Like many global companies, our network engineering environment here at Microsoft is gigantic.

It spans 88 countries, more than 700 buildings, 64,000 devices, 7,500 Microsoft Azure Virtual Networks, and nearly 150 lab sites. It’s a system that serves more than 220,000 employees and generates its fair share of service tickets, more than 170,000 per year.

How do you keep something of that size healthy?

Joshua Green and Soundarya Tekkalakota wondered if their team in Microsoft Digital, the company’s IT organization, could build an AI agent with Microsoft 365 Copilot to help accomplish this goal. Green, an Infrastructure and Engineering Services (IES) principal software engineering manager, and Tekkalakota, an IES product manager, quickly realized that the answer was a resounding yes, if they sprinkled in a helping of artificial intelligence and machine learning.

“We essentially put an AI lens on the network engineering challenges that already existed, and that our engineering teams have been dealing with for years,” says Tekkalakota, who served as lead product manager on the effort. “We decided to use AI to enable faster gathering of information and data insights, and to identify network problems more quickly and efficiently—this would give our network engineers more time to take the human actions needed to resolve issues.”

That kicked off their AI journey, in which they and their team built a custom engine agent before eventually using the extensibility capabilities of Microsoft 365 Copilot to create a declarative AI agent. The result is Network Copilot (also known as Network Infrastructure Copilot, or “NiC”), a powerful tool that provides support for various networking and infrastructure-management tasks and helps us work toward our goal of operating the industry’s most secure and reliable enterprise network.  

Importantly, Network Copilot is another proof point in our ongoing journey to show how we’re benefitting from Microsoft 365 Copilot internally here at Microsoft. Read this story to learn how we’re thinking about AI agents internally at Microsoft and to get our guidance on how to get started with them at your company.

The spark of inspiration

Network Copilot originated in a hackathon project in early 2023, inspired by the excitement at that time around generative AI and ChatGPT. Tekkalakota pulled together a small group of AI enthusiasts and launched the effort to develop a tool that would be able to simplify network management tasks.

“These were network engineers who were at that intersection of new tech enthusiasts and experts in their particular job,” Tekkalakota says. “We leaned on them heavily in the first few iterations of the project, collecting their feedback manually on what the right queries were. And as time went on, we kept adding more and more of these enthusiastic users to help us build the community, and to test the tool and gather feedback.”

On the engineering side, the project started out with a custom-agent approach, reflecting the available technology at that point in time.

“We went with a conversational agent built on Semantic Kernel and Azure OpenAI, because that was the only option at the time,” Green says. “Over time, we switched to a declarative-agent model based on the Microsoft 365 Copilot capabilities that were being released. In a sense, Network Copilot is the story of how fast AI technology is progressing, and how it’s becoming faster and easier to develop these kinds of tools.”

Improving network services with Network Copilot

Generative AI tools excel at one of the biggest challenges that network engineers face in their day-to-day work: how to quickly track down the specific information needed to resolve a network issue.

“There’s something like five to eight different steps in the network management workflow, and many of them have a manual component,” Tekkalakota says. “Network engineers drill through siloed documents like wikis and troubleshooting guides, data sources such as infrastructure data lake and incident management (IcM), and more to define data insights and documentation. We wanted to make this search faster and easier for these engineers.”

The answer was Network Copilot, an AI chat interface in which engineers can use natural-language queries to gain insights and determine recommended actions without leaving the flow of their work process.

“It’s a great solution because it keeps them in the context of their current work,” Tekkalakota says. “They don’t have to step out of the network lifecycle management task that they’re currently in to find answers. It gives them the next step in a concise, summarized manner—something that they would have to spend multiple hours tracking down outside of their context.”

The use of natural language to access network telemetry in real time is one example that Green cites when talking about how Network Copilot is transforming the way that engineers do their job.

“I can ask NiC, ‘What’s the network health of Building 32?’ and it will run a query against the network telemetry data,” he says. “Then it summarizes the results in a nice, clean report for the user, including details on risks and recommendations for that building’s network. Then the engineer can take the appropriate action.”

Transforming network engineering with a Copilot agent

Network Copilot development journey

The initial development of Network Copilot as a custom agent meant it relied on plug-ins to give it more flexibility.

“We first built NiC in a very modular way, and all its capabilities were done with plug-ins and APIs,” Green says. “For example, we provided a library of more than 1,000 queries, which were written by the teams that know the data best (like the wireless team, which wrote queries to check the health of wireless access points). So, when Copilot is able to access that data, it can stand toe-to-toe with the network engineers because it’s able to draw on that same knowledge base.”

Then, when declarative agents were released in 2024, the development strategy shifted to take advantage of these faster, less code-heavy solutions.

