Browse All Artificial Intelligence Content (1090)

Freddy Chiu demonstrates how to profile and tune agentic AI applications on Intel-powered Windows PCs, focusing on end-to-end performance across CPU, GPU, and NPU. The session shows how to collect telemetry, identify bottlenecks, and apply practical optimization techniques to improve responsiveness and power efficiency.

davidwright, Arnaud Lheureux, and Suzanne Daniels explain why architecture and governance frameworks only help when they actively change delivery decisions. Using Git-Ape as the example, they show how to turn Azure Well-Architected, Azure Policy (including NIST mappings), and CAF guidance into repeatable repo-driven assessments with prioritized findings tied to code and policy.

Allison announces that Copilot Pro, Pro+, and Max subscribers can use “Fix with Copilot” to automatically investigate and propose fixes for failing GitHub Actions jobs, pushing changes to a branch and tagging the developer for review.

Allison announces a public preview REST API that lets Copilot Pro, Pro+, and Max users start and track Copilot cloud agent tasks programmatically, enabling teams to integrate agent-driven code changes into scripts and internal tooling.

Microsoft AI Red Team updates its agentic AI failure-mode taxonomy based on a year of red team engagements, adding seven new categories and translating real-world attack patterns into practical mitigations teams can apply to deployed agentic systems.

Allison announces new GitHub Copilot capabilities: support for one-million-token context windows and configurable reasoning levels, plus guidance on how these choices affect AI credit consumption across VS Code, Copilot CLI, and the Copilot app.

tinotereshko rounds up the Build 2026 announcements for Microsoft Fabric Data Warehouse, covering GPU-based query acceleration, configurable data retention and time travel, SQL editor upgrades (including inline Copilot chat), and new T-SQL capabilities. The post also highlights DevOps-focused features like REST APIs and Git/DacFx-based schema deployments for the SQL analytics endpoint.

WillT announces the general availability of Microsoft Fabric Operations agent, describing how it uses LLM-driven rule generation plus Real-Time Intelligence monitoring to detect issues, ask clarifying questions, and (with approval) run remediation actions like pipelines, notebooks, UDFs, and Power Automate workflows, with tracing and governance built in.

Pierce Boggan and Joshua Spicer share how the VS Code team moved from monthly to weekly releases by tightening review and testing workflows, automating triage at scale, and using agent-driven sessions that turn conversations into pull requests while keeping quality high with 100+ commits landing daily.

Julia Kasper, Harald Kirschner, Burke Holland, Kent Dodds, Christian Reddington, and Pierce Boggan share practical patterns for orchestrating multiple agents in VS Code, focusing on how to split work across local, background, and cloud surfaces and how to keep quality under control as agent count grows.

Michael Chiang walks through using Ollama to run open models locally and in the cloud, and how to wire those models into real applications. The session also demonstrates setting up Copilot CLI and connecting an agent to tools like web search and vision, with a focus on hybrid patterns and privacy.

Microsoft Developer’s Data Exposed episode shows how to build a data-powered application using Rayfin with a Microsoft Fabric SQL Database backend, including Fabric SSO authentication. It also covers iterating on the app with GitHub Copilot and how Rayfin’s code-first SDK reduces the amount of infrastructure wiring you need to do.

Cassidy Williams and Evan Boyle demonstrate an end-to-end, agentic GitHub Copilot workflow that starts in the terminal and ends with a merged pull request, focusing on the practical mechanics teams need to make AI-assisted sprint work repeatable.

Mark Russinovich and Scott Hanselman discuss how AI agents are changing day-to-day software engineering, focusing on where agentic workflows speed things up, where they break down, and what engineers can do to adapt without buying into hype.

Amanda Silver and Marco Casalaina explain how to build context-aware AI agents by combining enterprise knowledge, business data, and work signals, using Foundry IQ, Fabric IQ, and Work IQ to add orchestration and governance so agents can act within trusted boundaries.

Allison summarizes the May 2026 update for GitHub Copilot in Visual Studio 2026, covering new agent planning workflows, skill discovery, multi-file change review, context window tracking, and tighter Git integration for bringing commits into Copilot Chat and centralizing commit message instructions.

Scott Hanselman and Mark Russinovich host a live Microsoft Build 2026 showcase where developers demo AI-assisted apps, agents, tools, and workflows, then get “vibe checked” on how they work, what the AI actually produced, and what it would take to move from prototype to production.

Mark Russinovich and Ion Stoica discuss how distributed-systems principles are shaping next-generation AI platforms, covering what changes as workloads become agentic, multimodal, and globally distributed, and why open source, security, and governance are now core requirements from training through real-time serving.

Sameer Nori, Pranay Bakre, and Govardhani Babu show how to run and scale LLM inference for agentic, cloud-native apps on Azure using Arm-based Azure Cobalt VMs, including an AKS demo and practical guidance on performance, scaling, and cost trade-offs.

Ari LiVigni and Alejandro Menocal demonstrate GitHub Agentic Workflows, showing how a simple markdown-driven setup can launch an AI agent via GitHub Actions to triage issues, fix CI failures, update docs, and improve tests, producing a ready-to-review pull request while keeping developers in control.

