Chat and Conversations

A published Agent provides a full chat page; the preview on the right side of the editor is for build-time debugging. A conversation is created when the first message is sent and stores variables, message count, and Token usage.

Start a Conversation

1. Open the Agent from Apps and select Chat or Public Page.
2. If the Agent defines required variables, complete the variable form first.
3. Enter your message. Enter sends it; Shift+Enter starts a new line.
4. If attachments are enabled, you can attach files and images; the count and size per message are determined by the Agent configuration.

Understand a Reply

A reply may consist of the following parts:

• Body: Displayed in streaming increments.
• Reasoning: Shown only when the model provides it and the Agent does not hide it.
• Referenced documents: The chunks, document names, and relevance returned by RAG.
• Tool calls: Parameters, results, logs, and artifacts; details can be hidden by the Agent.
• Media results: Images or videos rendered directly into the assistant's message body.
• Message actions: Copy, version, Token, speed, and more; can be hidden by the Agent.

Stop, Edit, and Regenerate

• Select Stop during streaming. The message status is recorded as manually stopped.
• Editing a historical user message creates a new branch from that message and streams a new reply.
• Regenerating an assistant message creates a new version. Switching versions only changes the active branch; it never deletes older versions.
• Deleting a message also handles its downstream branches; deleting a conversation permanently deletes all of its messages.

Manage Conversations

The conversation drawer lets you select, rename, and delete your own conversations. Titles are up to 200 characters. The app's Logs page shows conversations by time and search term, and displays variables, model, Token, response time, reasoning, and knowledge sources.

Related: Streaming events, Conversations API.