Microsoft Mechanics Podcast

Apply the newest engineering from Microsoft to the work you do every day. Mechanics is Microsoft's official video series for IT Pros, Solution Architects, Developers, and Tech Enthusiasts. Watch as Microsoft engineers show you how to get the most from the software, service, and hardware they built. Through in-product demos, recommendations, how-to's, and tips, they simplify complex topics so you can share them with clients, peers, and your management team. These are in-depth looks at Microsoft 365, Azure, Data and AI, Surface, Windows, and the Power Platform. Get up to speed and subscribe.

New Agents in Microsoft Purview 12/15/2025

How Microsoft Agent 365 works 12/09/2025

Microsoft Foundry - Everything you need to build AI apps & agents 12/05/2025

Foundry IQ for Multi-Source AI Knowledge Bases 12/03/2025

Foundry IQ for Multi-Source AI Knowledge Bases Ground your AI agents on your organization’s knowledge, pulling from multiple sources at once, connecting the dots automatically, and getting more accurate, context-rich answers without doing manual orchestration with Foundry IQ in Microsoft Foundry. Navigate complex, distributed data across Azure stores, SharePoint, OneLake, MCP servers, and even the web, all through a single knowledge base that handles query planning and iteration for you. Reuse the Azure AI Search assets you already have, build new knowledge bases with minimal setup, and control how much reasoning effort your agents apply. As you develop, you can rely on iterative retrieval only when it improves results, saving time, tokens, and development complexity. Pablo Castro, Azure AI Search CVP and Distinguished Engineer, joins Jeremy Chapman to share how to build smarter, more capable AI agents, with higher-quality grounded answers and less engineering overhead. ► Link References To learn more check out For more details on the evaluation metric discussed on this show, read our blog at For more on Microsoft Foundry go to ► Unfamiliar with Microsoft Mechanics? As Microsoft's official video series for IT, you can watch and share valuable content and demos of current and upcoming tech from the people who build it at Microsoft. • Subscribe to our YouTube: • Talk with other IT Pros, join us on the Microsoft Tech Community: • Watch or listen from anywhere, subscribe to our podcast: ► Keep getting this insider knowledge, join us on social: • Follow us on Twitter: • Share knowledge on LinkedIn: https://www.linkedin.com/company/microsoft-mechanics/ • Enjoy us on Instagram: • Loosen up with us on TikTok: ► QUICK LINKS: - Foundry IQ in Microsoft Foundry - How it's evolved - Knowledge bases in Foundry IQ - Azure AI Search and retrieval stack - How it works - Visualization tool demo - Build a knowledge base - Evaluating results - Wrap up /episode/index/show/microsoftmechanics/id/39250825

Run local AI on any PC or Mac - Microsoft Foundry Local 11/20/2025

Microsoft Sentinel platform – Unified, Graph-enabled, and AI-ready Security 11/20/2025

Replace your VPN - Global Secure Access in Microsoft Entra 11/19/2025

Synced Passkeys in Microsoft Entra for Phishing-resistant MFA 11/19/2025

New Data Security Posture Management | Microsoft Purview 11/19/2025

Windows 365 updates | AI‑Ready Work, Apps on Demand, Resilient Access 11/18/2025

Microsoft Excel Power User Updates | Agent Mode, Copilot Function & Formula AI 10/30/2025

How to move Active Directory Source of Authority to Microsoft Entra ID and why 10/08/2025

Microsoft Security Copilot agents 10/03/2025

Copilot now included with Word, Excel, PowerPoint, Outlook & OneNote | Microsoft 365 & Office 365 10/01/2025

New collaborative agents in Microsoft 365 Copilot 09/23/2025

Choosing the right Virtual Machine on Azure 09/19/2025

Build autonomous agents in Copilot Studio | Your MCPs, your models & multi-agent 08/19/2025

New data lake in Microsoft Sentinel 07/24/2025

New Surface Laptop 5G for Business, Copilot+ PC 07/24/2025

NEW Conditional Access Optimization Agent in Microsoft Entra + Security Copilot in Entra updates 07/15/2025

How SharePoint Embedded works and how to build AI apps on it 07/07/2025

How SharePoint Embedded works and how to build AI apps on it Build AI-powered apps that connect directly to Microsoft 365 content without moving files or compromising security, using SharePoint Embedded. SharePoint Embedded is a fully managed, cloud-based, API-only document management system that lets you securely integrate your custom web or mobile apps, whether built on Azure or other clouds, with Microsoft 365 file storage. It’s especially ideal for ISVs building multi-tenant apps because content stays within each customer’s Microsoft 365 tenant. Design apps that include Microsoft 365 Copilot and agent capabilities, connected Office experiences like Word, and Microsoft Purview compliance and data protection, all within your own user experience. Use built-in retrieval augmented generation (RAG) or bring your own models to create intelligent, secure solutions that reason over your business content, support real-time co-authoring, and scale with granular permissions and storage control. Jeremy Chapman, Microsoft 365 Director, shares how to build intelligent, secure solutions that integrate seamlessly with Microsoft 365 content and services. ► QUICK LINKS: - Keep content secure & compliant without moving it - Build fully custom experiences - Use built-in vector indexing and RAG - Use your models with Copilot's vector search - How it works - How the app is built - Microsoft Copilot retrieval API - Security and compliance - Wrap up ► Link References Build your first agent at ► Unfamiliar with Microsoft Mechanics? As Microsoft's official video series for IT, you can watch and share valuable content and demos of current and upcoming tech from the people who build it at Microsoft. • Subscribe to our YouTube: • Talk with other IT Pros, join us on the Microsoft Tech Community: • Watch or listen from anywhere, subscribe to our podcast: ► Keep getting this insider knowledge, join us on social: • Follow us on Twitter: • Share knowledge on LinkedIn: • Enjoy us on Instagram: • Loosen up with us on TikTok: /episode/index/show/microsoftmechanics/id/37308105

