Microsoft Developer Video Summaries

AI-generated summaries of new videos. A no-sign-up video summary & introduction page

15 件の動画 · 更新: 0秒前
👤 701K subscribers · 🎬 8.9K videos
RSS で購読:
⏳ 紹介を準備中です 30秒後に更新できます
Announcements across Microsoft SQL at Microsoft Ignite 2026 | Data Exposed 📺 Announcements across Microsoft SQL at Microsoft Ignite 2026 | Data Exposed 📅 2026/11/19 17:00

紹介を準備中です…

▼
紹介を準備中です…
Azure HorizonDB + VS Code: Your AI App Development Workspace 📺 Azure HorizonDB + VS Code: Your AI App Development Workspace 📅 2026/11/16 20:00

紹介を準備中です…

▼
紹介を準備中です…
Microsoft Foundry: Bigger Models Aren’t Always Better 📺 Microsoft Foundry: Bigger Models Aren’t Always Better 📅 2026/11/16 14:45

紹介を準備中です…

▼
紹介を準備中です…
Microsoft Foundry: Keep Your AI Spend Under Control 📺 Microsoft Foundry: Keep Your AI Spend Under Control 📅 2026/11/12 20:00

紹介を準備中です…

▼
紹介を準備中です…
Build smarter search without AI: Fuzzy matching for applications | Data Exposed 📺 Build smarter search without AI: Fuzzy matching for applications | Data Exposed 📅 2026/11/12 17:00

紹介を準備中です…

▼
紹介を準備中です…
Your Path to Production for Agents 📺 Your Path to Production for Agents 📅 2026/11/11 21:26

紹介を準備中です…

▼
紹介を準備中です…
Microsoft Foundry: Test Your Agent Before You Ship 📺 Microsoft Foundry: Test Your Agent Before You Ship 📅 2026/11/10 21:00

紹介を準備中です…

▼
紹介を準備中です…
Web IQ: Grounding Agents with Real World Intelligence 📺 Web IQ: Grounding Agents with Real World Intelligence ⏱ 22:46📅 2026/11/10 17:29

Grounding AI Agents with Microsoft Web IQ: Fresh, Cited, Production-Ready Web Knowledge

▼
AI agents are only as reliable as the knowledge they can access, yet models stop learning at their training cu…

AI agents are only as reliable as the knowledge they can access, yet models stop learning at their training cutoff while the world keeps changing. This session introduces Microsoft Web IQ, a suite of AI-native grounding APIs that connects agents to fresh web knowledge with verifiable sources, and explains how to build with it.

■ Why grounding matters
- The gap between training cutoffs and real-world change
- How stale facts propagate through multi-step agent loops

■ Web IQ overview
- Six grounding scopes: web, news, images, videos, browse, and places
- The auto orchestrator with fast and advanced modes
- Integration paths: REST API and hosted MCP server, available to Azure customers

■ Performance and trust
- Quality, latency, and token efficiency covered through Microsoft's own testing
- Responsible sourcing, transparent citations, and enterprise controls

■ Scopes configuration
- Including or excluding URLs, domains, sites, and paths
- Consistency, relevance, and control across agents

■ Demos and setup
- A competitive intelligence agent example and an energy markets demo
- Deploying a Web IQ resource from the Azure portal, the Microsoft Learn quick start, and the playground

Builders of AI agents, application developers, and enterprise administrators evaluating grounding solutions will gain a clear picture of what Web IQ covers, how it differs across modes and scopes, and the concrete steps to deploy it and run a first call. Following the session, you can deploy a resource, open the playground, and try the shared demo repository against your own use case.

Microsoft Foundry with Adrian Twarog: Build Your First Agent 📺 Microsoft Foundry with Adrian Twarog: Build Your First Agent ⏱ 15:49📅 2026/11/10 08:00

Getting Started with Microsoft Foundry: Setup, Agents, Models, and Tools

▼
Microsoft Foundry is a unified platform for building AI projects on Azure, covering AI agents, model customiza…

Microsoft Foundry is a unified platform for building AI projects on Azure, covering AI agents, model customization, and application development. This walkthrough covers account setup through publishing, plus a discussion on who the platform is aimed at and how model selection and cost control work in practice.