“One of the things we’re always trying to do at Microsoft is provide low-code and no-code options,” Green says. “That’s what Microsoft 365 Copilot is focused on. Or you can go with full-code development, do it all yourself and have ultimate control and customization. Our journey with NiC was kind of a hybrid approach. We’re still on the journey from full code to low code; we’re not there yet.”

Overcoming the challenges of AI tool adoption

As Green, Tekkalakota and the team began rolling out Network Copilot to larger and larger groups of network engineers, they began running into some of the challenges inherent in widespread AI tool adoption.

“The first thing was just the cultural change of our engineers building the daily habit of using the tool, because it’s not always top of mind for them,” Tekkalakota says. “It’s the stickiness factor, and that’s something we’re still working on. The other challenge was what we came to call ‘prompter’s block,’ where the engineers weren’t sure what to ask in the NiC chat, or they wouldn’t keep querying to get better results. So, we put out newsletters and did road shows to educate them on the tool and how to use it. It’s more about a larger cultural shift.”

One major takeaway from this process was that users wanted more integrated and one-click solutions for interacting with Network Copilot.

“Some of it might be contextual, where we’re able to integrate NiC on a specific tab or page or in a specific web application,” Green says. “In some cases, it could be in the form of a button they click that sends a pre-created prompt to the back end. It’s a more simplified approach, rather than just giving people a free-range chat interface where they can ask anything.”

The impact of Network Copilot

Today, Network Copilot is available to our company’s network professionals through an internal preview and is used by more than 200 network engineers. By surveying users, Tekkalakota has already been able to show that NiC has made a significant difference in terms of employee time and effort.

“We’ve found that NiC can cut the amount of time engineers take searching for documentation and insights by 20 to 25 minutes for each successful prompt,” she says. “It also drastically reduces documentation time and has cut live incidents down by 10%.”

This finding is backed up by employees such as Brandon Hughes, a senior service engineer who played an important role in developing Network Copilot.

“Being able to extract data through natural-language questions is a huge departure from having to manually write a Kusto query, which could take you a few hours to refine in order to get the exact output that you want,” Hughes says. “Whereas in NiC, I can spend five minutes questioning it like a human and get a response that includes specific data points from the actual databases. We get a huge amount of value from Network Copilot on a day-to-day basis.”

Hughes and others are also working on extending the capabilities of Network Copilot to handle tasks such as generating customer update emails, troubleshooting suggestions based on service ticket details, and postmortem report generation. They even hope to add the ability for NiC to analyze images of network environments and provide feedback and optimization suggestions.

Taking a wider view, agents like Network Copilot offer the ability to manage complexity and empower users to accomplish more, no matter their role.

“In general, these agents are going to make our lives easier,” says Abhishek Kumar, a software engineer who also assisted in the development of Network Copilot. “We’re always working to reduce complexity, and agents take that a step further—decreasing complexity where it’s needed but allowing the full breadth of complexity when required. They’re enabling users to do things they normally wouldn’t be able to do.”

Network Copilot and AI agents: The journey continues

Tekkalakota and Green know that, for as much as Network Copilot can do now, the team has only just scratched the surface of the full potential that AI agents have to change the way IT—and the world—works.

“I think we’re one of the earlier efforts at Microsoft to build an AI agent, figuring out what skills it needs to have and then building them,” Tekkalakota says. “The next steps are to build on the agent capabilities that it already has, adding things like monitoring or predictive alerting. Then, eventually be able to connect to other agents; having a connected experience between Copilot agents is the uber goal.”

Green emphasizes that when it comes to AI, the pace of change is remarkable.

“It’s still early days for AI agents, and things are moving and changing extremely quickly,” Green says. “What we did with Network Copilot was kind of like building a foundation. Now we’re working on adding more capabilities. The potential is great—we’re just seeing the tip of the iceberg.”

We learned some important lessons while developing Network Copilot that you can draw on when creating your own AI agent solutions, including:

• The team found it most effective to slowly build a community of enthusiastic users, continually soliciting feedback and ideas for improvements from these early adopters.
• Users expect an AI agent to “just work” with one prompt. Query debugging features (“Help me with this error”) and contextual prompts encourage users to engage in a conversation to generate the information they need.
• Users want the AI agent to know everything that their team knows. The Network Copilot team continues to expand the tool’s knowledge base with additional troubleshooting documents, network config files, and data sources
• It’s helpful if the agent is accessible from the UI the users are already in, so the team is working on an embedded Network Copilot experience in their custom web apps that offers buttons for commonly used functions.
• Frequently requested use cases for Network Copilot include network device deployment failure remediation, network health and inventory, troubleshooting, and log monitoring for anomalies.
• Technology moves fast. The team built Network Copilot in a modularized way (using plug-ins and APIs) so that they could adjust to the latest AI capabilities as they were released.
• Follow best practices for accessing data from external sources, ensuring that your data is secure and sensitive information isn’t exposed.

