AI/ML
Azure SQL Hyperscale Vector Search Evaluation Guide
Azure SQL Hyperscale Vector Search at Billion-Row Scale: When It’s Good Enough for AI Retrieval
Frank Garofalo
Cloud Solutions Architect & Data Engineering leader at Microsoft. I build production AI, data, and home-lab systems — Azure, Fabric, Copilot, Proxmox/Ceph — and write about what actually works. New posts weekly.
AI/ML
Microsoft Copilot Usage-Based Billing Governance Guide
Microsoft Copilot’s Usage-Based Billing Model: What Finance and Platform Teams Need to Know
AI/ML
Durable Azure AI Agents with Governed Storage State
My practical pattern for durable agents on Azure: state belongs in storage, not in the prompt
Azure
Azure PostgreSQL Major Upgrade Planning for Platform Teams
Azure Database for PostgreSQL Elastic Clusters: What Major Version Upgrades in Preview Mean for Platform Teams
AI/ML
Enterprise AI Case Study Lessons for Decision Velocity
The best enterprise AI case studies aren’t about chat — they’re about decision velocity under uncertainty
AI/ML
Azure AI Foundry Hosted Agent Network Governance Guide
If your hosted agents can reach anything, you don’t have governance — you have hope
AI/ML
Enterprise Copilot Release Management for Teams
Publishing agents to Teams is the easy part — the real work starts with release management, identity, and blast-radius control
AI/ML
Microsoft Foundry Routines for Enterprise Agent Control
Foundry Routines could be the missing layer between clever demos and repeatable enterprise agents
Azure
Azure Cosmos DB Indexing Policies for AI Performance
Why Azure Cosmos DB Indexing Policies Still Decide AI App Performance
AI/ML
Guided Copilot in VS Code for Azure App Delivery
How Guided Copilot in VS Code Could Change the Azure App Build Loop
AI/ML
Local Inferencing Governance for Microsoft 365 Copilot
What Local Inferencing Means for Microsoft 365 Copilot Governance
Microsoft Fabric
The Skills Gap Myth: What Fabric, Databricks, and AI Copilots Actually Close
What Fabric, Databricks and AI copilots make easier, and what teams still need to validate across platform boundaries and government clouds.