Am really keen on exposing PowerApps / Flow news - this was provided from Microsoft Flow. You can read out the full post available on this link:
https://powerautomate.microsoft.com/en-us/blog/generative-ai-prompts-to-automate-content-processing/
AI Builder releases new GPT powered AI actions, giving citizen developers advanced tools to automate content processing with GPT-4.
Starting your organization’s AI transformation may seem challenging when users want to use AI tools now and IT teams want to ensure data security. AI is spreading surprisingly quickly, with 75% of knowledge workers reporting that they use AI at work.¹ But if your users are leveraging unsanctioned AI tools, it puts sensitive business data at risk—once it goes into an AI model, there is no getting it back. And if you block AI services to prioritize security, you risk falling behind other organizations who are moving full speed ahead with AI.
You can give users the AI tools they want today while also protecting sensitive data with Microsoft Copilot with commercial data protection. Best of all, it’s available at no additional cost if you’re on an eligible Microsoft 365 or Office 365 subscription, and it’s easy to roll out using the Copilot adoption kit.
We know all the AI options out there might be confusing, so we have a new Copilot explainer video available as part of Microsoft Build to help provide greater clarity about how users can be more creative at work and save time using AI. You can watch the new Copilot explainer video at aka.ms/Copilot/BuildVideo.
Bring AI-powered web chat to your users today
Rolling out Copilot is easy. When an eligible user signs in with their work or school account (Entra ID), Copilot automatically adds commercial data protection. This means prompts and responses are not saved, no one at Microsoft has eyes-on access, and data is not used to train the underlying large language model. You can learn more about managing Copilot on Microsoft Learn.
Give your employees a productivity and creativity boost with Copilot
People have a lot on their plate at work, and Copilot with commercial data protection uses advanced AI models like GPT-4 and DALL-E 3 to provide powerful AI tools to help tackle tasks of all sizes.
With AI in their toolkit, users are already recognizing gains at work with 90% reporting that AI helps them to save time,² and 84% reporting that it helps them be more creative.³ They’re using it to do things like:
You and your users can sign in and try Copilot today at copilot.microsoft.com.
Pair Copilot with Microsoft Edge for added security capabilities
Users get additional security features when they access Copilot through the Microsoft Edge sidebar, including capabilities like native support for Data Loss Prevention (DLP) policies that add protections to prevent sensitive content from being summarized, copied, pasted, or captured by screenshot.
Plus, Edge offers controls for managing Copilot and third-party AI services with Edge management service and new user features such as real-time translation of videos using AI and AI-powered Workspaces. Learn more about Microsoft Edge and new announcements at Build.
Kickstart your AI journey with the Copilot adoption kit
If you’re ready to train your users on how to make the most of AI at work, use the customizable resources in the Copilot adoption kit. Available in nine languages, this kit includes ready-made resources such as a training presentation, company-wide communications, tip sheets, and more. The kit can help you unlock the full potential of AI for your users and accelerate your AI transformation.
¹, ², ³: 2024 Work Trend Index Annual Report (Microsoft, LinkedIn)
Ross Smith interviews Jason Weum on the deployment of artificial intelligence in support at Microsoft.
Ross Smith: Hey Jason,. as a leader in the deployment of AI in Customer Support, I’m interested in learning more about your background and how you started engaging with AI..
Jason Weum: My background is in software development and engineering having spent a large part of my career both developing software (custom & boxed product) as well as managing the process through Technical PM and Product Management roles. I have spent time in consulting, development, PM, testing, and support roles throughout my career. Most recently I moved into the Supportability function within Microsoft Support where we focus on crafting an AI-Frist Customer support experience while making our Support Engineers more efficient and effective through developing cutting-edge solutions.
Ross: Wow, that’s great – you have both and engineering and support background. , so you haveThis gives you a good great perspective on this new world of AI that blends cutting edge technology and support practices. We know that Customer Service and Support is a top enterprise scenario for the use of AI. When did you first get involved with AI?
Jason: My team started discussing how we could disrupt shake up some of our current plans in support by leveraging AI back in the summer of 2022. We were laying the initial foundation of understanding for using AI in Customer Service. Then in December of 2022, ChatGPT burst onto the scene and because of our workwe’d already done a bunch of worksignificant research, experimentation, and work in this space, we were primed for seizingto seize the opportunity. Quickly in January 2023 we started building models based on our data sets combined with the power of GPT 3.5, and learning as the technology was changing so rapidly. It was and continues to be quite a wild ride.
Ross: So you were ininvolved with experimenting with AI this early on, before ChatGPT was even introduced to the world. You’ve clearly got a lot more experience than most. What are some of the things you’ve learned?
Jason: One of the most important things I learned is that AI, like many technologies, has a learning curve for users to see the promised efficiencies. Early on many people thought it was this magical tech to solve all problems and, while it is amazingly powerful, it does take investment to realize the potential. Another key learning is that there isare certain things AI is really good at and others where it tends to struggle. Understanding the parts of your processes or tooling that are good candidates for AI is key to unlocking the most productivity gains. Finally, AI is only as good as the model or knowledge source you feed it. We learning learned that having a good set of high-quality content is important to ensuring the best possible response quality.
