Browse All Posts (104)

Burke Holland shares a practical GitHub Copilot “harness” workflow for building features end-to-end: pick a Copilot surface, enable more autonomy safely, prototype and plan in the same session, implement with Autopilot, then iterate and run a Rubber Duck review to catch blind spots.

AmirJafari announces updates to Fabric data agents in Microsoft Foundry, focusing on simpler MCP-based connectivity, OneLake Catalog discovery, support for attaching multiple data agents to a single Foundry agent, and improved production troubleshooting via Foundry Observability traces and logs.

John Savill gives a very quick overview of Rayfin and Microsoft Fabric Apps, focusing on where they fit in the Fabric ecosystem and why they matter for analytics and data platform work.

John Savill gives a quick overview of Rayfin and Microsoft Fabric Apps, focusing on the problem they’re trying to solve, how the Fabric Apps data model works, and what app hosting looks like in practice, with a short demo and key takeaways.

Yuliia Kovalova and Jan Krivanek introduce the MSBuild Binlog Analyzer for VS Code, a preview extension that uses GitHub Copilot Chat plus an MCP server to explain build failures, pinpoint performance bottlenecks, compare builds, and spot regressions directly from MSBuild .binlog files.

mayurjain explains how the OpenAI Assistants API retirement on August 26, 2026 affects programmatic integrations with Microsoft Fabric Data Agents, and why Microsoft recommends moving to the Data Agent Model Context Protocol (MCP) endpoint instead of rebuilding directly on OpenAI’s Responses API.

robece-msft introduces the fundamentals of event-driven architecture in Microsoft Fabric, focusing on Real-Time Hub and how Fabric’s event capabilities help workloads react to meaningful business signals in real time.

vladvino announces the public preview of the AI Gateway tier for Azure API Management, focused on publishing and governing AI models and MCP servers. The post explains the new portal experience, policy-card governance (rate limits, quotas, Content Safety, fallback), and OpenTelemetry token metrics to destinations like Application Insights.

Ram Shankar Siva Kumar announces Microsoft’s External Red Team Alliance (EXTRA), a global effort to expand AI red teaming beyond internal teams by funding academic research and building an external network of specialists to test frontier AI systems across languages, regions, and domains.

Christopher Harrison introduces the GitHub Copilot app and shows how it supports real-world development workflows with project-scoped agent sessions, Quick Chat for parallel threads, interactive canvases for visual iteration, and Agent Merge to help move pull requests through CI and review.

Kumar Kaushal demonstrates a transitional Azure networking pattern for phased migrations where an application is hard-coded to a legacy private IP. The lab uses Private Link Service Direct Connect plus a Private Endpoint and a site-to-site VPN so Azure-hosted tiers can keep calling the same on-premises address during the interim phase.

Lee Stott explains why the Model Context Protocol (MCP) is becoming the standard way AI agents connect to tools and data, then shows minimal runnable MCP server examples in Python and TypeScript plus practical guidance for VS Code hosting, security, and production operations.

John Edward explains how to build an AI-powered IT support agent on Azure, using Azure AI Foundry with Azure OpenAI Service and (optionally) Azure AI Search for RAG-based answers grounded in internal documentation, plus ideas for automating common help desk actions like ticket creation and password resets.

Welcome to this week's GitHub Copilot roundup, where the story is less about a single assistant and more about a platform you can tune, govern, and measure. The model picker keeps expanding (Claude Opus 5 and Gemini 3.6 Flash), while cloud agents show up in more places like Linear, GitHub Mobile (for failed Actions checks), and GitHub Issues with new automation controls. On the operations side, Copilot adds clearer AI Credits visibility, cost center pools, and an impact dashboard, and GitHub Code Quality reaches GA with Copilot Autofix bringing fix suggestions directly into PR workflows.

This week's DevOps roundup connects day-2 guardrails, agentic workflows, and stricter pull request gates. Azure Policy for Kubernetes moves validation closer to the API server with VAP and CEL, while GitHub and VS Code keep pushing Copilot agents earlier into issues, PR creation, and even mobile-first CI triage. On the reliability side, GitHub Code Quality and Dependabot's default cooldown add more predictable merge-time checks, and Azure deep dives on large-scale migrations and hybrid Logic Apps highlight rollout and rollback patterns that hold up under real traffic.

