Streamline your workflow and enhance team collaboration with one-click AI agents in Microsoft 365 Copilot. Automate responses, generate detailed documents, and maintain up-to-date content without moving files outside Microsoft 365. Agents utilize your existing content to provide accurate and efficient outputs, saving you time and ensuring consistency. Integrate them into Microsoft Teams to facilitate real-time information sharing and collaboration.

CJ Tan, Microsoft SharePoint and OneDrive GPM, shares the steps to get started building custom AI agents.

► QUICK LINKS: 00:00 - Create specialist agents in one click 00:42 - How to create an agent 02:12 - Data security & version control 02:39 - Customize your agent 04:14 - Access and permissions 05:39 - Test it out 06:23 - Use agents in Teams 07:50 - Agent files 08:25 - Wrap up

► Link References

For more ideas and details for building your own agents, check out https://aka.ms/SharePointAgentsAdoption

► 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: https://www.youtube.com/c/MicrosoftMechanicsSeries

• Talk with other IT Pros, join us on the Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog

• Watch or listen from anywhere, subscribe to our podcast: https://microsoftmechanics.libsyn.com/podcast

► Keep getting this insider knowledge, join us on social:

• Follow us on Twitter: https://twitter.com/MSFTMechanics 

• Share knowledge on LinkedIn: https://www.linkedin.com/company/microsoft-mechanics/

• Enjoy us on Instagram: https://www.instagram.com/msftmechanics/

• Loosen up with us on TikTok: https://www.tiktok.com/@msftmechanics

Spin up SQL databases in seconds with Microsoft Fabric, seamlessly integrating your operational and analytical data across multiple clouds. Use AI to scale, tune, and secure databases, so you can focus on building powerful, data-rich applications without the manual management overhead.

Create and host API endpoints directly from your SQL database in one click, enabling seamless interaction with your data using popular frameworks like React. Integrate your database management into your CI/CD pipelines with ease, ensuring high availability and streamlined development processes.

Anna Hoffman, Principal GPM, SQL database in Microsoft Fabric, joins Jeremy Chapman, Director of Microsoft 365, to show you how to get started.

► QUICK LINKS:  00:00 - SQL database in Microsoft Fabric 00:38 - A new class of autonomous database 01:44 - Spin up a database in seconds 03:09 - Use APIs to read and write data 05:00 - Integrate into CI/CD pipeline & source control 05:41 - Bring in data from across your data estate 06:50 - Vector-based semantic search with keyword search 09:03 - See a finished app 11:12 - Query performance 12:31 - Security and control 13:04 - Wrap up

► Link References

Sign up for a free trial at https://aka.ms/SQLinFabric

 ► 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: https://www.youtube.com/c/MicrosoftMechanicsSeries • Talk with other IT Pros, join us on the Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog • Watch or listen from anywhere, subscribe to our podcast: https://microsoftmechanics.libsyn.com/podcast

► Keep getting this insider knowledge, join us on social: • Follow us on Twitter: https://twitter.com/MSFTMechanics • Share knowledge on LinkedIn: https://www.linkedin.com/company/microsoft-mechanics/ • Enjoy us on Instagram: https://www.instagram.com/msftmechanics/ • Loosen up with us on TikTok: https://www.tiktok.com/@msftmechanics  

Increase scalability, optimize performance, and integrate advanced AI features with Azure Database for PostgreSQL Flexible Server. Scale up with SSD v2 for up to 4x more transactions per second and significantly lower latency. Scale out effortlessly with elastic clusters using Citus, distributing workloads across multiple servers at no extra cost. Optimize performance with Automatic Index Tuning, reducing server utilization and enhancing efficiency. Leverage advanced AI features like DiskANN, semantic reranking, and Graph RAG to build better AI apps.

Charles Feddersen, Partner Director of Program Management for Postgres at Microsoft, joins Jeremy Chapman to show you how to build scalable, high-performance AI apps on Azure PostgreSQL Flexible Server today. 

