Browse Artificial Intelligence Videos (432)

Microsoft Developer shares a 2-minute weekly roundup covering an AI agent preview in Visual Studio built on the GitHub Copilot SDK, plus Azure AI Foundry model updates and the MCP C# SDK 2.0 release with stateless-first communication and improved interoperability.

Microsoft Developer introduces the Microsoft Quantum Development Kit (QDK), an open-source platform for building quantum applications across Q#, Python, OpenQASM, Qiskit, and Cirq, with QIR support plus integrated simulation and resource estimation tools, and AI-powered assistance in VS Code and GitHub Copilot.

John Savill runs through the 7th August 2026 Azure update, covering changes across compute, networking, security, storage, SQL, and Databricks—highlighting VM defaults and retirements, new routing and proxy capabilities, Private Link over IPv6, and several Databricks and Azure SQL enhancements.

GitHub covers stacked pull requests (now in public preview), a security incident involving an OpenAI test model accessing Hugging Face servers, and a pixel-art “Isometric NYC” project built with 3D tiles and image generation models.

Mark Russinovich explains how he used AI-assisted coding to port the long-running Sysinternals ZoomIt tool from Windows to macOS in two days, including a walkthrough of ZoomIt’s core presentation features and a demo of the new Demo Mirror capability for sharing content while staying in PowerPoint Presenter View.

James Montemagno gives a first look at using Kimi K3 (Moonshot’s open-weight model) inside GitHub Copilot in VS Code, focusing on what it enables for agentic coding and how developers can start trying it in their editor workflow.

Sameen Karim demonstrates GitHub’s stacked pull requests workflow, showing how to split large feature branches into smaller PR layers, work with stacks from the GitHub CLI using the gh-stack extension, and merge an entire stack efficiently while using Copilot to help generate tests.

Fokko at Work demos selected new features in Visual Studio Code 1.132 that affect day-to-day Copilot Chat and editor workflows, including tracking session activity from the chat input, starting side chats with /btw, terminal output reflow, and dictation onboarding/customization, with notes on enterprise policy and plan-based availability.

Bruno Capuano, Pranav Senthilnathan, and Tarek Mahmoud Sayed walk through MCP C# SDK 2.0 and what its stateless-first approach means for building .NET AI agents, including standardized HTTP support, multi round-trip requests, and compatibility considerations, plus an overview of Microsoft Foundry Hosted Agents for scalable AI solutions.

Mine Starks demonstrates the Quantum Development Kit (QDK) learning experience in VS Code, showing how guided lessons and hands-on Q# exercises are paired with GitHub Copilot assistance to help developers learn quantum computing fundamentals and progress into algorithms like Grover’s and Shor’s.

Microsoft Developer shares Shireesh Thota’s perspective on turning “data everywhere” into usable intelligence by bringing data together, adding context, and applying AI on top—framed as an architecture discussion rather than a single feature walkthrough.

GitHub shows how Dan, a senior corporate counsel, uses GitHub Copilot CLI to verify AI-generated analysis by grounding outputs in source documents. The video highlights a custom Copilot CLI skill (“Eyeball”) that embeds inline screenshots to help reviewers validate clauses and act on AI outputs with more confidence.

Authorised Territory demonstrates a .NET MCP server pattern where a tool call starts a background task and returns a task handle instead of an immediate result, while a .NET client polls the server every second until the final output is available.

Victoria shares how she built an internal “Innovation Marketplace” for the GitHub legal team using GitHub Copilot CLI, from planning and tracking work in GitHub Issues to deploying with GitHub Actions and GitHub Pages.

James Montemagno introduces VS Code 1.131’s built-in dictation feature, showing how developers can speak directly into chat, editors, and the terminal without installing extensions, with an emphasis on privacy via on-device transcription and an optional AI cleanup step for more readable output.

GitHub walks through the My work tab in the GitHub Copilot app, showing how to manage issues and pull requests across repositories with default and custom views, filters, and layout options, and how to start agent sessions directly from work items.

John Savill recaps major Microsoft AI updates from July 2026, including new and updated models, Azure AI Foundry changes, and GitHub Copilot feature additions such as new “harness” options, @-mentioning app agents, and browser tools for Copilot in VS Code.

Visual Studio Code shares a short tip on teaching GitHub Copilot your project-specific rules using custom instructions, as part of learning agentic development in VS Code.

GitHub shows how to use voice prompting in the GitHub Copilot app to quickly turn a spoken “brain dump” into a usable text prompt, helping you get started faster when you’re not sure how to phrase what you want.

Visual Studio Code shares a quick update that OpenAI reduced pricing for GPT-5.6 Luna and GPT-5.6 Terra, and points developers to try both models directly in VS Code.

John Savill rounds up a week of Azure platform updates, spanning AKS, networking, API Management, monitoring, data services, and regional expansion, plus a few notable AI model availability items and security-related changes like Azure Enclave and Key Vault symmetric keys.

Authorised Territory demonstrates how a .NET MCP server can expose a skill as a resource, and how an AI agent client can use that skill to answer a question, using a locally running LLM via Ollama.

Visual Studio Code shares a quick tip for reducing token usage and improving GitHub Copilot results by running a grammar check on your prompt before submitting it in VS Code.

Gwyneth Peña-Siguenza demonstrates how to debug a real Python API in VS Code, covering breakpoints, stepping, variable inspection, watch expressions, and the call stack, plus how GitHub Copilot can help you understand failures and fix bugs faster.

Fokko at Work demos selected new features in Visual Studio Code 1.131 that relate to GitHub Copilot, including subagents session information in the Agents window and dictation mode, with notes on how enterprise policies and pricing plans can affect feature availability.

GitHub walks through what an agent Skill is and how to build one in GitHub Copilot, then covers what’s new in the MCP release that shipped this week.

Davide Mauri breaks down where AI genuinely helps in a real-world developer-focused app, using an example that improves how developers find relevant resources faster while keeping the application’s core purpose unchanged.

GitHub shows how to customize the GitHub Copilot app, including themes and sounds, voice dictation and transcription model settings, and connecting custom MCP servers or local AI models using bring-your-own-key providers.

Bruno Capuano and Angel Hernandez discuss practical enterprise patterns for adding AI capabilities to modern .NET applications, with a focus on moving from prototypes to production. The session covers architecture approaches, AI-powered workflows, and tools and practices that help teams build reliable intelligent experiences.

Matt Gordon and Anna Hoffman show how to set up anomaly detection in Microsoft Fabric using streaming change events from Azure SQL/SQL Server, then trigger alerts and actions with Fabric components like Eventstream, Eventhouse, and Activator.

GitHub walks through starting a session in the GitHub Copilot app, including writing a first prompt, adding project context from a local folder or GitHub repository, choosing an AI model, and using voice input to describe coding problems.

Visual Studio Code shows how the new Migration feature in VS Code turns existing prompts into reusable skills, focusing on a faster way to organize and reuse prompt-driven workflows inside the editor.

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.

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.

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.

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.

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.

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.

Microsoft Developer introduces SQL MCP Server 2.0 and explains how it helps agentic apps work with production SQL data more safely, including new OBO authentication, MCP tool improvements, and security guardrails, with demos covering configuration and controlling access across Graph, REST, and MCP.