Skip to main content
The Thread view renders traces as a chat-style conversation, showing the back-and-forth between users, assistants, and tools in chronological order. It is especially useful for conversational AI and multi-agent systems.
Thread view with message list on the left showing agent conversations, and message detail on the right showing system prompts, user context, and function calls

​
Reading the thread

The view is split into two panels:

​
Message list (left)

Lists all messages grouped by agent or conversation turn. Each entry shows:
  • Role (System, User, Assistant, Tool)
  • Preview of the message content
  • Agent name and message count when multiple agents are involved
Click any message to view its full content in the detail panel.

​
Message detail (right)

Shows the complete content of the selected message, including:
  • System prompts with full agent instructions
  • User messages with input context
  • Assistant responses with model output, function calls, and token usage
  • Tool results with returned data
  • Agent handoffs shown as visual indicators (e.g., customer_support -> technical_agent)

​
Multi-agent conversations

When a trace involves multiple agents, the Thread view groups messages by agent. The left panel shows each agent as a collapsible section with its message count. This makes it easy to follow how agents hand off conversations and what context each agent receives.

​
When to use

Use the Thread view to:
  • Read through conversational traces as a natural dialogue
  • Debug multi-agent handoffs and routing decisions
  • Review what system prompts and context each agent received
  • Inspect tool calls and their results in conversational context
  • Verify that agent responses match the expected behavior for given inputs