Explore your extensibility options with Microsoft 365 Copilot.

• AI-powered agents in action: How we’re embracing this new ‘agentic’ moment at Microsoft
• Boosting our Security First Initiative at Microsoft with a transformed approach to wired network security
• Check out how we’re moving our network to the cloud with Azure.
• Learn we’re unlocking the power of AI with Microsoft 365 Copilot extensibility.
• Read our guide for deploying Microsoft 365 Copilot at your company. 

• Want more information? Email us and include a link to this story and we’ll get back to you.

The post Keeping our network infrastructure healthy at Microsoft with an employee-built AI agent appeared first on Inside Track Blog.

Brian Shaw has been a Microsoft 365 Copilot enthusiast since the company first launched the generative AI solution in February 2023. But with AI tools evolving rapidly, he knew it would be a challenge to keep up with the latest changes and feature releases.

The most effective way he found to do that? Share his knowledge with other employees.

“One of the best ways to learn something is to train others,” says Shaw, a 17-year Microsoft veteran who currently works as a principal customer success account manager on the Retail and Consumer Goods team. “Every time I’ve trained a group on Power BI, I’ve learned something. It’s the same with Copilot. Someone asks a question—I have to figure out the answer. It keeps my skillset sharp and allows me to keep my technical focus.”

That passion for training and enthusiasm for the ways that Copilot can make everyone’s job easier explains why Shaw stepped up to be one of the first Copilot Champs at Microsoft—and why he remains one of the most dedicated evangelists for the technology solution at the company.

“I’m always finding new ways that Copilot can save you time,” he says. “And the great thing about that is that you can redirect that time to have more impact, whether that’s with a customer, in another aspect of your work, or with your community. It really helps magnify what you can accomplish.”

Customer Zero focus

Microsoft Digital, the company’s IT organization, puts a strong emphasis on Customer Zero: the idea that our employees—early adopters and consistent users of the latest Microsoft software tools and processes—should share their experiences with others, including our customers. It’s an idea that Shaw embraces wholeheartedly.

“If we as employees aren’t successful using Copilot, no one’s going to be successful,” Shaw says. “I’ve always heard that if Copilot helps you save 20 minutes a week for six straight weeks, you’ll be hooked. I want everyone to see those benefits, so that’s why I’m always encouraging people to get in the habit of using Copilot every day.”

One example Shaw cites is the way he uses Microsoft 365 Copilot to help him reduce his work email burden.

“I get up to 200 emails a day just from customer support cases, which can be difficult to keep up with,” he says. “So, I ask people to @mention me in the email. Then I can ask Copilot to go through all the emails where I’ve been @mentioned and tell me the subject line, who sent it, the date and time, and what task I need to complete. This allows me to get caught up very quickly and understand what my next actions are.”

On the leading edge

Shaw’s excitement in sharing his knowledge of Microsoft 365 Copilot comes directly from his passion for technology, according to those who work with him.

“Brian is an early adopter and a technologist at heart,” says Rod Combs, a leader in the Customer Success unit for Microsoft’s Eastern U.S. region. “He loves to learn and to be one of the first to master something. So, when Copilot first came along, Brian was in there messing around with it, trying to understand its capabilities and get the most out of it. From there, he’s continued to lead and drive engagement with Copilot across Microsoft.”

One of Shaw’s key principles when approaching any training session is to strive to explain technical points as simply as possible.

“I try to demystify Copilot for people,” he says. “For example, people often ask me, ‘Why are there so many Copilots?’ and I explain that there are basically three types of Copilot: a tools-based Copilot, an application-specific Copilot—like in Word or Outlook—and Copilot Chat, like the one you see at copilot.microsoft.com.”

Jody Ryan, director of Copilot Sales and Compete in Customer Health and Growth at Microsoft, agrees that Shaw’s ability to simplify things sets him apart.

“He really makes Copilot accessible for everyone to understand, just by the way he presents it,” she says. “Brian has a way of explaining things in a non-technical way so that everyone can grasp it, across all skill levels. I think that’s a key strength.”

A customer-centric mentality

Another reason Shaw is so successful at helping fellow employees get the most out of Microsoft 365 Copilot is his “day job” as a customer success account manager (CSAM), which relies on some of the same strengths. It’s a parallel that Cadie Kneip has observed in her role as a leader of the Copilot Champs community.