► QUICK LINKS: 00:00 - Azure Database for Postgres Flexible Server 00:39 - Updates to PostGreSQL 01:50 - Faster storage with SSD v2 03:06 - Scale out workloads using elastic cluster 03:59 - Provision an elastic cluster 05:34 - Scale "in-place" 07:12 - Eliminate redundant indexes 07:44 - Optimize server parameters 09:52 - Improve AI apps with Postgres Flexible Server 11:40 - Code behind queries using PG Admin 12:31 - Scale workloads 13:36 - Wrap up ► Link References Get started at https://aka.ms/azurepostgresblog Access code at https://aka.ms/AzurePostgresAI ► 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: https://www.youtube.com/c/MicrosoftMechanicsSeries • Talk with other IT Pros, join us on the Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog • Watch or listen from anywhere, subscribe to our podcast: https://microsoftmechanics.libsyn.com/podcast

► Keep getting this insider knowledge, join us on social: • Follow us on Twitter: https://twitter.com/MSFTMechanics • Share knowledge on LinkedIn: https://www.linkedin.com/company/microsoft-mechanics/ • Enjoy us on Instagram: https://www.instagram.com/msftmechanics/

Stay ahead of evolving risks and mitigate vulnerabilities with Microsoft Purview Data Security Posture Management (DSPM). Gain prioritized visibility into data security risks, track unprotected sensitive information, and receive actionable insights. With built-in classifiers, automated risk assessments, and AI-powered capabilities like Security Copilot, you can identify and mitigate threats, ensuring a compliant data security environment.

Talhah Mir, Microsoft Purview’s Principal Group Product Manager, shows how to transform your data security strategy with automated, intelligent risk management and maintain continuous protection across your organization.

► QUICK LINKS: 00:00 - Build and maintain a strong data security posture 01:25 - Start in Microsoft Purview Portal 02:14 - Microsoft Purview solutions 03:39 - Analytic reports 04:39 - Take action 05:30 - AI app-focused view 06:13 - View trends 06:59 - Add Security Copilot capabilities 09:37 - Wrap up

► Link References

Get started at https://aka.ms/DSPM

► 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: https://www.youtube.com/c/MicrosoftMechanicsSeries

• Talk with other IT Pros, join us on the Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog

• Watch or listen from anywhere, subscribe to our podcast: https://microsoftmechanics.libsyn.com/podcast

► Keep getting this insider knowledge, join us on social:

• Follow us on Twitter: https://twitter.com/MSFTMechanics 

• Share knowledge on LinkedIn: https://www.linkedin.com/company/microsoft-mechanics/

• Enjoy us on Instagram: https://www.instagram.com/msftmechanics/

• Loosen up with us on TikTok: https://www.tiktok.com/@msftmechanics

Windows 365 Link is the first Cloud PC device purpose-built for Windows 365. It can connect to your Cloud PC in seconds with a simple sign-in, accessing a familiar Windows Desktop with high-fidelity performance. Windows 365 Link offers seamless setup and streamlined management through Microsoft Intune, ensuring your IT environment is efficiently maintained alongside other PCs. As a stateless and adminless device, it does not store user profile data or install additional software.

Optimize your work experience with passwordless authentication, high-performance video conferencing, and support for essential peripherals. Designed with a robust security posture, Windows 365 Link provides data protection with features like Secure Boot, BitLocker encryption, Hypervisor-based Code Integrity, and more.

Jalleen Ringer, Partner GPM for Windows Cloud Endpoints, shows how Windows 365 Link is the ideal choice for secure, scalable, and efficient cloud computing.

