md): `GET /v1/ai/evaluation-runs`
- [Get evaluation run by ID](https://developer.kustomer.com/api/ai/get-evaluation-run-by-id.md): `GET /v1/ai/evaluation-runs/{runId}`

## Evaluation Test Case Results

An evaluation is a test suite for one AI agent. It holds test cases, each a customer message plus a description of a good answer; running the evaluation sends every case to the agent, has an AI judge mark each answer pass or fail, and gives the agent a score from 0 to 100.

- [List evaluation test case results](https://developer.kustomer.com/api/ai/list-evaluation-test-case-results.md): `GET /v1/ai/evaluation-testcase-results`
- [Get test case result by ID](https://developer.kustomer.com/api/ai/get-test-case-result-by-id.md): `GET /v1/ai/evaluation-testcase-results/{resultId}`

## Summaries

An AI summary is a short, AI-written overview of a conversation, a customer or a custom object, which Kustomer generates and keeps up to date so agents can catch up without reading the whole history. The API reads these summaries, optionally translated.

- [Get AI summary by resource ID](https://developer.kustomer.com/api/ai/get-ai-summary-by-resource-id.md): `GET /v1/ai/summaries/{resourceId}`
- [Batch get AI summaries by resource IDs](https://developer.kustomer.com/api/ai/batch-get-ai-summaries-by-resource-ids.md): `GET /v1/ai/summaries/batch`