“There’s something unique about the combination of skills that CSAMs have, of being very technical but able to deliver technical trainings in a way that lands a customer,” says Kneip, a readiness business program manager in Microsoft Digital tasked with finding creative ways to get more Microsoft employees using Copilot in their day-to-day work. “It tends to be very friendly and personable. I see that with Brian, who is very generous with his time to demo Copilot to so many fellow employees. I don’t know the exact number, but he’s completed more than 500 activities to help his peers learn Copilot.”

Yen Anderson, a fellow CSAM at Microsoft and another enthusiastic Copilot Champ, recognizes the skills and passion that Shaw brings to his Copilot advocacy.

“Brian really has knack for instructional training and is masterful at walking people through a tool’s features and functionality,” she says. “He goes out of his way to amplify his impact and upskill the learning community at scale.”

Going global with Camp Copilot

Observing Shaw’s enthusiasm for Copilot trainings, Kneip invited Shaw to be part of Camp Copilot. The internal Microsoft event, held over three weeks in the summer of 2024, attracted 25,000 participants from around the world, all interested in learning more about how Microsoft 365 Copilot can enhance their work and magnify their impact.

“I ended up being one of main presenters in Camp Copilot,” Shaw says. “Over my four sessions, we had more than 5,800 people attending and listening in. It was a lot of fun. And of course, I had a lot of people follow up with me and ask me to do a presentation to their team or group, sometimes for multiple sessions. I would never have had that opportunity if it wasn’t for Camp Copilot.”

Looking to what’s next

Always looking to the future, Shaw can’t wait to be a part of the next wave of features that Microsoft 365 Copilot releases.

“I like to say that the Copilot you’re using today is the dumbest Copilot you’ll ever use, because it’s constantly getting upgrades, getting smarter,” he says. “As it starts learning more about you and the things you work on every day, it’s going to give you better and better information.”

He cites the progression of Copilot in Excel as one example.

“When Excel Copilot first came out, it did maybe three things and I don’t think people were very excited,” he says. “But now that they’ve integrated Python into it, it can write code, create custom visuals, link multiple files and tables together, and more. It’s turned into a real tool that people who use Excel everyday are just going to absolutely love, because it will save them a ton of time.”

Shaw’s also looking forward to the imminent introduction of automated agents with Microsoft 365 Copilot extensibility, which will bring even greater productivity enhancements.

“Soon, we’ll have agents where you can say, ‘Hey, create a Help Desk ticket on this issue’ and it just goes out and does it, and returns with, ‘Your ticket’s been opened, and here’s the link to it,’” Shaw says. “Having Copilot agents do that kind of thing is going to save people a significant amount of time and effort.”

In the meantime, Shaw will continue to keep teaching others about Copilot, which will help him stay ahead of the curve with a technology that he believes is changing the world.

“I’m always working to keep up with the roadmap, which is a large ask, but it’s also fun,” he says. “With Copilot, we’ll eventually have one central tool that can do everything—the future is going to be incredible. I can’t wait to see what the journey holds.”

Here are Shaw’s top tips and insights for using Microsoft 365 Copilot:

• Let Copilot teach you how to use it. Copilot is one of the few tools that will tell you how to use it. For example, if you are unsure what you can accomplish with Copilot in Word, just say, “Hey Copilot, I’m new here. What are all the things you can do?” and it will tell you.
• Use Copilot as an interactive conversation engine. Don’t think of Copilot as a search engine, where you type in one query and then page through the results. Instead, carry on a conversation with Copilot. Keep asking it questions until you have the information you need.
• Ask Copilot to analyze your meeting while it’s happening. For example, if you’re in a Teams call with a customer, at any point you can ask Copilot, “Are there any questions that the customer asked that I haven’t answered yet?” Copilot will search the transcript and see if there’s anything that got skipped over; then you can go back and address those issues.
• Treat Copilot like you would a new intern. You need to give Copilot the context it needs to produce valuable results. If you want the information in a table, tell it to make a table, including what information should be included and how it should be displayed. Give it specific instructions and you’ll have a much better chance of getting the output you want.
• Use Copilot to catch things you might have missed. Copilot can do sentiment analysis to detect when a customer or team member is concerned or upset. It can also help you if you’re distracted during a call. Just ask Copilot, “Hey, can you summarize the last five minutes?” That way you don’t have to interrupt the call and ask, “Can you please repeat that?”

• Try Microsoft 365 Copilot.
• Make a difference. Become a Champion.

