Microsoft Mechanics Podcast Microsoft Mechanics

Use your files, emails, chats and meeting information automatically or with direct references using Copilot prompts in Microsoft 365 apps. You don't need to copy information then paste it into a browser tool or upload work files and images into other generative AI experiences. Instead, directly from Teams, Word, PowerPoint and other Microsoft 365 apps, you can leverage not only your opened file, email, chat or meeting, but also other work data that you have permissions to in SharePoint and OneDrive. Copilot retrieves and synthesizes information across emails, chats, and files, so you can generate presentations, respond to emails, and catch up on meetings. The Copilot process also follows your organization's policies for data protection and compliance, eliminating the need and added risk of bringing your work data to those tools.
Mary David Pasch, Principal Product Manager from the Copilot Platform team, joins Jeremy Chapman to share how Copilot enhances collaboration and efficiency, making complex tasks like document creation and information retrieval effortless and secure.
 
► QUICK LINKS:
00:00 - Leverage your work data with Copilot
00:51 - How Copilot augments your prompts
02:22 - Automatically works across your files
03:03 - Meeting recaps with Copilot in Teams
03:59 - Meeting summaries with Copilot in Teams
04:57 - Incorporate specific info from work data
06:53 - Convert written docs to PowerPoint presentations
09:07 - Recommended prompts
10:29 - Standalone Copilot chat experience
12:11 - Stay within your Microsoft 365 data security boundary
12:39 - Wrap up
 
► Link References

For more go to Copilot Lab at https://copilot.cloud.microsoft 
Watch our full series on Microsoft Mechanics at https://aka.ms/M365CopilotMechanics 
 
► 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

Improve search capabilities for your PostgreSQL-backed applications using vector search and embeddings generated in under 10 milliseconds without sending data outside your PostgreSQL instance. Integrate real-time translation, sentiment analysis, and advanced AI functionalities securely within your database environment with Azure Local AI and Azure AI Service. Combine the Azure Local AI extension with the Azure AI extension to maximize the potential of AI-driven features in your applications, such as semantic search and real-time data translation, all while maintaining data security and efficiency.
Joshua Johnson, Principal Technical PM for Azure Database for PostgreSQL, demonstrates how you can reduce latency and ensure predictable performance by running locally deployed models, making it ideal for highly transactional applications.
 
► QUICK LINKS: 
00:00 - Improve search for PostgreSQL
01:21 - Increased speed
02:47 - Plain text descriptive query
03:20 - Improve search results
04:57 - Semantic search with vector embeddings
06:10 - Test it out
06:41 - Azure local AI extension with Azure AI Service
07:39 - Wrap up
 
► Link References
Check out our previous episode on Azure AI extension at https://aka.ms/PGAIMechanics 
Get started with Azure Database for PostgreSQL - Flexible Server at https://aka.ms/postgresql 
To stay current with all the updates, check out our blog at https://aka.ms/azurepostgresblog
 
► 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

Ensure high-accuracy, efficient vector search at massive scale with Azure Cosmos DB. Leveraging Microsoft’s DiskANN, more IO traffic moves to disk to maximize storage capacity and enable high-speed similarity searches across all data, reducing memory dependency. This technology, powering global services like Microsoft 365, is now integrated into Azure Cosmos DB, enabling developers to build scalable, high-performance applications with built-in vector search, real-time fraud detection, and robust multi-tenancy support.
Join Kirill Gavrylyuk, VP for Azure Cosmos DB, as he shares how Azure Cosmos DB with DiskANN offers unparalleled speed, efficiency, and accuracy, making it the ideal solution for modern AI-driven applications.
 
