> For the complete documentation index, see [llms.txt](https://docs.wem.io/platform/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.wem.io/platform/wemreference/data-types/convo-id.md).

# Convo ID

### Description

The AI agent conversation datatype stores a handle to a single conversation with an AI agent. The field does not contain the conversation itself: the messages, the provider used and the token usage are held by the runtime, and the field holds the reference that identifies which conversation it is.

A field of this type is linked to one specific AI agent when it is created in the Data Model. That link is what allows expressions on the field to be checked against the agent, and it makes clear in the Data Model which agent a conversation belongs to.

Conversations are created and used by the AI agent flowchart nodes, and displayed with the AI agent chatbox or AI agent voice chat components. Check the Agentic AI section for more information on agents, and the AI Functions for the functions available on a conversation field.

### Unknown

An unknown value can be written as `UnknownAiAgentConversation`

### Remarks

There is no function that returns the message text of a conversation. To show a conversation to a user, place an AI agent chatbox on an interaction; use its read-only mode when the conversation should be displayed but not continued.

`DateModified()` and `HasContent()` both ignore the initial system message. A conversation that has just been created therefore returns false on `HasContent()`, which makes it a reliable check for whether an exchange has actually started.

{% hint style="info" %}
Before version 5.2 a conversation was commonly held in a Text field containing the conversation id. Projects using that pattern keep working, and the field converts to this datatype when the project is republished.
{% endhint %}


---

# 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.wem.io/platform/wemreference/data-types/convo-id.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.