> For the complete documentation index, see [llms.txt](https://developerdocs.instructure.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://developerdocs.instructure.com/services/canvas/resources/ai_conversations.md).

# AI Conversations

API for managing conversations with AI Experiences.

## [Show conversation](#method.ai_conversations.show) <a href="#method.ai_conversations.show" id="method.ai_conversations.show"></a>

[AiConversationsController#show](https://github.com/instructure/canvas-lms/blob/master/app/controllers/ai_conversations_controller.rb)

#### `GET /api/v1/courses/:course_id/ai_experiences/:ai_experience_id/conversations/:id`

**Scope:** `url:GET|/api/v1/courses/:course_id/ai_experiences/:ai_experience_id/conversations/:id`

Get a specific conversation by ID (for teachers viewing student conversations)

## [Get active conversation](#method.ai_conversations.active_conversation) <a href="#method.ai_conversations.active_conversation" id="method.ai_conversations.active_conversation"></a>

[AiConversationsController#active\_conversation](https://github.com/instructure/canvas-lms/blob/master/app/controllers/ai_conversations_controller.rb)

#### `GET /api/v1/courses/:course_id/ai_experiences/:ai_experience_id/conversations`

**Scope:** `url:GET|/api/v1/courses/:course_id/ai_experiences/:ai_experience_id/conversations`

Get the active conversation for the current user and AI experience

## [Create AI conversation](#method.ai_conversations.create) <a href="#method.ai_conversations.create" id="method.ai_conversations.create"></a>

[AiConversationsController#create](https://github.com/instructure/canvas-lms/blob/master/app/controllers/ai_conversations_controller.rb)

#### `POST /api/v1/courses/:course_id/ai_experiences/:ai_experience_id/conversations`

**Scope:** `url:POST|/api/v1/courses/:course_id/ai_experiences/:ai_experience_id/conversations`

Initialize a new conversation with the AI experience

## [Post message to conversation](#method.ai_conversations.post_message) <a href="#method.ai_conversations.post_message" id="method.ai_conversations.post_message"></a>

[AiConversationsController#post\_message](https://github.com/instructure/canvas-lms/blob/master/app/controllers/ai_conversations_controller.rb)

#### `POST /api/v1/courses/:course_id/ai_experiences/:ai_experience_id/conversations/:id/messages`

**Scope:** `url:POST|/api/v1/courses/:course_id/ai_experiences/:ai_experience_id/conversations/:id/messages`

Send a message to an existing conversation and get the AI response

#### Request Parameters:

| Parameter | Type              | Description                          |
| --------- | ----------------- | ------------------------------------ |
| `message` | Required `string` | The user's message to send to the AI |

## [Delete AI conversation](#method.ai_conversations.destroy) <a href="#method.ai_conversations.destroy" id="method.ai_conversations.destroy"></a>

[AiConversationsController#destroy](https://github.com/instructure/canvas-lms/blob/master/app/controllers/ai_conversations_controller.rb)

#### `DELETE /api/v1/courses/:course_id/ai_experiences/:ai_experience_id/conversations/:id`

**Scope:** `url:DELETE|/api/v1/courses/:course_id/ai_experiences/:ai_experience_id/conversations/:id`

End the current conversation session

## [Get conversation evaluation](#method.ai_conversations.evaluation) <a href="#method.ai_conversations.evaluation" id="method.ai_conversations.evaluation"></a>

[AiConversationsController#evaluation](https://github.com/instructure/canvas-lms/blob/master/app/controllers/ai_conversations_controller.rb)

#### `GET /api/v1/courses/:course_id/ai_experiences/:ai_experience_id/conversations/:id/evaluation`

**Scope:** `url:GET|/api/v1/courses/:course_id/ai_experiences/:ai_experience_id/conversations/:id/evaluation`

Fetch the latest stored evaluation for a conversation from the llm-conversation service. Reads only — does not run the LLM and is not rate-limited. `evaluation` is null when none has been generated yet (llma returns 200 + null, never 404, so this is distinguishable from an outage). `stale` is true when the AI experience was edited after the stored evaluation was generated.

## [Generate conversation evaluation](#method.ai_conversations.create_evaluation) <a href="#method.ai_conversations.create_evaluation" id="method.ai_conversations.create_evaluation"></a>

[AiConversationsController#create\_evaluation](https://github.com/instructure/canvas-lms/blob/master/app/controllers/ai_conversations_controller.rb)

#### `POST /api/v1/courses/:course_id/ai_experiences/:ai_experience_id/conversations/:id/evaluation`

**Scope:** `url:POST|/api/v1/courses/:course_id/ai_experiences/:ai_experience_id/conversations/:id/evaluation`

Run the LLM to (re)generate an evaluation for a conversation and persist it in the llm-conversation service. Rate-limited. Also the Reset path — a fresh run replaces any prior stored evaluation.

## [Create feedback on a conversation message](#method.ai_conversations.create_feedback) <a href="#method.ai_conversations.create_feedback" id="method.ai_conversations.create_feedback"></a>

[AiConversationsController#create\_feedback](https://github.com/instructure/canvas-lms/blob/master/app/controllers/ai_conversations_controller.rb)

#### `POST /api/v1/courses/:course_id/ai_experiences/:ai_experience_id/conversations/:id/messages/:message_id/feedback`

**Scope:** `url:POST|/api/v1/courses/:course_id/ai_experiences/:ai_experience_id/conversations/:id/messages/:message_id/feedback`

Submit a like or dislike vote on an AI-generated message.

Ownership: load\_conversation gates this action — only the conversation owner or a course manager reaches here. Sub-resource (message\_id within the conversation) scoping is delegated to llma.

#### Request Parameters:

| Parameter          | Type              | Description                   |
| ------------------ | ----------------- | ----------------------------- |
| `vote`             | Required `string` | "liked" or "disliked"         |
| `message_id`       | Required `string` | llm-conversation message UUID |
| `feedback_message` | `string`          | optional text for dislike     |

## [Delete feedback on a conversation message](#method.ai_conversations.delete_feedback) <a href="#method.ai_conversations.delete_feedback" id="method.ai_conversations.delete_feedback"></a>

[AiConversationsController#delete\_feedback](https://github.com/instructure/canvas-lms/blob/master/app/controllers/ai_conversations_controller.rb)

#### `DELETE /api/v1/courses/:course_id/ai_experiences/:ai_experience_id/conversations/:id/messages/:message_id/feedback/:feedback_id`

**Scope:** `url:DELETE|/api/v1/courses/:course_id/ai_experiences/:ai_experience_id/conversations/:id/messages/:message_id/feedback/:feedback_id`

Remove a previously submitted vote (toggling off like/dislike).

Ownership: load\_conversation gates this action — only the conversation owner or a course manager reaches here. Sub-resource (message\_id, feedback\_id within the conversation) scoping is delegated to llma.

***

This documentation is generated directly from the Canvas LMS source code, available [on Github](https://github.com/instructure/canvas-lms).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://developerdocs.instructure.com/services/canvas/resources/ai_conversations.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.