@LangChain: .@AdamRLucek on how we use traces to build evals for production agents.
Summary
Adam Łucek discusses how LangChain uses trace data to build evaluations for production agents.
View Cached Full Text
Cached at: 05/27/26, 12:59 AM
.@AdamRLucek on how we use traces to build evals for production agents.
Adam Łucek (@AdamRLucek): Trace data is literally worth its weight in gold these days, if you know what to do with it! As has been established, creating effective agents requires shipping early, observing behavior, and iterating quickly. At the core of this are your agent traces capturing exact inputs,
Similar Articles
@LangChain: Great thread from @AdamRLucek on LangSmith Engine!
Adam Łucek discusses LangSmith Engine, an agent for automating agent development using trace data.
@LangChain: We built a tracing plugin that turns every @cursor_ai agent session into a structured trace in LangSmith: the model run…
LangChain released a tracing plugin that converts every Cursor AI agent session into a structured trace in LangSmith, including model runs, tool calls, and nested subagent work, part of a series comparing coding-agent traces.
@LangChain: Improving agents The old way: Manually reading traces, looking for patterns, writing evals, and creating fixes. The bet…
This tweet contrasts the old manual approach to improving AI agents with a new automated method using LangSmith Engine, which cycles through tracing, eval, and fixes.
@LangChain: You can use the LangSmith CLI to pull your flagged traces, classify each one by issue type, and build an eval dataset w…
This article explains how to use the LangSmith CLI to manage traces and build evaluation datasets through a quick tutorial.
@LangChain: LangSmith lets @MorningstarInc trace every agent decision in one place. Senior Software Engineer Matt Trivett on what d…
LangSmith enables centralized tracing of agent decisions, improving debugging efficiency as demonstrated by Morningstar Inc's senior software engineer.