> For the complete documentation index, see [llms.txt](https://docs.interactive.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.interactive.ai/improve/annotations/comments-on-objects.md).

# Comments on Objects

Comments allow team members to leave notes, questions, and feedback directly on objects within InteractiveAI Platform.

### Why Comments Matter

Scores capture structured evaluations, but not every observation fits neatly into a numeric or categorical value. Comments fill that gap by providing a space for unstructured feedback. A reviewer might notice that a trace handled an edge case particularly well, or that a prompt version needs refinement for a specific use case. Without comments, this context gets lost or not captured at all.

Comments also create a lightweight audit trail. When you revisit a trace weeks later, comments from teammates explain why it was flagged, what was tried, or what conclusions were reached. This institutional knowledge stays attached to the object itself rather than scattered across external tools.

***

### Supported Object Types

InteractiveAI supports commenting on the following:

**Traces**

Add comments to complete execution flows when you want to flag interesting behavior, note edge cases worth investigating, or leave context for teammates reviewing the same trace later.

<div data-with-frame="true"><figure><img src="/files/9FfVFsZyDQc3wb5bYmZ9" alt=""><figcaption></figcaption></figure></div>

**Sessions**

Leave notes on user interaction patterns across multiple traces. Session-level comments help document recurring behaviors or patterns that emerge over time.

<div data-with-frame="true"><figure><img src="/files/lLTfKGUZyLZQ83s3n2UJ" alt=""><figcaption></figcaption></figure></div>

**Prompts**

Collaborate on prompt versions by commenting directly on the prompt detail view. Use comments to discuss proposed changes, explain why a version was created, or coordinate with teammates on prompt improvements.

<div data-with-frame="true"><figure><img src="/files/k5rO2leYOdZqKqgxLOoj" alt=""><figcaption></figcaption></figure></div>


---

# 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://docs.interactive.ai/improve/annotations/comments-on-objects.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.