Ross: Sounds like you all have learned a lot about what works and what doesn’t. Can you tell us all a little more about where you see AI totally shine and where it tends to not perform as well in customer scenarios?
Jason: In the customer service space, we see AI perform well at tasks that typically require less deep knowledge about the thing you are supporting. For example, helping draft high quality customer emails, helping create initial troubleshooting or scoping emails to your customer, categorizing your support case based on a defined taxonomy, answering customer questions on how to use a particular feature –, basically things that typically take up time in a support engineers’ day but don’t require deep specialized knowledge. Conversely, deeply technical nuanced issues, issues specific to an individual implementation, issues on new areas that aren’t well documented, these are candidates more suited for your human engineers.
Ross: You have a long history with building diagnostics and automation to help customers help themselves with their technology issues. How will AI be integrated or will it be different from traditional diagnostics we read about here Save time and effort with Microsoft 365 self-help diagnostics – Microsoft Community Hub
Jason: Right now, we believe AI will help in a few ways. First, AI continues to help our developers generate code more efficiently, allowing them to accomplish more in the current methodology of development. Secondly, we see diagnostic services being able to leverage LLMs to perform tasks that would normally be embedded in business logic. For example, we have diagnostics that analyze large log files looking for predefined patterns. Going forward we will be able to leverage the pattern recognition and categorization capabilities of AI to be able to find new patterns in logs files we haven’t encountered yet. This will shorten the development cycle and increase the effectiveness of these diagnostics. Lastly, we can use AI to generate natural outputs along with advanced troubleshooting steps that evolve over time. With diagnostic results being able to prompt an LLM for additional insights we can ensure diagnostics can provide the most up to date guidance in a low code way.
Ross: This is such a fascinating time of technological change and rapid advancements. What are you excited about for the future?
Jason: As many have said, we are just on the verge of this AI revolution and what it can unlock for do for many around the world. I am excited to be a part of one of the most exciting times in computing history and being able to learn every day as new things continue to be discovered. Many problems we have tried to solve in the past with marginal results now seem much more feasible. I am excited to see where we can go, what we can do, and what problems we can solve in the months to come.
Ross: You have clearly come a long way in your AI journey, Jason. What advice would you share with customer support professionals who are trying to figure out how to deploy AI in their organizations? This is an intimidating space. What should people do to get started?
Jason: AI is another tool that can be used to help you solve business problems. While it is powerful and exciting, it won’t address everything all at once. I would recommend being clear on the challenges in your organization and then seeing how AI might help. Make sure you have a foundational understanding of where AI excels today and take that into careful consideration before planning out where to start. Also, be aware that AI will change your existing processes and you may need to rethink how things work to get the most out of these new capabilities. I like to start small and learn, building out based on positive results. Finally, remember that any AI solution is only as good as the data in the model. Taking time to ensure you have quality knowledge source content first will go a long way in ensuring the results AI delivers meet expectations.
Related: ChatGPT & AI: 6 Tips for Managing Support Content (microsoft.com)
Ross Smith is the Worldwide Support Leader for the CSS Modern Work Supportability team.
Jason Weum is a director of supportability for OneDrive and SharePoint support, and he led strategy development for Modern Work GPT.
Am a keen follower of Microsoft's SharePoint Blog and proud to provide this direct from the Microsoft Tech Community:
Welcome to Microsoft Build 2024! Whether you’ll be joining us live in Seattle or online, get a look at how Microsoft AI innovations can help you unlock opportunities and drive productivity.
Microsoft SharePoint is the platform trusted by countless organizations for storing, managing, and sharing content. In the face of growing content repositories, how do you ensure you’re getting answers based on the most accurate information? How can you share that knowledge with others without overwhelming them? The answer lies in harnessing the power of AI to refine workflows and foster collaboration that’s tailored for your team or organization. This allows you to concentrate on actual work rather than sifting through content to find what you need to accomplish your tasks.
We’re excited to introduce the ability for anyone to create custom copilots from SharePoint. In just a few clicks, you— whether an admin or business user— can create and share a copilot from SharePoint that’s grounded in the curated, authoritative content you choose. Since you rarely work alone, you can also easily share your copilots with others in Teams chat, email, and more. It’s like a subject matter expert ready to help you, your team, department, or even the whole company while respecting all your existing security settings and permissions.
Site owners can enable any site to get a built-in copilot, scoped to the content of that site. This copilot is a new way for users to interact with the content on the site and can be shared to other Microsoft 365 apps and experiences.
Imagine you’re on the Marketing team, which has a SharePoint site that stores all the materials for an upcoming product launch— content such as demo videos, spec sheets, pitch decks, and press releases. This copilot for the site gives organizations or groups, like yours, specific and trustworthy responses to questions like, “what is the final decision on the product launch date?”. Because the copilot is scoped to the content of this site, you’ll get the latest, most accurate answer about the project based on your permissions.