Welcome to this week's Weekly Azure Roundup, where the theme is tightening the path from prototype to production across governance, security, and operations. AKS governance takes a Kubernetes-native step forward with CEL and Validating Admission Policy support, while networking and protection updates add practical controls like IPv6 for VPN Gateway and custom DDoS policy tuning. On the platform side, Azure Functions runtime updates and a large-scale migration case study highlight what it takes to keep serverless estates current under live load, and the agent stack continues to fill in with Foundry design tooling, delegated auth, a released Agent Framework runtime, and GA observability in Azure Monitor. We also cover new AI model options, expanding HPC capacity, and data streaming and network controls across Azure SQL and Fabric, plus hybrid updates spanning Azure Local storage and Logic Apps Hybrid on self-managed Kubernetes.

This week in .NET, Microsoft Agent Framework hit a more practical stride with a batteries-included runtime (Harness) and Declarative Workflows 1.0 that moves multi-agent orchestration into YAML you can review and change without rewriting core code. On the web stack, .NET 11 Preview 6 focused on safer defaults and sharper APIs, including async validation for minimal APIs, automatic CSRF protection, and OpenAPI updates that help keep server and client contracts aligned. We also saw VS Code refine the in-editor agent experience and more hands-on guidance for building MCP servers in .NET, with sampling and logging patterns that improve repeatability and observability. Rounding things out, hybrid integration stayed in focus with a detailed walkthrough for running Azure Logic Apps Hybrid on a self-managed Kubernetes setup.

This week's ML roundup focuses on the practical path from research ideas to systems you can ship. Microsoft open-sourced ML Video Codec (MLVC) with code, weights, and tooling for real-time deployment on commodity NPUs, while Fabric and SQL updates show clearer patterns for streaming fresh signals into ML enrichment and feature updates. On the platform side, OneLake and Lakehouse improvements reduce friction around query iteration, cross-platform table access, and tighter inbound controls. We close with lessons on scaling large training runs across AMD and NVIDIA via Foundry Managed Compute and a look at Microsoft IQ as a governance-first way to feed agents the right context.

This week's Weekly AI Roundup is about AI features that are starting to look like real workflow infrastructure: more Copilot model choices (Claude Opus 5 and Gemini 3.6 Flash), more places to run coding agents, and clearer controls for approvals, auditability, and spend. Copilot's ticket-to-PR story got deeper with Linear GA, mobile-triggered agent fixes for failed CI checks, and new agent automation controls in GitHub Issues, while GitHub Code Quality reached GA with enforceable gates and Autofix in PRs. On the platform side, MCP moved toward a stateless spec and stronger governance patterns (including Azure API Management and OBO identity), and Microsoft pushed more of the "ship and operate" stack with Agent Framework releases, Foundry Toolboxes, and an observability agent for day-two operations.

This week's Security roundup tracks a clear shift toward platform-enforced guardrails for both AI-assisted development and cloud operations. GitHub and Azure shipped changes that make controls more explicit and easier to standardize, from stateless MCP support and model selection safeguards in Copilot to Kubernetes-native admission policy, DDoS tuning, and tighter data plane access rules. On the supply chain side, Dependabot's default cooldown and GitHub Code Quality's PR gating aim to reduce risky churn while catching issues earlier. Threat reporting also reinforces that defenders need coverage beyond email as Teams-based lures and vishing keep growing, while incident response becomes more packaged through new insurer-aligned options.

Authorised Territory demonstrates a .NET AI agent setup where an agent is allowed to rename a file inside a confined folder using the .NET Agent Framework harness, with a local Ollama-hosted LLM (gpt-oss) driving the agent’s decisions.

GitHub highlights an open-source project that turns World Cup 2026 match event data into interactive 3D “data portraits,” focusing on how the visualization is built and delivered in the browser.

GitHub shares that Microsoft Comic Chat, a classic IRC client from 1996, has been open-sourced on GitHub, including original source snapshots and experiments to modernize it for current Windows versions.

