Ramshaiqbal·4d agoVibe Checks Don’t Scale: A Visual Guide to Evals for AI AgentsHow to know your last prompt change actually made things better: aligned LLM judges, the 90% agreement trap, and scoring the path, not just…
InLevel Up CodingbyDr. Varshita Sher·6d agoCreating Custom (Code-Based) Agent Evaluators in Microsoft Foundry with PythonBuild, register, and debug an evaluator using the Foundry SDK. Plus some common runtime errors discussed.A response icon1A response icon1
Deepan Kumar·Oct 29We Gave Our AI Agent 13 Safety Checks. The Only Real One Guarded the Wrong Door.We thought 13 gates guarded production. Twelve were just instructions — and the only real one ran on 0.9% of attempts.
In99P LabsbyNithin Santhanam·Oct 26What AGNTCon + MCPCon 2026 Showed Us About the Architecture of Reliable Agentic SystemsBy Nithin Santhanam and Luka Brkljacic
Indata from the trenchesbyAdel Hassen·Oct 22Agent evaluation: What to measure, how, and whenThe key to shipping agents with confidenceA response icon1A response icon1
Kunal Khanvilkar·Oct 21Why AI Agents Repeat Their Mistakes, and the Feedback Loop That Fixes ItBeyond prompt engineering: the architecture of self-improving agents, from failure analysis to evaluation, promotion and rollback, with a…
InTowards AIbyRick Hightower·Oct 19LangFuse IX: One Trace Tells You What Happened. Langfuse Metrics Tell You What It Costs.Part 9: Metrics are not a second instrumentation project. They are sums and filters over the traces you already emit, and cost applies only…
InAI Tools Digestbybytebantz·Oct 14Testing LangChain & LangGraph Agents: Comprehensive GuideLearn to test LangChain and LangGraph agents with pytest: fake models, integration tests, VCR replay, trajectory evals and LLM-as-judge.
InWorkday Technology BlogbyWorkday Technology Writer·Oct 12Two AIs Agreeing Doesn’t Make Them RightBy Jason Vantomme and Peter Hogan, Workday AI Platform