Sunitha Muthukrishna demonstrates how to use Rayfin with Microsoft Fabric to generate and deploy an agent-driven full-stack web app, including a managed database, authentication, and backend services, then connect it to an existing Fabric data estate to add analytics, BI, and AI-powered experiences.

Allison announces that GitHub Copilot Chat is now generally available on github.com with richer pull request and diff context, making it easier to ask questions, review changes, and get summaries while staying in the PR workflow.

kinfey explains how to run LLM agents that write and execute code without giving them a host-sized blast radius, using a MicroVM sandbox. The post walks through a real pipeline (a daily Mandarin World Cup podcast) built with Microsoft Agent Framework, Azure AI Foundry, and Hyperlight snapshot/restore isolation.

Microsoft Developer presents an in-depth Build 2026 session on .NET 11 improvements across the runtime, libraries, and SDK, with a focus on performance, diagnostics, and developer productivity. It also highlights work that supports intelligent, cloud-connected, and agent-driven apps, plus concrete library updates like Unicode and JSON enhancements.

Nikola Metulev, Beth Pan, and Aditya Ramnathkar walk through a developer-optimized Windows setup aimed at reducing friction in day-to-day workflows, with demos spanning WinGet configuration, WSL-based container development, and guardrails for agent-driven actions.

Chip Huyen and John Maeda discuss practical AI systems for robotics, focusing on what it takes to program real robots safely and consistently. They cover the Vision-Language-Action (VLA) approach, challenges in collecting robot action data, and the idea of interfacing with multiple robots through a shared API.

Scott Guthrie shares a fast-paced builder’s view of what matters for developers in the current AI wave, covering how Microsoft is scaling Azure infrastructure and what “AI-ready” systems look like from silicon to software.

John Link and Viktor Veis introduce Microsoft Discovery and the idea of “Agentic Discovery,” where autonomous AI agent teams help run end-to-end scientific R&D loops. They demo how the system turns a research question into a generated notebook, analyzes container vs serverless cost and utilization patterns, and produces an executive-ready summary of findings.

Tim Bozarth presents Microsoft’s EngThrive framework (Speed, Ease, Quality) for measuring and improving developer productivity in the AI era, with practical guidance on choosing outcome-focused metrics, building dashboards, and driving changes that reduce developer toil and bottlenecks across teams.

Prachi Sethi introduces OM1, a modular orchestration layer for robotics that aims to decouple robot hardware from higher-level cognition. The session walks through OM1’s architecture, shows how capabilities can be swapped in and out, and demonstrates LLM-driven decision-making with both a physical robot and a cloud simulator.

Mike Richter shows how Elastic Agent Builder (Elasticsearch 9.4) can help AI agents manage long-running context by using a conversation context store, selective compaction, and dynamically loaded skills, with an emphasis on deploying these patterns in the Microsoft ecosystem on Azure and with Azure AI Foundry models.

Edo Segal demonstrates how to build multimodal AI agents with persistent memory, including a live walkthrough of provisioning Napster as an Azure resource and integrating the agent securely with Azure AI Foundry.

Caroline Matthews demonstrates how long-running coding agents can be built and guided in Azure AI Foundry using Claude Code and Cowork, focusing on practical patterns like evaluation-first workflows, safe autonomous execution, and multi-agent loops that can plan, test, and recover across larger codebases.

Jared Rhodes demonstrates a practical .NET pattern for building apps that connect to real hardware, including device discovery over BLE and data exchange over NFC, serial, and USB. The session focuses on structuring device services, handling cross-platform differences, and choosing local connectivity when cloud APIs aren’t the right fit.

Alexander Wachtel shows how Microsoft Fabric can be used to build dynamic, context-aware multi-agent workflows, using Fabric foundations like semantic models, lakehouses, and pipelines to support planning, retrieval, summarization, and execution across specialized agents.

Michel Hubert demonstrates how AI can improve developer onboarding by helping a new team member understand a codebase faster, find relevant context, identify key components, and make an initial contribution with less frustration and a shorter path to impact.

Dom Robinson, samkemp, and Inbal Sagiv announce Foundry Local 1.2.0 and preview Foundry Local on Azure Local, focusing on running AI on-device and at the edge with better transcription, broader hardware support, improved cancellation, and simpler acceleration across Windows and Linux.

Adrian Macias presents a practical “setup-to-ship” workflow for developing on Windows using AI playbooks and local agents on AMD Ryzen AI PCs, focusing on reducing friction from idea to first commit and showing how local execution can scale across Windows systems optimized for AMD hardware.

Srikumar Nair demonstrates how to build context-aware Azure AI Foundry agents by connecting them to Work IQ via MCP, then governing them with Agent 365. The session shows tool invocation at runtime, agent identity, end-to-end observability, and side-by-side evaluations comparing grounded vs. context-blind agents.

Rishabh Saha shares how Microsoft and PepsiCo engineers modernized PepsiCo’s data foundation for agentic applications, using Azure SQL, Cosmos DB, PostgreSQL, and Azure Databricks. The session outlines a practical build path for agentic RAG, including Azure SQL vector indexing and semantic search to speed up repeatable app patterns.