Your LLM App Returned 200 OK. It Was Still Wrong. — Marina Petzel, Datadog
Datadog's Marina Petzel on LLM observability: catching the silent failures that still return 200 OK and wiring tracing and evals into production monitoring.
More in Infra
About this video
AI Engineer · October 3, 2026 · 18:01
observabilityLLMOps
Datadogtalk
Open on YouTube ↗More in Infra
More Infra
When Running Your Own AI Models Beats Paying for APIs - Steven Latré, imec
Serving World Models: Latency vs Throughput with NVIDIA Cosmos 3 Super on Nebius | Cosmos Labs
Why Humans Can't Keep Up With AI-Written Code - Tariq Shaukat, Sonar
