Browse Artificial Intelligence Videos (296)

Microsoft Developer demonstrates Intelligent Terminal running a 120-billion-parameter model locally on Surface hardware with NVIDIA RTX Spark N1X and 128 GB of unified memory. The demonstration covers completing workflows such as writing new agent skills with context, without sending requests to the cloud.

John Savill reviews this week's Azure updates, covering Container Apps logging, confidential VMs, network security, storage quotas, and cross-tenant backup restore. The Halloween edition also covers Azure AI Foundry model cost management, Azure MCP Server 3.0, new model topics, and GitHub Universe.

Michael MacKenzie, Microsoft’s VP of Product Management for Azure IoT and Digital Operations, explains how physical AI differs from traditional automation: automation repeats a task, while physical AI gets smarter each time it runs. This short introduces the distinction as part of a broader conversation on IoT and physical AI.

Microsoft Developer explores model selection using the Microsoft Foundry model catalog. By swapping only the model deployment and running the same evaluation on both options, the episode compares results alongside measured cost and latency to show when a smaller model is suitable for production and when it is not.

Visual Studio Code demonstrates how to use IntelliSense and GitHub Copilot to write, explain, and improve PostgreSQL queries without switching tools. The workflow also covers running queries and validating their results directly in the editor.

Maggie Appleton, Martin Woodward, and Jocelyn Velarde close GitHub Universe 2026 with open-source perspectives and coding demos. The session explores learning with GitHub Copilot, scaling projects with AI agents, and collaborative AI planning, alongside creative experiments that highlight the craft of coding and building together.

Martin Woodward demonstrates how to install Super Mona on a GitHub Universe 2026 conference badge using GitHub Copilot. The demo shows copying repository instructions into Copilot Chat and letting the agent configure the app, then using the badge’s hidden capacitive buttons to play.

Microsoft Developer shows how to build a prompt agent in Microsoft Foundry using a model, instructions, and MCP tools, without managing containers or servers. The video explains when custom orchestration or a different framework calls for a hosted agent, while keeping name-based invocation consistent for callers.

Patrick LeBlanc joins Anna Hoffman to demonstrate Database Agents in Microsoft Fabric, which detect SQL performance problems before they affect users. The episode covers Database Hub, configuration requirements, issue detection, and SQL Server Management Studio integration, alongside a longer-term vision for agents that learn from DBA interactions.

GitHub recaps the opening keynote at GitHub Universe 2026, covering a dedicated Copilot app, third-party connectors, and multi-model orchestration through Copilot Fusion. The video also highlights multi-repository agent workflows with Copilot Projects, cloud sandboxes, Code Review Max, code scanning, and architectural upgrades to Git.

GitHub recaps the GitHub Universe 2026 opening keynote, highlighting the new GitHub Copilot app, multi-model orchestration through Copilot Fusion, and autonomous task management in Copilot Projects. The video also covers Code Review Max for catching critical bugs and GitHub’s work to rebuild the core infrastructure underneath Git.

Michael MacKenzie explains how IoT, industrial AI, and physical AI connect machine data to decisions and actions. He outlines the roles of Azure IoT Hub, Azure IoT Operations, and Azure Device Registry, including operational inference and the policy, access, and certificate controls that bridge IT and operational technology.

April Leonard, Jay Parikh, Cassidy Williams, Burke Holland, and Damian Brady present GitHub Universe 2026’s opening keynote. The session covers GitHub Copilot updates, autonomous agent workflows, agent-powered quality and security, and changes to GitHub’s core infrastructure, with live demonstrations of developer tools and capabilities.

Visual Studio Code demonstrates Agent Bake Off by running six AI coding agents on the same Windows settings reorganization. The video compares results, tool use, context, and cost, then shows how judging and synthesis can combine the strongest ideas into a finished change, including when starting without an existing project.

Cassidy Williams and GPS welcome Martin Woodward to discuss how AI-generated pull requests affect open source maintainers and how contribution limits can help. They also explore the hackable GitHub Universe badge, including its hardware controls and GitHub Copilot-assisted MicroPython app deployments, alongside DevOps fundamentals and favorite open source projects.

John Savill explains where Microsoft security solutions fit as AI accelerates both attacks and defenses. The video covers MDASH, Perception, Defender ISOC, security foundations, securing AI, and DART, providing an overview of how these offerings relate to cybersecurity.

dotnet demonstrates how to build an agentic AI companion using the GitHub Copilot SDK, a .NET and Aspire backend, and an M5Stack StackChan robot. The session explores agent behaviors and tool use, then connects the agent to the robot’s display and movements.

dotnet demonstrates how to build a StackChan robot's AI brain using a .NET backend orchestrated with Aspire. The session connects the backend to the physical desk robot, adds services and local observability, and brings the pieces together into an end-to-end interaction.

dotnet demonstrates how to bring an M5Stack StackChan desk robot to life by programming its expressions and movements and connecting it to a .NET backend and dashboard. This hands-on session explores how hardware and .NET services work together to create a first end-to-end interaction with a physical AI companion.

