Browse All GitHub Copilot Content (490)
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.
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.
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.
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.
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.
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.
Shawn Henry, Amanda Foster, and Glenn Condron go deep on building and operating multi-agent systems on Microsoft Foundry, focusing on “agent harness” patterns (including Claw) and hosted agents architecture. They cover long-running agents with triggers, state and file access, plus how Copilot SDK and Claude Agent SDK fit into coordinated workflows.
Dan Hellem and Dave Burnison demonstrate how Azure DevOps and GitHub integrate for hybrid DevOps workflows, including Azure Boards and Azure Pipelines connectivity, migration tooling, and AI-powered capabilities like Copilot assignment, Copilot code reviews, and automated multi-file fixes.
Mads Kristensen and Nik Karpinsky demo GitHub Copilot in Visual Studio, focusing on agent-style workflows that go beyond code generation: diagnosing bugs from runtime behavior, profiling performance to find bottlenecks, recommending targeted fixes, and building tests to prevent regressions for enterprise C#, .NET, and C++ codebases.
Nik Karpinsky demonstrates how to diagnose and fix modern performance issues using Visual Studio’s profiling and diagnostics tools, with GitHub Copilot and AI-powered agents helping generate, refine, and explain benchmark and profiling results for faster root-cause analysis.
Ellie Bennett and Denizhan Yigitbas show how GitHub Copilot can follow you across development environments, from local CLI workflows to cloud execution using Remote Sandboxes, with an emphasis on staying in control while Copilot runs commands and iterates on changes.
Parthasarathy Srinivasan and Rajya Laxmi Yellajosyula demonstrate a multi-cloud, enterprise AI workflow that combines Oracle Database@Azure with Microsoft Fabric, MCP, and GitHub Copilot, covering provisioning, synthetic data creation, ETL from bronze to gold, and an end-to-end fraud detection demo driven by natural-language orchestration.
GitHub introduces and demos the GitHub Copilot App, focusing on what it is and how developers can use Copilot features from the app experience.
Fokko at Work demos selected updates in Visual Studio Code 1.123 with a focus on GitHub Copilot-related changes, including session sync/Chronicle and the Agents window, plus improvements to the built-in browser and screenshot workflow.
Visual Studio Code hosts a live Microsoft Build session with the GitHub Copilot team, covering agentic development across the Copilot ecosystem. The agenda includes Copilot CLI, building with the GitHub Copilot SDK, and a segment on .NET Aspire alongside Copilot and related tooling.
Microsoft Developer promotes the Microsoft Build 2026 Day 2 livestream, highlighting GitHub and VS Code updates, GitHub Copilot deep dives, and a day of live programming sessions with Microsoft and GitHub engineers, plus Foundry-focused talks and selected breakout streams.
Poonam Gupta shares how Microsoft’s CAP organization is moving repositories from Azure DevOps (Azure Repos) to GitHub at enterprise scale, while keeping Azure Boards and Azure Pipelines where they still matter. The post highlights migration tooling, hybrid workflow patterns, and how Copilot-driven agentic workflows are influencing platform decisions.
Microsoft Developer announces that Microsoft Build 2026 Day 2 is live, highlighting a schedule that includes GitHub Copilot deep dives, VS Code announcements and demos, and live coding sessions with Microsoft and GitHub engineers.
Microsoft Developer shares a short announcement that Microsoft Build 2026 Day 2 is streaming live, highlighting GitHub, VS Code announcements and demos, GitHub Copilot deep dives, and live coding sessions with Microsoft and GitHub engineers.
Teddyb introduces Microsoft Fabric Skills, an open-source set of packaged instructions and API patterns that help GitHub Copilot and other AI coding tools use Fabric correctly. The post explains what the skill bundles contain, how to install them via Copilot plugins or by cloning the repo, and how auth/token audiences are handled across Fabric workloads.
Microsoft Developer introduces Project Lobster and the early Microsoft Scout desktop experience, focusing on always-on AI agents that can coordinate work, surface risks earlier, and keep tasks moving with less prompting. The video also outlines how Frontier customers can access the experimental release and what enrollment and policy prerequisites are required.
Shawn Henry rounds up the BUILD 2026 announcements for Microsoft Agent Framework, covering the new Agent Harness for production-grade agent execution, Foundry Hosted Agents for deploying and operating agents at scale, and CodeAct (Hyperlight) to reduce tool-calling latency and token usage, with examples in .NET and Python.