■ Setup
- Creating a Foundry account and linking an Azure subscription
- Three starting paths: building an agent, deploying a model, or starting with code
■ Building and deploying
- Using the playground to test prompts and customize instructions
- Requesting model quota and deploying base models from the publisher catalog
- Publishing an agent as a web app and accessing it via the Azure SDK
■ Tools and integration
- Using built-in tools, MCP servers, and pre-baked Azure skills
- Building a custom skill with a limited-permission MCP connection
- Testing tool calls such as retrieving and drafting emails
■ Discussion
- Content creation process and how tutorial videos are condensed
- Model choice, free credit usage, and intended enterprise audience
- Cost visibility and oversight through the Azure ecosystem

企業向けAI開発に関心のある方、Azure上でエージェントやモデルを構築・運用したい方が対象です。視聴後は、アカウント作成からエージェント公開までの手順、モデルのデプロイとクォータ申請の流れ、カスタムツール接続の方法を把握できます。まず概要欄のリンクからFoundryにアクセスし、無料クレジットを使って最初のエージェントを構築してみてください。

Copilot Harness, DirectX, and Azure Auth 📺 Copilot Harness, DirectX, and Azure Auth 📅 2026/11/06 18:30

紹介を準備中です…

▼
紹介を準備中です…
52% More Throughput. 1.5x Better Value. The Azure SQL DB Hyperscale Advantage | Data Exposed 📺 52% More Throughput. 1.5x Better Value. The Azure SQL DB Hyperscale Advantage | Data Exposed ⏱ 5:51📅 2026/11/05 17:00

Azure SQL Hyperscale Benchmark Results Against Amazon Aurora

▼
A third-party benchmark commissioned by Microsoft compares Azure SQL Database Hyperscale with Amazon Aurora on…

A third-party benchmark commissioned by Microsoft compares Azure SQL Database Hyperscale with Amazon Aurora on an order-processing workload. SQL product team member Robby explains how the study was conducted and what customers can take away from the results.

■ Benchmark Overview
- Study setup: independent vendor, HammerDB-based e-commerce order processing simulation
- Test conditions: 16 vCore configurations and multiple concurrency levels
■ Results and Flexibility
- Raw performance and price-per-performance comparisons with Aurora
- Scaling options: serverless, sub-core, elastic pools, and database size range
- Guidance on choosing the right Hyperscale option for different workloads

This episode suits database administrators, developers, and decision-makers evaluating cloud database options for new applications or modernization projects. Viewers will understand the scope and methodology of the benchmark, the comparison criteria used, and the range of deployment choices available in Hyperscale, which can inform vendor selection and capacity planning decisions.

AI That Works Offline 📺 AI That Works Offline 📅 2026/11/03 20:25

紹介を準備中です…

▼
紹介を準備中です…
What does it really take to ship an AI agent? 📺 What does it really take to ship an AI agent? 📅 2026/11/03 16:00

紹介を準備中です…

▼
紹介を準備中です…
How to Run AI Agents at the Industrial Edge 📺 How to Run AI Agents at the Industrial Edge ⏱ 3:36📅 2026/11/03 08:00

Enabling Physical AI: Connecting Edge Devices and Virtual Co-Workers in a Microsoft Architecture

▼
Microsoft customer and partner engagement product manager Jason Farmer explains what it takes to enable physic…

Microsoft customer and partner engagement product manager Jason Farmer explains what it takes to enable physical AI, which requires connecting physical things on the edge. He walks through a reference architecture from an architectural perspective and outlines the benefits of putting such an infrastructure in place, covering both cloud-connected and on-site connected devices.

■ Architecture Overview
- Cloud-connected devices connecting directly to Azure IoT Hub vs. on-site devices communicating over a proximal protocol
- Edge infrastructure running on Azure Local or an Arc-enabled server, hosting Arc-enabled Kubernetes
- Azure IoT Operations for on-prem data and Foundry Local for running AI workloads on-prem
- Both data streams reaching Azure Resource Manager and Microsoft Fabric, then exposed to services such as Teams, Dynamics, and Work IQ

■ Virtual Co-Workers
- An OT virtual co-worker agent running in Foundry Local that keeps functioning on-prem if the cloud connection is lost
- An enterprise virtual co-worker running in Microsoft Foundry or Fabric, communicating through solutions like Dynamics and Teams

■ Closed-Loop Operations & Demo
- How virtual co-workers link agentic solutions down to edge devices
- A link to a demo for seeing the setup in action

IT/OT professionals, digital operations teams, and anyone involved in industrial edge deployments will come away with a clear map of how physical AI is structured end to end, and with a reference point to explore the architecture further through the provided demo.

WebTransport Headers, Zstd WAL Compression, and Copilot Studio Conversation Harness 📺 WebTransport Headers, Zstd WAL Compression, and Copilot Studio Conversation Harness 📅 2026/11/02 18:49

紹介を準備中です…

▼
紹介を準備中です…

他のチャンネルも紹介を読めます

入力フォームにチャンネル URL を貼り付けるだけで、好きなチャンネルの動画紹介を生成できます。

📄 このページの紹介文は AI が独自に生成したものであり、著作権をはじめとする他者の権利(商標権・名誉権・プライバシー等)を侵害しないよう配慮しています。動画の著作権は各作成者に帰属します。