Tracing, evaluation and observability platform for LLM applications with dataset management and CI integration.
Workday built an internal agent developer platform on LangGraph for orchestration and LangSmith for tracing, observability and evals, running production AI agents on its own infrastructure. A four-person team delivered it under some of the strictest security, audit and data governance constraints in enterprise software, targeting agents in production by end-2026.
Dosu describes how it applies evaluation driven development (EDD) to make its LLM-powered engineering agent more reliable, using LangSmith to monitor and search agent activity at scale. The post frames reliability gains as directly reducing maintenance and support burden for the LangChain team.
LangChain announced general availability of LangSmith Bring Your Own Cloud (BYOC) on AWS, letting enterprises run a managed LangSmith deployment inside their own AWS account and VPC. Traces, datasets, experiments, prompts, agent deployments and sandbox data stay within the customer's cloud boundary, while LangChain handles monitoring, upgrades, scaling and cluster lifecycle management.
LangChain's LangSmith team outlines eval-driven development (EDD), an approach that builds agents while continuously measuring performance against a consistent metric set and hill-climbing toward an eval. The workflow starts with a short spec defining desired and forbidden behavior, judges each change through comparative experiments to catch regressions, and keeps evals running in CI and production so failures become new dataset examples.