Reynald Adolphe and members of the VS Code and GitHub Copilot teams recap the past month’s updates, with live demos of notable Visual Studio Code improvements and GitHub Copilot changes, plus a chance for viewers to ask questions in chat.

Naba Kumar and the MLVC team announce the open-source release of MLVC, a learned video codec that replaces traditional codec primitives with end-to-end neural compression. The post shares bitrate savings versus H.264/H.265, real-time performance targets on commodity NPUs, and what’s included in the GitHub release (models, weights, training scripts, and conversion tooling).

Allison announces that Anthropic’s Claude Opus 5 is now selectable in GitHub Copilot, highlighting its strengths on long-running, multi-step coding tasks and agentic workflows, plus where it’s available, how admins enable it for Business/Enterprise, and how usage-based billing applies.

John Savill recaps a small set of Azure updates for the week of 24th July 2026, covering new capabilities across AKS, Azure Functions runtimes, networking, DDoS protection, Defender security assessments for PostgreSQL Flexible Server, and a new Log Analytics table aimed at generative AI workloads.

GitHub’s The Download rounds up developer news including TypeScript 7’s new native Go compiler, VS Code 1.129’s dedicated agent host runtime, Kimi K3’s 2.8T-parameter model, and Microsoft open-sourcing the 1996 Comic Chat IRC client, plus a few other notable open-source and ecosystem updates.

Visual Studio Code shares a short announcement for a new course on using Foundry Toolkit in VS Code to build, test, debug, and deploy AI applications.

Fokko at Work walks through what’s new for GitHub Copilot in Visual Studio Code 1.130, focusing on assisted tool approvals, Agents window improvements, and chat updates, with notes on how enterprise policies and plan differences can affect feature availability.

carlottacaste shares a short walkthrough of the Foundry Toolkit for Visual Studio Code and a companion VS Code Learn course, focused on keeping model selection, prompt iteration, and agent development inside VS Code, with links to a full video playlist and a featured setup episode.

Kayla Cinnamon gives a quick tour of the redesigned editor panel inside the Agents window in VS Code 1.129, showing how the updated layout supports agent-driven workflows and keeps code editing and AI-assisted interactions in one place.

Allison announces general availability of Copilot cloud agent for Linear, letting teams assign Linear issues to Copilot to produce draft pull requests, run work in an ephemeral environment backed by GitHub Actions, and report progress back into Linear with configurable models, branches, and custom agents.

arindamc explains how to build a real-time “row-to-intelligent-action” pipeline in Microsoft Fabric that captures shopping-cart signals via CDC, reshapes them into analytics-ready rows, and enriches each micro-batch with AI in a Spark Structured Streaming notebook to drive timely actions.

Allison announces that GitHub MCP Server already supports the upcoming stateless MCP specification, outlining protocol changes (like removing sessions and initialize) and what GitHub changed internally to stay compatible while improving scalability and verification.

AbodeSaafan explains how the Azure Logic Apps team migrated roughly 60,000 per-customer Azure Functions apps from the end-of-life v1/v2 runtime to Functions v4 (isolated worker) under live load, using shadow traffic, strict parity checks, and a progressive rollout with fast rollback and careful retirement of the old fleet.

sbaynes announces two new Microsoft in-house model variants—MAI-Image-2.5-Pro and MAI-Voice-2-Flash—now in public preview, and explains where they’re already running in production across Microsoft products and Azure, including pricing, performance claims, and developer entry points via Azure AI Foundry.

Allison announces a GitHub Mobile improvement that lets you use the Copilot cloud coding agent to investigate and fix failing GitHub Actions checks directly from a pull request, creating a follow-up PR for you to review and merge.

stevenbucher explains how Azure Policy for Kubernetes can now enforce policies using Kubernetes Validating Admission Policy (VAP) with CEL, via Gatekeeper’s integration. The post contrasts the older webhook/Rego flow with in-process validation, then walks through packaging a CEL constraint template into an Azure Policy definition and rolling it out across AKS clusters.

Steve Sweetman explains how AT&T built and scaled its telecom-focused OTel 2.0 models using Microsoft Foundry Managed Compute, combining open models from Hugging Face with AMD and NVIDIA GPU capacity to process around one trillion tokens while optimizing for cost, performance, and deployment speed.