Agent Evals

12 posts · 4 sources

HexBlog4d

Hill climbing to glory: using evals to improve AI error rate by 7x

AI EngineerYouTube1w

Your LLM Judge Is a Confident Liar: Building Better Verifiers — Browserbase

LangChainYouTube3w

Building a Harness with Jev

LangChainYouTube4w

Catch Agent Regressions Before You Ship: Evals for Managed Deep Agents

GleanBlog26 Aug

Glean Agents can now work independently, build faster, and stay governed at scale

HexBlog4 Aug

Introducing Evals

HexBlog29 Jul

Trust used to be implied

HexBlog9 Jun

We had to build new evals for Fable

HexBlog22 May

How we built a lab to evaluate data agents

HexBlog30 Apr

We cloned our visualization team — They live inside a subagent now

HexBlog22 Oct

Improving the Notebook Agent: Error Clustering

HexBlog2 Oct

Lessons from Ramp: Running AI-powered data teams