Build Agent Architecture using AI Landing Zones
About this episode
The episode discusses building secure, scalable AI agents using Microsoft Azure and related technologies.
Build enterprise-ready AI agents that scale without sacrificing security or control using Microsoft Azure. Establish a shared Governance Hub to centralize model access, MCP catalogs, and policy enforcement, then give every agent a traceable identity, runtime protection, and data governance through Agent 365. Layer in Microsoft Fabric's Ontologies so your agents reason over real business context, not just raw data. Choose your runtime — no-code, hosted container, or custom — and deploy a production-grade environment in minutes using the AI Landing Zone accelerator. Matt McSpirit, Microsoft Azure Expert, joins Jeremy Chapman, Microsoft 365 Director, to share how to architect, govern, and scale a full agent mesh across the Microsoft stack. ► QUICK LINKS: 00:00 - Build secure AI agents 01:07 - Accelerate development, reduce risks 02:51 - Model Gateway + MCP Gateway 03:24 - Agent 365 Unified Control Plane 03:56 - Azure Policy + Azure Monitor 04:27 - Intelligent data platform 05:37 - OneLake in Microsoft Fabric 06:39 - Microsoft Purview data governance 07:13 - Fabric IQ with Ontologies 07:51 - Landing Zones 09:23 - Three Hosting Runtimes 11:06 - AI Landing Zone Accelerator 13:16…
More episodes of Microsoft Mechanics Podcast
- Build your first Power App from data in seconds
- Microsoft Entra Suite hands-on tour of identity and network access protections
- New agentic platform in Dynamics 365 for Sales and Service
- Tokenomics | The new AI currency & your options explained
- Deploy Windows updates to counter AI-discovered threats
- Zero Trust security for AI agents
Explore listener stats, chart rankings, contacts and more on the Microsoft Mechanics Podcast podcast page.