► QUICK LINKS: 
00:00 - Latest Cosmos DB optimizations with DiskANN
02:09 - Where DiskANN approach is beneficial
04:07 - Efficient querying
06:02 - DiskANN compared to HNSW
07:41 - Integrate DiskANN into a new or existing app
08:39 - Real-time transactional AI scenario
09:29 - Building a fraud detection sample app
10:59 - Vectorize transactions for anomaly detection
12:49 - Scaling to address high levels of traffic
14:05 - Manage multi-tenancy
15:35 - Wrap up
 
► Link References
Check out https://aka.ms/DiskANNCosmosDB
Try out apps at https://aka.ms/DiskANNCosmosDBSamples
 
► 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

Quickly spot real-time indicators of issues as they unfold, without the need to poll or manually monitor changes in your data and without writing a single line of code. That’s what the new Real-Time Intelligence service in Microsoft Fabric is all about. It extends Microsoft Fabric to the world of streaming data across your IoT and operational systems. Whether you are a data analyst or business user, you can easily explore high-granularity, high-volume data and spot issues before they impact your business. And as a Data engineer, you can more easily track system level changes across your data estate to manage and improve your pipelines.
Courtney Berg, from the Microsoft Fabric product team, joins Jeremy Chapman to explore all of the updates, explain how Real-Time Intelligence adds to what was possible with Data Activator and Microsoft Synapse Real-Time Analytics and demonstrates how this would work to derive insights and take actions automatically in a scenario with multiple live data streams across different data types.
► QUICK LINKS:
00:00 - Real-Time Intelligence
00:54 - How it’s different
02:07 - Eventstream and Real-Time Hub
03:27 - Synapse Real-Time Analytics
04:03 - See it in action
05:25 - Use Copilot to stay updated
06:28 - Filter data and set up alerts
08:25 - Sophisticated Logic and Data Integration
09:48 - Data integration to Real-Time Hub
11:23 - Workflow automation
12:18 - System events
13:30 - Additional areas of use for Real-Time Intelligence
14:02 - Wrap up
 
► Link References
Check out Real-Time Intelligence at https://aka.ms/RealTimeIntelligence
For all things Microsoft Fabric, go to https://microsoft.com/fabric


► 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
 

Optimize the sales process by integrating internal and external data with Copilot for Sales. Create enriched email summaries, customized meeting prep documents, and actionable meeting recaps to improve customer interactions. Copilot uses AI to generate insights and suggest actions based on comprehensive data, ensuring sales teams have all the necessary information at their fingertips. Create custom AI experiences using Copilot Studio with zero code. By adding Copilot extensions, users can connect to external data sources and build tailored AI skills.
Eric Boocock, Copilot for Sales Principal Program Manager, shares how Copilot for Sales works and how to build Copilot extensions to connect with other systems for personalized experiences.
► QUICK LINKS:
00:00 - Copilot for Sales
00:36 - Baseline experiences
02:13 - Bring in external data
03:26 - Use Copilot to respond to emails
03:54 - Meeting prep and meeting recap
04:52 - Security and Responsible AI
06:27 - Copilot extensions
09:09 - Publish Copilot extensions
09:40 - Wrap up
 
► Link References
Check out https://aka.ms/CopilotforSalesExtensibility 
Stay updated on monthly releases at https://aka.ms/CopilotforSalesUpdates
 
► 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

Now you can build your own highly specialized copilot using Microsoft Copilot Studio or Visual Studio Code. See how you can tailor Copilot for Microsoft 365 experiences to focus on specific tasks and use external data integration through Copilot extensions. Enhance productivity by leveraging large language models and Microsoft Graph for personalized responses. With plugins and connectors, extend Copilot's capabilities to streamline tasks and automate actions, all while maintaining context and boosting efficiency.
Abram Jackson, Principal Product Manager for Microsoft 365 shows how you can get started building Copilot extensions.
 
► QUICK LINKS:
00:00 - Copilot extensions
01:08 - Types of Copilot extensions
01:59 - Microsoft Graph connectors
03:20 - Plugins
04:14 - Specialized copilot
04:54 - Multiple customized copilots working together
05:42 - How to build Copilot extensions
06:45 - Plug into data-external or inside of Microsoft 365
07:31 - IDE/Visual Studio Code
08:57 - Wrap up
 
► Link References
To get started, check out https://copilotstudio.microsoft.com
 
► 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