APIM Policy Patterns for AI Governance: Part 1 – Rate Limits, Token Quotas & Observability
How I would use Azure API Management to control AI request rates and token consumption, attribute usage, emit useful telemetry and handle backend throttling.
Observability
HolmesGPT + Azure AI Foundry: A Quick Kubernetes Troubleshooting Demo
A quick HolmesGPT demo using Azure AI Foundry, Azure OpenAI and a local kind cluster. Deploy a deliberately broken Kubernetes pod, ask HolmesGPT to investigate it, and see how it identifies the root cause from the pod spec, scheduler events and cluster state.