{"conference":"ai-engineer-melbourne-2026","query":"evaluating production agents","kind":"sessions","count":10,"results":[{"id":"924ae0be-d390-45af-b60b-ff7c0120fac0","score":0.7367609326771108,"title":"Our AI Hallucinated in Production: How We Fixed It With Evals"},{"id":"0e7cddbf-7e05-47b1-8ced-d63ca6736081","score":0.7322416192269342,"title":"Stop vibing your agents to production: applying ML discipline to agent development"},{"id":"8c29bef6-e037-47ff-a130-642da3ec44a5","score":0.7130456825465932,"title":"Observability and Evaluation for LLM Apps and Agentic AI with Langfuse"},{"id":"665cc753-e86b-4d2a-bd73-44b618481ef8","score":0.7126360340570175,"title":"When a Small Language Model Beat Our LLM in Production"},{"id":"f45cb6cc-51d1-49a4-9842-82d370886d8e","score":0.7067509985874967,"title":"Engineering for the Agentic Web When 50% of Your Traffic is Robots"},{"id":"8699baf3-d7cd-4065-9d4c-e22ab1a36f35","score":0.7036529375700155,"title":"Your Agents Pass Every Benchmark—Then Memory Breaks Them in Production"},{"id":"cc043bba-6d57-4082-ae3c-75045603c32b","score":0.6988395275064505,"title":"Craft in the Time of Agents"},{"id":"c9667f3a-9cad-4df9-9ca5-2facc06e8207","score":0.6953273532137306,"title":"Agent Observability: Monitoring and Understanding Agents at Internet Scale"},{"id":"c4331a08-d65f-49a4-a937-f73d60a4afa6","score":0.6927946454414348,"title":"Agentic Self-Healing in Production"},{"id":"0716c074-bc59-47ba-a2b2-7fd916c0cad5","score":0.6884067506473522,"title":"Spec driven AI development - A Real World Perspective"}]}