aiqbench takeAI Products

Trajectories are a read-only, chronological view over LangSmith traces, aimed at making long-running agent sessions easier to follow. The practical value is for teams debugging multi-turn agents with tool calls and subagent handoffs, where the full execution tree is too granular to see the agent's path. Readers should note that the feature depends on traces from supported frameworks and SDKs, and that its usefulness will depend on how well it surfaces the decisions that matter in real failures.

Source coveringLangChain Blog

Trajectories now in LangSmith: A readable view of every agent session

LangChain BlogSeptember 24, 20265 min read

Trajectories in LangSmith provide a conversational view of an agent session. Trajectories make trace data easy to navigate and speed up debugging for long-running agents.

Debugging agents often starts with a simple question: what did the agent actually do? For short, single-turn workflows, the answer is usually easy to find. For longer-running agents, it gets harder fast. A single session can span many user turns, tool calls, retries, and subagent handoffs. The full trace is still the right place to inspect execution details, but it can be too much detail when you’re trying to understand the path the agent took. Today, we’re launching Trajectories in LangSmith, a chronological, conversational view of an agent session. A Trajectory aggregates messages…

Excerpt shown under the publisher's RSS terms · 93 words · full text and figures are on the publisher's site

Read at LangChain Blog ↗Ask about this article