Secure your AI apps with user-context-aware controls | Microsoft Purview SDK 06/26/2025

Microsoft Intune data-driven management | Device Query & Copilot 06/17/2025

Introducing Microsoft Purview Alert Triage Agents for Data Loss Prevention & Insider Risk Management 06/16/2025

Fix Identity Sprawl + Optimize Microsoft Entra 06/10/2025

What's new in SQL Server 2025 06/03/2025

What runs ChatGPT, Sora, DeepSeek & Llama on Azure? (feat. Mark Russinovich) 05/29/2025

What runs ChatGPT, Sora, DeepSeek & Llama on Azure? (feat. Mark Russinovich) Build and run your AI apps and agents at scale with Azure. Orchestrate multi-agent apps and high-scale inference solutions using open-source and proprietary models, no infrastructure management needed. With Azure, connect frameworks like Semantic Kernel to models from DeepSeek, Llama, OpenAI’s GPT-4o, and Sora, without provisioning GPUs or writing complex scheduling logic. Just submit your prompt and assets, and the models do the rest. Using Azure’s Model as a Service, access cutting-edge models, including brand-new releases like DeepSeek R1 and Sora, as managed APIs with autoscaling and built-in security. Whether you’re handling bursts of demand, fine-tuning models, or provisioning compute, Azure provides the capacity, efficiency, and flexibility you need. With industry-leading AI silicon, including H100s, GB200s, and advanced cooling, your solutions can run with the same power and scale behind ChatGPT. Mark Russinovich, Azure CTO, Deputy CISO, and Microsoft Technical Fellow, joins Jeremy Chapman to share how Azure's latest AI advancements and orchestration capabilities unlock new possibilities for developers. ► QUICK LINKS: 00:00 - Build and run AI apps and agents in Azure 00:26 - Narrated video generation example with multi-agentic, multi-model app 03:17 - Model as a Service in Azure 04:02 - Scale and performance 04:55 - Enterprise grade security 05:17 - Latest AI silicon available on Azure 06:29 - Inference at scale 07:27 - Everyday AI and agentic solutions 08:36 - Provisioned Throughput 10:55 - Fractional GPU Allocation 12:13 - What's next for Azure? 12:44 - Wrap up ► Link References For more information, check out ► Unfamiliar with Microsoft Mechanics? As Microsoft's official video series for IT, you can watch and share valuable content and demos of current and upcoming tech from the people who build it at Microsoft. • Subscribe to our YouTube: • Talk with other IT Pros, join us on the Microsoft Tech Community: • Watch or listen from anywhere, subscribe to our podcast: ► Keep getting this insider knowledge, join us on social: • Follow us on Twitter: • Share knowledge on LinkedIn: • Enjoy us on Instagram: • Loosen up with us on TikTok: /episode/index/show/microsoftmechanics/id/36764530

New Microsoft 365 Copilot Tuning | Create fine-tuned models to write like you do 05/20/2025

New Microsoft 365 Copilot Tuning | Create fine-tuned models to write like you do Create fine-tuned, task-specific models that write like you by teaching models using expert knowledge, tone, and structure - with reference information directly attached to the models themselves using Microsoft 365 Copilot Tuning. Fine-tuning adds new skills to foundational models, simulating experience in the tasks you teach the model to do. This complements Retrieval Augmented Generation, which in real-time uses search to find related information, then add that to your prompts for context. Fine-tuning helps ensure that responses meet your quality expectations for specific repeatable tasks, without needing to be prompting expert. It's great for drafting complex legal agreements, writing technical documentation, authoring medical papers, and more - using detailed, often lengthy precedent files along with what you teach the model. Using Copilot Studio, anyone can create and deploy these fine-tuned models to use with agents without data science or coding expertise. There, you can teach models using data labeling, ground them in your organization’s content - while keeping the information in-place and maintaining data security and access policies. The information contained in the task-specific models that you create stay private to your team and organization. Task-specific models and related information are only accessible to the people and departments you specify - and information is not merged into shared large language models or used for model training. Jeremy Chapman, Director on the Microsoft 365 product team, shows how this simple, zero-code approach helps the agents you build write and reason like your experts—delivering high-quality, detailed responses. ► QUICK LINKS: - Fine-tune Copilot - Tailor Copilot for specialized tasks - How it works - Create a task-specific model - Data labeling - Build agents that use your fine-tuned model - Wrap up ► Unfamiliar with Microsoft Mechanics? As Microsoft's official video series for IT, you can watch and share valuable content and demos of current and upcoming tech from the people who build it at Microsoft. • Subscribe to our YouTube: • Talk with other IT Pros, join us on the Microsoft Tech Community: • Watch or listen from anywhere, subscribe to our podcast: ► Keep getting this insider knowledge, join us on social: • Follow us on Twitter: • Share knowledge on LinkedIn: • Enjoy us on Instagram: • Loosen up with us on TikTok: https://www.tiktok.com/@msftmechanics /episode/index/show/microsoftmechanics/id/36645285

Agent management updates | Copilot Control System 05/06/2025

Data security for agents and 3rd party AI in Microsoft Purview 05/06/2025

Microsoft Mechanics Podcast

TOPICS