From the source
From the source
Laminar's trace viewer adds a transcript view for agent loops
Laminar introduces a transcript view for agent traces that displays the agent's loop—LLM calls and tool calls in sequence—alongside a timeline strip and collapsible subagent cards, designed to make debugging agent runs easier than traditional span-tree views.
From the source
At the core, an agent is a simple while loop: LLM call, tool call, LLM call, tool call, until a final answer. Complexity shows up when a tool call spawns another agent, but the spine of any trace is that loop, in order. That sequence is what we mean by transcript. The view exposes the loop directly, with the model's reasoning surfaced right next to the tool call it produced.
laminar.sh
