Ashwin deshpande·2d agoRetrieval Eval SuiteWhy a Retrieval Eval Suite Can Keep Passing Long After It Stopped Measuring AnythingA response icon1A response icon1
Jatinkumar Parmar·4d agoHow WAS Evals Improve AI ModelsAI models have changed a great deal over the years. Across successive generations, they’ve become better at taking requests of all kinds…
Bhrugu Giri·Oct 28A Better Talking MonkeyWhy context, not the model, decides whether conversational AI can be trusted
Shrikant Lambe·Oct 23Evals for the Semantic Layer Under Your AI Agent : Test the Metric Before the ModelPart 3 of 6: Building Agentic Evals on Snowflake. Why the semantic view is a contract, how to test governed metrics directly before any…
tapas mohanty·Oct 21Your Coding Agent Passed the Tests. Did It Break the Behavior?Coding agents are getting good at changing code.A response icon1A response icon1
Paige Anderson·Oct 17Half of the PM openings Lenny shared ask for eval experience, and the skill is a personal test set…On September 24, 2026, Laura Entis published “Why Evals Are So Hot Right Now” in Every’s Context Window column, and the hiring number…
Shrikant Lambe·Oct 10A Wrong Number Looks Exactly Like a Right One: Why Your AI Agent Needs Evals Before LaunchPart 1 of 6: Building Agentic Evals on Snowflake. Why evals come first, the architecture that makes them work, and a process you can start…A response icon2A response icon2
InAI Safety & EthicsbyNeha·Oct 1How SWE-bench Evolved Over Time and Why?Software engineering benchmarks evolved as coding agents became more capable
