Clay runs millions of agent runs monthly with LangSmith online evaluators, not manual review
LangChain · x · 2026-09-10
Clay runs millions of agent runs per month, where manual review breaks down, so the company relies on LangSmith's online evaluators to monitor agent behavior automatically. It is also testing LangSmith's insights product for deeper visibility into agent performance, as explained by LangChain's Jeff Barg.
More from coding & agent
- Mollick: you can't be in the loop for long-running agents, but you can oversee it — emollick · 2026-09-10
- Ethan Mollick on steering long-running agents: when to instruct, queue or fork — emollick · 2026-09-10
- The mental model for LLM guardrails: a separate layer that distrusts the model — Careless_Sabfey_4906 · 2026-09-10
- Ethan Mollick: you're probably not steering your long-running coding agents enough — emollick · 2026-09-10
- AgentGrad: intervention-guided prompt optimization hits SOTA with 2.5x faster tuning — _akhaliq · 2026-09-10
- Claude embeds cyber controls in models vs Codex as a separate orchestratable model — HankYeomans · 2026-09-10