GitHub takes viewers inside Pimoroni’s factory to explore how the hackable GitHub Universe 2026 badge is manufactured. The video follows stencil printing, component placement, and solder reflow, and covers the handheld console’s capacitive touch controls, auto-flipping interface sensors, and custom firmware developed with GitHub Copilot.

Christoph Berlin explains how manufacturers can reuse one AI agent across cloud, edge, and fully disconnected environments. Building on a root cause example, he describes shared data contracts, guardrails, and repeatable blueprints that support deployment across many sites, with agent instances managed through a single interface.

Louis Erbkamm shares how Arnis converts real-world geographic coordinates into playable Minecraft worlds using OpenStreetMap data. The video explores the project's international contributor community and how its sole maintainer uses GitHub Copilot to triage bug reports, review pull requests, and keep the project moving.

Visual Studio Code demonstrates how the PostgreSQL extension and GitHub Copilot help you explore an unfamiliar database. The episode covers inspecting schemas, tables, views, and functions, visualizing relationships, asking context-aware questions in Copilot Chat, and checking answers against the database to understand its data model.

Visual Studio Code demonstrates a PostgreSQL workflow combining the PostgreSQL extension’s IntelliSense and database context with GitHub Copilot. The video covers drafting, explaining, analyzing, and improving SQL queries, then running them, inspecting results, and exporting data without leaving the editor, while keeping developers in control of the final queries.

John Savill examines why AI agents fail beyond the model itself, covering unclear goals, bad context, tool misfires, reasoning errors and lost state. He also discusses hijacking, excessive privileges, limited visibility and an improvement loop for understanding and addressing failures.

Microsoft Developer highlights three updates: .NET 11 is ready for serious production validation, Python 3.15 defaults to a native Arm64 runtime on Windows on ARM, and browser automation in Microsoft Foundry is generally available. The video outlines what these changes mean for developers.

Microsoft Developer demonstrates how to protect an AI agent from malicious user input and instructions hidden in tool responses. The walkthrough configures Microsoft Foundry guardrails and Prompt Shields, replays both attacks, and uses traces to show where protections intervene before the agent acts.

John Savill reviews this week's Azure and AI updates, including networking, backup, monitoring, storage, and identity changes. Topics include Traffic Manager integration with Azure DNS, keyless TLS, Cosmos DB key rotation, Azure Databricks private networking, and Copilot Studio agent identity.

Visual Studio Code introduces a four-part video series focused on doing more PostgreSQL work directly inside VS Code, including connecting to databases, writing and optimizing SQL, using GitHub Copilot to understand database context, and troubleshooting performance, with Azure mentioned as the underlying platform for modern PostgreSQL workloads.

Microsoft Cloud outlines a “Physical AI” vision for industrial scenarios, describing how AI systems can perceive, reason, and act in the physical world across manufacturing, quality, and supply chains, and how organizations can move from simulation to real operations spanning edge and cloud.

GitHub demonstrates a hands-on workflow for going from a GitHub issue prompt to a deployed AI agent inside the GitHub Copilot app, using Azure AI Foundry tooling to provision resources, deploy a model, validate grounding to reduce hallucinations, and ship a secure proxy plus a website chat widget.

Microsoft Developer introduces the idea of “adaptive” software that can reason and take actions, positioning it as a shift beyond apps that only respond to user input.

Christoph Berlin explains how an AI agent can speed up root cause analysis by correlating data and reducing the dependency on tracking down subject-matter experts, helping engineers start investigations with better initial context.

Microsoft Developer walks through how developers (and AI coding agents) can build applications with Azure SQL, including a demo flow that starts from an Azure SQL DB container and moves into Azure SQL Database’s free tier, plus an overview of Microsoft SQL agent skills and plugin concepts.

Marko Hotti and Patty Chow show how to build an Azure Cosmos DB app using AI-assisted development, starting from a blank folder and a product spec to generate a working travel planner. They cover data modeling, container design, queries, and local testing using the Cosmos DB Linux emulator and GitHub Copilot in VS Code.

GitHub explains how GitHub Copilot approvals can help teams avoid routine pull request review bottlenecks by letting Copilot provide delegated review approvals that count toward merge protection rules, while still combining that automated assessment with a human approval to satisfy branch requirements.

Marko Hotti and Madeline Egan explain how to move an AI agent from a demo to a production-ready system using Azure Cosmos DB, focusing on observability and evaluation practices like tracing, regression testing, and before/after metrics to improve retrieval quality, latency, token usage, memory efficiency, and RU consumption.

Marko Hotti and Madeline Egan show how to build AI agents that keep durable, shared memory across sessions using Azure Cosmos DB, so a multi-agent travel planner can remember user preferences, share context between agents, and continue work after handoffs instead of restarting from scratch.

Marko Hotti and Patty Chow demonstrate how to build a smarter AI travel planner on Azure Cosmos DB by combining operational app data with vector embeddings and search features, so the app can answer nuanced queries while still respecting real inventory and booking workflows.

Microsoft Developer shows how to use Agent Optimizer in Azure AI Foundry to improve an agent when prompt tweaks aren’t reliably fixing behavior. The video walks through building an evaluation dataset, scoring a baseline, generating candidate instruction sets, and validating improvements (quality, latency, and safety) before shipping a new agent version.