Evaluation

LangSmith Engine v2 does not just watch your agent. It red-teams it, flags inefficient trajectories, and validates its own fixes before handing you a pull request. Observability is no longer a dashboard; it is an operator.

The prompt stopped being the hard part. What makes an agent survive tool failures, context drift, and non-deterministic outputs is the open-source harness around it, and a solo operator can now self-host the whole thing.

Reasoning models got good because verification works: verifiable rewards, consensus, and learned scoring. Agentic workflows skip it. Dan Luu's experiment shows agents cannot check their own work even when told how.

ClickHouse bought Langfuse and Gartner minted a new category. The agent stack's trust layer is consolidating around observability and evaluation, and eval is still the under-built half.