> 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/wemmodeler/agentic-ai/ai-user-interaction.md).
# AI User Interaction
## User Interaction with AI Agents
The **AI Agent Chatbox** component can be found in the Miscellaneous section of the Interaction Template Editor toolbar and allows users to communicate directly with an AI agent in real time.
The Chatbox component provides a user-friendly interface where users can input queries, receive responses, and engage in conversations with AI agents.
#### Properties
**General**
| Property | Description |
| --------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Conversation ID | The conversation to display. This can be either an **AI agent conversation** field or a text field containing a conversation ID. The chatbox will show the message history of this conversation and allow the user to continue it. |
| Readonly mode | When enabled, the chatbox displays the conversation in real time but disables the input — the user can observe what is happening but cannot send messages or otherwise influence the interaction. Useful for monitoring screens, supervisor views, or playback of historical conversations. |
**Behavior**
| Property | Description |
| ---------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Show function and tool calls | When enabled, the chatbox surfaces function calls and hosted tool invocations (File search, Web search, Code interpreter) made by the agent. Useful during development and debugging to see exactly what the agent is doing. For end users, leaving this off keeps the conversation clean and on-topic. |
| Show reasoning | When enabled, the chatbox shows the agent's reasoning steps for models that support reasoning (such as OpenAI's reasoning models or Anthropic models with thinking enabled). Has no effect on non-reasoning models. |
| Show system messages | When enabled, system messages, including the initial instruction sent to the agent and any internal status messages, are visible in the chatbox. Typically left off in production, since users don't usually need to see these. |
**Appearance**
| Property | Description |
| ---------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Display mode | Controls how the chatbox is positioned on the page. **Normal flow** renders the chatbox inline as part of the page layout. **Fixed** anchors the chatbox to a specific screen position regardless of scroll, which is useful for persistent helper-style chatbots that should stay visible while the user navigates the rest of the page. |
| Input placeholder text | The hint text shown in the message input field before the user types anything (e.g. "Ask me anything…" or "Describe your request"). Helps set expectations about what the chatbox is for. |
| Show timestamps | When enabled, each message is annotated with the date and time it was sent. Useful for longer conversations or for audit-friendly UIs. |
| Height | The vertical size of the chatbox in pixels. Defaults to 500. Adjust based on the available space in your template, taller for dedicated chat pages, shorter for embedded helpers. |
---
# 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:
```
GET https://docs.wem.io/platform/wemmodeler/agentic-ai/ai-user-interaction.md?ask=
```
The question should be specific, self-contained, and written in natural language.
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.