► QUICK LINKS: 00:00 - Windows 365 Link—First Cloud PC device purpose-built for Windows 365 00:55 - What it's like to use Windows 365 Link 02:32 - Ports and connectivity 03:18 - Set it up 03:48 - Device management 05:26 - Wrap up

► Link References

Check out https://aka.ms/Windows365Link

► 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: https://www.youtube.com/c/MicrosoftMechanicsSeries

• Talk with other IT Pros, join us on the Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog

• Watch or listen from anywhere, subscribe to our podcast: https://microsoftmechanics.libsyn.com/podcast

► Keep getting this insider knowledge, join us on social:

• Follow us on Twitter: https://twitter.com/MSFTMechanics 

• Share knowledge on LinkedIn: https://www.linkedin.com/company/microsoft-mechanics/

• Enjoy us on Instagram: https://www.instagram.com/msftmechanics/

• Loosen up with us on TikTok: https://www.tiktok.com/@msftmechanics

Provide tailored Cloud PC experiences for diverse workforce needs with Windows 365 Frontline. With shared mode, offer cost-effective, on-demand Cloud PCs that reset after each session—ideal for frontline and part-time staff needing intermittent access. Dedicated mode delivers a personalized, consistent desktop experience for employees requiring prolonged use, all managed through Microsoft Intune. As an IT admin, set precise access policies, automate session timeouts, and adjust resources based on role requirements.

Sam Tulimat, Cloud Endpoints Principal PM Lead, shows how Windows 365 Frontline is designed to optimize resources, streamline workflows, and meet the unique needs of any team, ensuring every employee has the tools they need, when and where they need them.

► QUICK LINKS: 00:00 - One Cloud PC for multiple users 01:01 - Optimize costs with shared Cloud PCs 01:44 - Role-specific Cloud PCs 02:15 - Dedicated mode configuration 04:40 - Shared mode configuration steps 06:25 - Provisioning Policies 07:15 - Options to reprovision Cloud PCs 07:49 - Wrap up

► Link References

To get started, check out https://aka.ms/Windows365Frontline 

► 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: https://www.youtube.com/c/MicrosoftMechanicsSeries

• Talk with other IT Pros, join us on the Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog

• Watch or listen from anywhere, subscribe to our podcast: https://microsoftmechanics.libsyn.com/podcast

► Keep getting this insider knowledge, join us on social:

• Follow us on Twitter: https://twitter.com/MSFTMechanics 

• Share knowledge on LinkedIn: https://www.linkedin.com/company/microsoft-mechanics/

• Enjoy us on Instagram: https://www.instagram.com/msftmechanics/

• Loosen up with us on TikTok: https://www.tiktok.com/@msftmechanics

Minimize risks that come with oversharing and potential data loss. Use Microsoft Purview and its new Data Security Posture Management (DSPM) for AI insights, along with new Data Loss Prevention policies for Microsoft 365 Copilot, and SharePoint Advanced Management, which is now included with Microsoft 365 Copilot. Automate site access reviews at scale and add controls to restrict access to sites if they contain highly sensitive information.

Erica Toelle, Microsoft Purview Senior PM, shows how to control data visibility, automate site access reviews, and fine-tune permissions with Pilot, Deploy, Optimize phases.

► QUICK LINKS:

00:00 — Minimize risk of oversharing 01:24 — Oversharing scenarios 04:03 — How oversharing can occur 05:38 — Restrict discovery & limit access 06:36 — Scope sites 07:15 — Pilot phase 08:16 — Deploy phase 09:17 — Site access reviews 10:00 — Optimize phase 10:54 — Wrap up

► Link References

Check out https://aka.ms/DeployM365Copilot 

Watch our show on the basics of oversharing at https://aka.ms/SMBoversharing

► 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: https://www.youtube.com/c/MicrosoftMechanicsSeries • Talk with other IT Pros, join us on the Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog • Watch or listen from anywhere, subscribe to our podcast: https://microsoftmechanics.libsyn.com/podcast

► Keep getting this insider knowledge, join us on social: • Follow us on Twitter: https://twitter.com/MSFTMechanics • Share knowledge on LinkedIn: https://www.linkedin.com/company/microsoft-mechanics/ • Enjoy us on Instagram: https://www.instagram.com/msftmechanics/ • Loosen up with us on TikTok: https://www.tiktok.com/@msftmechanics

Millions of people use Azure AI Search every day without knowing it. You can enable your apps with the same search that enables retrieval-augmented generation (RAG) capabilities when you build Custom GPTs or attach files in your ChatGPT prompts.