GitHub hosts a live coding stream from Microsoft Build focused on agentic development with GitHub Copilot, including sessions on Copilot CLI, the Copilot SDK, and Copilot workflows across VS Code and Visual Studio, plus a segment covering .NET Aspire alongside Copilot.
Cassidy Williams demonstrates practical, demo-driven agentic coding workflows with GitHub Copilot, focusing on planning work, delegating implementation, reviewing AI-generated pull requests, and shipping changes with guardrails that teams can apply immediately.
Tina Schuchman and Jeff Hollan walk through the end-to-end lifecycle for building production-grade AI agents using Foundry Agent Service and Microsoft Agent Framework, covering local prototyping through hosted deployment, with identity, secure networking, evaluations, and operational lifecycle management, plus how GitHub Copilot fits into the workflow.
Andrew Westgarth and Gaurav Seth explain how to modernize legacy .NET applications using Managed Instance on Azure App Service, focusing on removing migration blockers without code rewrites and moving to a scalable PaaS foundation. They also show how GitHub Copilot can support AI-assisted modernization and MCP-driven API interactions.
Sam Basu demonstrates how Uno Platform can be used to build modern cross-platform .NET apps with visual tooling and AI assistance, including GitHub Copilot integration. The session highlights a folder-based app structure, consistent rendering with SkiaSharp, and MCP-based workflows for documentation grounding and UI interaction.
GitHub highlights four announcements from Microsoft Build focused on GitHub Copilot and agentic workflows, including a new desktop Copilot app, voice mode and the Rubber Duck agent in Copilot CLI, the generally available Copilot SDK, and cloud/local sandboxes for safer experimentation.
GitHub demonstrates how GitHub Copilot can run code inside an isolated sandbox, either locally or in the cloud. The demo shows how to enable a sandbox with the /sandbox enable command and how to control permissions like network and file system access so developers can test changes safely.
Allison summarizes May/early June 2026 updates to GitHub Copilot in VS Code (v1.120–v1.123), including the new Agents window preview, remote agent sessions, expanded BYOK support (including air-gapped use), and safety/efficiency improvements for terminal-driven workflows.
Tessa Kloster, Arindam Chatterjee, and Anshul Sharma present a Microsoft Build 2026 session on using Microsoft Fabric Real-Time Intelligence to build event-driven AI applications and autonomous agents that react to live data, combining streaming ingestion, real-time analytics, and actioning in a governed workflow.
Rong Lu and Brady Gaster demonstrate an agent-driven workflow where a team of GitHub Copilot agents takes a blank repo to a live Azure AI app, including architecture planning, code generation, Azure provisioning, and deployment. The session also covers toolbox concepts, unified auth, and adding automated evaluations.
Marko Hotti and Sergiy Smyrnov demonstrate how GitHub Copilot and the Azure Cosmos DB Agent Toolkit can speed up NoSQL schema design, with AI-assisted schema generation, query optimization suggestions, and refactoring recommendations, plus local iteration using the new Mac/Linux Cosmos DB emulator.
Aamir Jawaid and Umang Sehgal build a Microsoft Teams agent live, showing how to go from an empty terminal to a deployed agent that can be @mentioned in chats and channels. The session highlights the Teams CLI, the Teams SDK’s new skills plugin, and how GitHub Copilot fits into the workflow.
Mario Rodriguez and Evan Boyle demonstrate how AI agents—centered around GitHub Copilot—can work across planning, coding, CI/CD, and production operations to help teams ship AI-assisted code safely. The session focuses on practical workflows, guardrails, and review patterns that keep autonomous changes controlled while still moving fast.
Jeff Smith and Ram Kakani show how Oracle managed MCP Servers can connect Oracle Database@Azure to Microsoft IQ (Work IQ, Fabric IQ, and Foundry IQ) so teams can build agentic, AI-driven workflows with more context, reasoning, orchestration, and governance over enterprise data.
Kirupa Chinnathambi, Stuart Schaefer, and Patrick Nikoletich explain how Windows is evolving to support AI agents that can take real actions (run commands, modify files, move data) while staying within clear safety boundaries, including identity, containment, and ongoing supervision.