- Microsoft Fabric IQ: The Foundation Data Architects Need to Know
- Fabric Data Agent: Structured and Unstructured Data
- Effective Team Structures for LLM Application Success
- Deployment Strategies: Optimizing Azure AI Foundry Models for Cost, Performance, and Scale
- AI and SQL from “Ground to Cloud”
- Choose Models from Azure AI Foundry: A Component Guide
- Azure AI Foundry and VS Code Integration Overview
- Leveraging Hubs and Projects in Azure AI Foundry
- Azure AI Foundry
Microsoft Fabric IQ: The Foundation Data Architects Need to Know
Microsoft Fabric IQ reached general availability at Build 2026, turning what was a preview into a platform architects now need to design around. This breakdown covers Fabric IQ’s five components: Ontology, Graph, Data Agent, Operations Agent, and Semantic Model. How they reinforce one another, and the governance decisions data architects need to make now that…
Fabric Data Agent: Structured and Unstructured Data
Explore Microsoft Fabric Data Agent’s AI-powered natural language queries across lakehouses, warehouses, semantic models, and Azure AI Search indexes.
Effective Team Structures for LLM Application Success
The development of large language model applications has become a critical capability for organizations looking to harness AI’s transformative potential. Yet many teams struggle with lengthy development cycles that seem to drag on indefinitely. The secret to breakthrough productivity isn’t just better tools or bigger budgets—it’s how you structure your development teams. Understanding the LLM…
Deployment Strategies: Optimizing Azure AI Foundry Models for Cost, Performance, and Scale
Don’t let AI become a cost center. This guide breaks down Azure AI Foundry’s three deployment types: Standard, Provisioned, and Batch, and how to strategically combine them based on workload urgency, volume, and processing timelines. From batch processing’s 50% cost savings to reserved capacity for mission-critical apps, learn how to build a deployment mix that…
AI and SQL from “Ground to Cloud”
SQL Server 2025 introduces a feature that enables the creation of external model objects, encapsulating the location, authentication method of the AI model inference endpoint. This capability allows you to integrate with AI models deployed with Azure OpenAI through Azure AI Foundry, empowering users to develop cloud-based AI models and leverage them within on-premises SQL…
Choose Models from Azure AI Foundry: A Component Guide
I had a great conversation with my son the other day on OpenAI and how the space has evolved rapidly over a very short period of time. I wanted to put together a “basics” overview of how we solve a problem space with AI by selecting the right model, and ensuring it scales.
Azure AI Foundry and VS Code Integration Overview
The Azure AI Foundry extension for VS Code brings code templates, a model playground, and seamless integration with your existing extensions directly into the editor. A quick look at how it streamlines AI development, and how Semantic Kernel lets you swap in new models as they drop without rewriting your codebase, hooks, or plugins.
Leveraging Hubs and Projects in Azure AI Foundry
Azure AI Foundry offers a structured and efficient framework for managing AI resources and development efforts by leveraging the concepts of Hubs and Projects. Hubs: Centralized Resource Management Hubs act as top-level containers that simplify the management of shared resources across multiple AI initiatives. This centralized approach enhances collaboration and resource allocation, ensuring that various…
Azure AI Foundry
A Multi-Service Resource Azure AI Foundry Services represent a robust suite of tools and solutions designed to empower businesses with advanced artificial intelligence capabilities. These services provide organizations with the ability to integrate machine learning, cognitive services, and data analytics at scale, enabling transformative insights and operational efficiency. By leveraging Microsoft’s Azure platform, AI Foundry…
Data, Analytics, ML, AI 