What problem does it solve? Governing AI model traffic—controlling token costs, caching responses, filtering harmful content, and load balancing across backends—requires complex Azure API Management policy configuration that is error-prone when done manually. ## Core Features & Use Cases - AI Governance Policies: Apply token rate limits, semantic caching, token usage metrics, and content safety policies to Azure OpenAI and AI Foundry backends. - Backend Configuration: Add AI model backends with managed identity authentication, load balance across regions, and convert APIs into MCP tools with rate limiting. - Troubleshooting Guidance: Diagnose 401 auth failures, 429 token limit errors, cache misses, and content safety false positives with step-by-step fixes. - Use Case: You need to cut Azure OpenAI costs and enforce per-tenant token limits. Use this Skill to configure semantic caching (60-80% savings) and per-subscription token-limit policies on your APIM gateway. ## Quick Start Ask the agent to add an Azure OpenAI backend to your API Management instance and apply token limiting and semantic caching policies.