Pablo Castro, Microsoft CVP and Distinguished Engineer Azure AI Search, joins Jeremy Chapman to share how with Azure AI Search, you can create custom applications that retrieve the most relevant information quickly and accurately, even from billions of records.

Manage massive-scale datasets while maintaining high-quality search results with ultra-compact, binary quantized vector search indexes that use Matryoshka Representation Learning (MRL) and oversampling to equal the search accuracy of vector indexes up to 96 times larger. These approaches drive significant cost savings by optimizing your vector indexes without compromising quality.

► QUICK LINKS: 00:00 - RAG powered by Azure AI Search 00:50 - Azure AI Search role in ChatGPT 02:01 - Azure AI Search use case - AT&T 03:27 - Start in Azure Portal 04:35 - Massive scale and vector index 06:08 - Scalar & Binary Quantization 07:21 - Martyoshka technique 09:07 - Oversampling 11:31 - How to build an app using Azure AI Search 13:00 - See it in action 14:28 - Enable binary quantization with oversampling 14:54 - Wrap up

► Link References

Get sample code on GitHub at https://aka.ms/SearchQuantizationSample 

Check out search solutions at https://aka.ms/AzureAISearch

► 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: https://www.youtube.com/c/MicrosoftMechanicsSeries

• Talk with other IT Pros, join us on the Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog

• Watch or listen from anywhere, subscribe to our podcast: https://microsoftmechanics.libsyn.com/podcast

► Keep getting this insider knowledge, join us on social:

• Follow us on Twitter: https://twitter.com/MSFTMechanics 

• Share knowledge on LinkedIn: https://www.linkedin.com/company/microsoft-mechanics/

• Enjoy us on Instagram: https://www.instagram.com/msftmechanics/

• Loosen up with us on TikTok: https://www.tiktok.com/@msftmechanics

Take a look at how wave two of Microsoft 365 Copilot can specifically help your small business by leveraging the secure application of generative AI with your work data. Use it to author presentations and content, reduce digital debt to focus on what’s important as you engage with customers, and automate everyday tasks and processes. For IT, see how to light up Microsoft 365 Copilot in your tenant, and get tips and resources for onboarding your organization.

Mary David Pasch, Principal Product Manager for Microsoft 365 Copilot, joins Jeremy Chapman to share how to use Copilot to save time, drive productivity, and foster stronger connections with your customers.

► QUICK LINKS: 00:00 - Microsoft 365 Copilot Small Business Guide 00:53 - Save time 02:14 - Privacy & safety 05:03 - How Microsoft 365 Copilot can assist you 06:24 - Work smarter, improve skill sets 08:13 - Create custom experiences 08:48 - Enable Copilot and onboard users 10:28 - How to apply Copilot to specific areas in your company 12:18 - Guidance & resources 14:07 - Wrap up 

► Link References

Watch our whole series at https://aka.ms/CopilotSMBMechanics

Check out our show on preparing for Copilot at https://aka.ms/SMBOversharingMechanics See how to create custom experiences at https://aka.ms/Wave2Mechanics

Use role-based scenario guidance at https://aka.ms/AIforAll Get a Success Kit at https://aka.ms/CopilotSMBSuccesskit

Sign up for or watch Quickstart Training at https://aka.ms/QuickStartCopilot 

► 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: https://www.youtube.com/c/MicrosoftMechanicsSeries

• Talk with other IT Pros, join us on the Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog

• Watch or listen from anywhere, subscribe to our podcast: https://microsoftmechanics.libsyn.com/podcast

► Keep getting this insider knowledge, join us on social:

• Follow us on Twitter: https://twitter.com/MSFTMechanics 

• Share knowledge on LinkedIn: https://www.linkedin.com/company/microsoft-mechanics/

• Enjoy us on Instagram: https://www.instagram.com/msftmechanics/

• Loosen up with us on TikTok: https://www.tiktok.com/@msftmechanics

What are prompt injection attacks and how do you stop them? How do you avoid deceptive responses? Can AI traffic be end-to-end encrypted? We'll answer these questions and more with technical demonstrations to make it real.

