Artificial Intelligence
Foundry Local 1.1: Live Transcription, Embeddings, and Responses API
Foundry Local 1.1 adds live transcription, embeddings, Responses API, WebGPU plugin, and download cancellation.
Least privilege AI agents: A new azd template from Curity and Microsoft
If you ever built an AI agent demo, you probably had this moment. Everything works: the agent interprets natural language, calls the right tools, and returns the right data. Then you start designing for the real users of the app. You think about data boundaries: what if someone tries to get data they're not supposed to see? For example, imagine a customer support app where users can say "give me a markdown report on the last three months of stock transactions and the value of my portfolio." Then an agent does the work. First, you need to design for security so the agent doesn't commingle data from separate cus...
Scalable AI with Azure Cosmos DB: Bringing Generative AI to Enterprise Scale with Super Insight by AVASOFT
Azure Cosmos DB enables scalable AI-driven document processing, addressing one of the biggest barriers to operational scale in today’s enterprise AI landscape. Organizations continue to manage massive volumes of structured and unstructured content—contracts, regulatory filings, operational records, images, and field documentation—yet many workflows remain fragmented, manual, and slow. Every month, the Scalable AI in Action with Azure Cosmos DB series brings the community together with Microsoft partners who are building real, production AI systems — not slides, not demos built for the occasion, but live walkth...
SQL query generation from natural language
Evaluating AI agents for NL-to-SQL generation across Azure Databricks AI/BI Genie, GitHub Copilot CLI, and Microsoft Agent Framework. We achieved ~75% accuracy with schema documentation and runtime validation, while discovering that business logic errors represent a fundamental limitation requiring domain expertise.
Durable Workflows in the Microsoft Agent Framework
Build durable AI agent workflows with the Microsoft Agent Framework. Start with in-process console apps, add durability with the Durable Task runtime, scale with parallel AI agents, and host on Azure Functions for serverless execution.
Announcing the Public Preview of Azure Cosmos DB Shell: Open-Source Power Meets AI-Driven Database Automation
 Today, we're thrilled to announce the public preview of Azure Cosmos DB Shell – a powerful, open-source command-line interface that revolutionizes how developers interact with their Azure Cosmos DB databases. With integrated Model Context Protocol (MCP) server support, native agentic capabilities, and bash-like syntax, Azure Cosmos DB Shell transforms database management into an intelligent, developer-friendly experience. From Friction to Flow: Why Cosmos DB Shell, and Why Open Source If you have ever bounced between a portal tab, an SDK sample, and a half-finished script just to answer one database quest...
Microsoft Agent Framework – Building Blocks for AI Part 3
Build intelligent AI agents in .NET with the Microsoft Agent Framework. Learn how to create agents with tools, multi-turn conversations, memory, and graph-based workflows that bring together the building blocks from Parts 1 and 2.
Introducing langchain-azure-cosmosdb: Build Agentic Apps and RAG with One Database
Build AI Agents and RAG Applications with the New LangChain + LangGraph Connector for Azure Cosmos DB Building AI agents and RAG applications today means stitching together half a dozen services, a vector database, a chat history store, a checkpointer for agent state, a semantic cache, a long-term memory layer. Each adds operational overhead, latency, and technical debt. langchain-azure-cosmosdb collapses that stack. It's a Python LangChain and LangGraph connector that turns Azure Cosmos DB for NoSQL into the single persistence layer for all of your agentic app scenarios. Azure Cosmos DB for NoSQL natively...
Building an AI-Powered Conference App with .NET’s Composable AI Stack
Learn how we built ConferencePulse, an AI-powered conference assistant, using .NET's composable AI stack including Microsoft.Extensions.AI, DataIngestion, VectorData, Model Context Protocol, and Microsoft Agent Framework.
Governing MCP tool calls in .NET with the Agent Governance Toolkit
Learn how to govern MCP tool calls in .NET with the Agent Governance Toolkit—policy-based access control, security scanning, and response sanitization to reduce risk in AI agent systems.