
The AI Gateway in Azure API Management: A Control Plane for Enterprise AI
One control plane for enterprise AI — how APIM's AI gateway gives security, network, and infrastructure teams governance over models, MCP tools, agents.

Lead Solutions Architect · Azure, AI, .NET
I build enterprise AI systems in insurance: multi-agent orchestration, RAG pipelines and human-in-the-loop workflows on Azure. I write them up here, with the source.

One control plane for enterprise AI — how APIM's AI gateway gives security, network, and infrastructure teams governance over models, MCP tools, agents.

The governance case for keyless Azure: why shared keys are a liability, how managed identity plus RBAC fixes it, and how teams enforce it.
A five-gate method for picking enterprise AI use cases and measuring AI ROI in a way finance will accept and delivery can instrument, with a claims example.
Start here. A guided index to 40 chapters on building production multi-agent systems with Microsoft Agent Framework, in Python and C#, against one open-source e-commerce platform.
How a production MCP server signs into Microsoft 365 with real SSO: public client + PKCE, delegated permissions, On-Behalf-Of, and 85 Graph tools kept safe.
Azure has two features named Groundedness — a runtime detection API that blocks ungrounded answers, and an offline evaluator that scores them in CI.
How to compose PII redaction (Presidio), Azure AI Content Safety, and NeMo Guardrails as layered middleware around a Microsoft Agent Framework agent.
What Azure's Prompt Shields and Spotlighting actually block against jailbreaks and prompt injection — and the gap: they don't fire on agent tool calls.
A multi-agent e-commerce platform in Python and .NET: orchestrator plus five specialists over A2A, with MCP tools, pgvector retrieval and OpenTelemetry throughout. The companion repo for the MAF series.
A framework-free reference for AI engineering fundamentals: prompting, evaluation, retrieval and agent design, without tying any of it to one SDK.