Mark Russinovich will show you how to develop and deploy AI applications that prioritize safety, privacy, and integrity. Leverage real-time safety guardrails to filter harmful content and proactively prevent misuse, ensuring AI outputs are trustworthy. The integration of confidential inferencing enables users to maintain data privacy by encrypting information during processing, safeguarding sensitive data from exposure. Enhance AI solutions with advanced features like Groundedness detection, which provides real-time corrections to inaccurate outputs, and the Confidential Computing initiative that extends verifiable privacy across all services.

Mark Russinovich, Azure CTO, joins Jeremy Chapman to share how to build secure AI applications, monitor and manage potential risks, and ensure compliance with privacy regulations.

► QUICK LINKS: 00:00 - Keep data safe and private 01:19 - Azure AI Content Safety capability set 02:17 - Direct jailbreak attack 03:47 - Put controls in place 04:54 - Indirect prompt injection attack 05:57 - Options to monitor attacks over time 06:22 - Groundedness detection 07:45 - Privacy—Confidential Computing 09:40 - Confidential inferencing Model-as-a-service 11:31 - Ensure services and APIs are trustworthy 11:50 - Security 12:51 - Web Query Transparency 13:51 - Microsoft Defender for Cloud Apps 15:16 - Wrap up

► Link References

Check out https://aka.ms/MicrosoftTrustworthyAI 

For verifiable privacy, go to our blog at https://aka.ms/ConfidentialInferencing 

► 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: https://www.youtube.com/c/MicrosoftMechanicsSeries

• Talk with other IT Pros, join us on the Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog

• Watch or listen from anywhere, subscribe to our podcast: https://microsoftmechanics.libsyn.com/podcast

► Keep getting this insider knowledge, join us on social:

• Follow us on Twitter: https://twitter.com/MSFTMechanics 

• Share knowledge on LinkedIn: https://www.linkedin.com/company/microsoft-mechanics/

• Enjoy us on Instagram: https://www.instagram.com/msftmechanics/

• Loosen up with us on TikTok: https://www.tiktok.com/@msftmechanics

With more than 1700 models to choose from on Azure, selecting the right one is key to enabling the right capabilities, at the right price point, and with the right protections in place. That's where the Azure AI model catalog and model benchmarks can help.

With Azure AI, you can seamlessly integrate powerful GenAI models into your app development process, making your applications smarter, more efficient, and highly scalable. Access a vast selection of AI models, from sophisticated large language models to efficient small models that can run offline.

Matt McSpirit, Microsoft Azure expert, shows how to compare and select the right AI model for your specific needs. Azure AI's model benchmarks evaluate models on accuracy, coherence, groundedness, fluency, relevance, and similarity. Experiment with different models in Azure AI Studio or your preferred coding environment, and optimize costs with serverless pricing options.

► QUICK LINKS:

00:00 - Build GenAI powered apps 00:53 - Model choice 02:11 - Use your environments of choice 02:44 - Choose the right AI model 05:28 - Compare models 08:04 - Wrap up

► Link References Get started at https://ai.azure.com  

See data, privacy, and security for use of models at https://aka.ms/AzureAImodelcontrols

► 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: https://www.youtube.com/c/MicrosoftMechanicsSeries • Talk with other IT Pros, join us on the Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog • Watch or listen from anywhere, subscribe to our podcast: https://microsoftmechanics.libsyn.com/podcast

► Keep getting this insider knowledge, join us on social:

• Follow us on Twitter: https://twitter.com/MSFTMechanics • Share knowledge on LinkedIn: https://www.linkedin.com/company/microsoft-mechanics • Enjoy us on Instagram: https://www.instagram.com/msftmechanics • Loosen up with us on TikTok: https://www.tiktok.com/@msftmechanics