If the copilot’s default scope doesn’t work for your site, you— as the site owner— can customize this copilot by changing the content, identity and behavior. You can also choose a copilot that you’ve created through Microsoft Copilot Studio or Visual Studio to be the default copilot for this site.
Built-in custom copilot for this site
Beyond only site owner or admins, anyone who has edit permissions on a site (such as a site member) can create a copilot for the site with a few clicks, no coding skills required.
Creating a custom copilot from SharePoint is a simple starting point for users looking to use AI tools to efficiently collaborate for a particular purpose, such as a specific project or topic, or users that want to spend less time looking for information, and more time focused on more meaningful work at hand.
Continuing the scenario above with the marketing site for the product launch, a cross-functional team of 20 people across marketing and engineering are working together with you to launch a new product. You are collaborating together via this SharePoint site that has a document library with the most accurate and up-to-date information.
Create a custom copilot from a file selection
As a member of this site, select “Create a copilot” and choose the folders or files that you want your copilot scoped to. The copilot will reason over only this content when providing responses.
You can start using this copilot immediately or make lightweight customizations, such as adjusting the identity, sources, and behavior of the copilot.
Custom copilot is pre-populated with information from the file/folder selection
The copilot has a default folder name, branding, description, sources you’ve selected, and other fields already. You can keep these fields and parameters as-is, or easily update them.
Customize the identity with a name change
Customize the grounding knowledge
Customize the behavior
This newly created custom copilot is now ready to use. It can answer your questions, summarize information, or find files, all based on the selected, authoritative content to give the most current and accurate response available. If you need deeper customizations for your copilot or to automate workflows, launch Copilot Studio directly from SharePoint.
Custom copilot with customized name, sources and start prompts
While you can use custom copilots on your own, they’re also shareable with your team, so you can interact with and learn from the same authoritative sources of information. There are a few ways to collaborate and share knowledge using these copilots. With the copilot that will be part of every SharePoint site, these are automatically scoped to the site content. You and your teammates can ask questions in the sidebar chat interface as soon as you visit the site.
Use the copilot on the SharePoint site
You can easily share this built-in copilot and your own custom copilots with others in the same way you would share a link to content in SharePoint by selecting “Share”.
Share the copilot
Just like other Microsoft 365 productivity apps, you can select “Copy link” and drop the link to team members in an email or select “Invite” to have an email auto-sent to them. The recipient can open the copilot in SharePoint.
Copy link or Invite to share
For real-time group collaboration, you can also easily share copilots in Microsoft Teams. You’ll take the same copied link and paste it in a Teams chat, and the copilot becomes part of the chat.
For example, you can share the custom copilot with your core launch team in a Teams group chat, where everyone already interacts with one another in the thread. Your teammate can ask the copilot in this chat, “What is the list of contacts?” This ensures that we can all, together, get up to speed quickly on the latest details of the product launch.
Drop the link in chat to collaborate with your team
The custom copilot follows existing SharePoint user permissions, so it’s accessible by those who are already permissioned and there’s no risk of oversharing information.
You will also be able to use your custom copilots or ones shared with you in Microsoft Copilot, as they will appear with your recently used copilot extensions.
ReleCloud Delivery Drone copilot could be used in Microsoft Copilot
If you need to expand the content that this copilot is grounded on beyond SharePoint, you can add additional data sources in Copilot Studio with over 1,000 different data connectors. For example, if the launch team needs to add a structured database that maintains customer leads, they can add this source. You can also add actions to automate workflows, such as updating customer lead records and notifying human agents on promising leads.
Tap “Add advanced customization in Copilot Studio” to launch Copilot Studio
Continue customization in Copilot Studio
When these advanced customizations are ready, you can publish via Copilot Studio, as usual, so the updated copilot is available across SharePoint, Teams, and Microsoft Copilot for your organization.
We can’t wait to see the custom copilots our incredible SharePoint user base will create! Everyone will now be empowered to create, use, and share copilots for better collaboration and knowledge sharing —always with the trusted Microsoft governance capabilities you already have.
Sign up for the private preview today and stay tuned for the public preview coming later this year.
Don’t miss us this week at Microsoft Build in Seattle and online, May 21-23, 2024, to learn more and chat about creating copilots from SharePoint and other AI innovations we’re bringing to our maker community.
• KEY01: Opening keynote with Satya Nadella, Kevin Scott, Rajesh Jha, and me.
• BRK144: Integrating your bots and Copilot experiences natively into SharePoint and Viva Connections
• BRK210: What’s new with Microsoft Copilot Studio
• Expert Meet-up station (Expo Hall, in-person only)
The above is kindly provided by the Microsoft Tech Community!
Am really keen on exposing PowerApps / Flow news - this was provided from Microsoft Flow. You can read out the full post available on this link:
Continue reading to learn about new ways to automate, from outcome-based AI flows that simplify complex processes, to multi-modal AI recording that makes UI automation more natural, accessible, and resilient.