• Check out this story that explains how our Microsoft 365 Copilot Champs program works. 
• Read our profile on Copilot Champ Yen Anderson.
• Here is where to go to get started with Microsoft 365 Copilot.
• Read our guide for deploying Microsoft 365 Copilot at your company.
• Learn how we’re tackling Microsoft 365 Copilot governance internally at Microsoft.

• Want more information? Email us and include a link to this story and we’ll get back to you.

The post Staying ahead of the AI curve with Microsoft 365 Copilot: How a champion does it appeared first on Inside Track Blog.

Yen Anderson remembers the first time she saw Microsoft 365 Copilot, the generative AI tool that the company launched in February 2023. She intuitively knew that the way she went about her job would never be the same.

“I realized I’d need to make significant changes in my work habits, and to start thinking with a different mindset in order to embrace AI,” says Anderson, a senior customer success account manager for Azure and AI. “So, I started to revamp the way I worked.”

She also immediately began to share her excitement about this powerful new virtual companion with her peers.

“By the second day after receiving Copilot, I was already demoing it to my internal team,” she says.

Helping her peers use the power of Microsoft 365 Copilot

Today, less than two years later, Anderson is one of the leading internal evangelists for Copilot at Microsoft. She has presented her tips and insights on how to get the most out of Copilot for dozens of internal teams, town halls, conferences and other Microsoft audiences around the world. She estimates she’s trained over 16,000 employees so far.

Anderson’s passion for Copilot and willingness to share what she knew caught the attention of Cadie Kneip, a readiness business program manager who was trying to come up with creative ways to get more Microsoft employees to use Copilot in their day-to-day work. When Kneip launched the Copilot Champs community in January 2024, Anderson was one of the first employees she invited to join.

“Yen was one of the earliest Copilot Champs, and she’s probably the most famous,” Kneip says. “She’s just naturally passionate about Copilot and AI, and she’s been insanely generous with her knowledge companywide.”

Powered by the enthusiasm of employees like Anderson, Copilot Champs has taken off. In less than a year, more than 6,000 Microsoft employees have joined the program, Kneip says. It’s a great example of Microsoft Digital’s Customer Zero philosophy, which pushes employees to use the company’s latest tools and technologies.

“My focus has been on amplifying use of Copilot inside of Microsoft for full adoption for Customer Zero,” Anderson says. “I think if we fully embrace Copilot internally at Microsoft, we’re better equipped to help our customers fully embrace Copilot as well.”

A passion for prompting and saving time

Anderson’s internal advocacy and external promotion of Copilot—she frequently posts about ways to save time and work smarter with AI on LinkedIn and in her personal Substack newsletter—focuses on practical tips and strategies that have broad appeal.

“Yen always tries to keep the audience engaged,” says Brian Shaw, a principal customer success account manager in RCG and fellow Copilot Champ. “She does these interactive sessions where she shows you how she’s saving all this time using Copilot, and she has people hooked on every word. Her excitement is contagious.”

Kneip appreciates how Anderson’s deep knowledge of how to get the most out of Copilot is communicated in live demos rather than through preset examples.

“I love the way she demos Copilot—not by using screenshots or a slide deck, but with live prompting,” Kneip says. “She has an incredible reputation for being a prompt-engineering wizard.”

Anderson’s most recent training efforts have focused on how Copilot itself has evolved over the last year or so, and what she’s learned along the way. “The prompting has definitely changed from when I first started, to the point that it’s radically different,” she says.

Yen Anderson’s top five Copilot prompting tips

How AI can improve job satisfaction and work/life balance

Anderson’s excitement about helping others unlock the power of Copilot is directly connected to the impact the tool has had on her own life.

“I’ve seen dramatic increases in my productivity and my well-being,” she says. “Copilot has the ability to help alleviate some of the problems with work today, like too many meetings, being overloaded, and not having time to do focused work. I’m a huge advocate of mental health in the workforce, and when you combine these productivity tools and mental frameworks with AI, that combination is a game changer in terms of improved work/life balance.”

One daunting task that Anderson was able to make easier through Copilot was employee self-reviews, known as Connects internally at Microsoft. She created a set of highly guided prompts that allowed employees to use Copilot to help them craft their self-reviews. She partnered with Human Resources to make sure the set of Connect-writing prompts that she created not only complied with company rules and regulations, but that it supported HR’s goals of helping to make the experience easier and more rewarding for employees.

Anderson also worked with Kneip to distribute train-the-trainer sessions on her Connect-writing prompts.

“Yen and I did several ‘Copilot for Your Connects’ sessions, and we also ran a Teams channel called Connects Helpline to answer questions about prompts,” Kneip says. “Microsoft is a competitive place, but Yen is so generous with her time in helping other employees. This is not her regular job, but she does this extra work because she believes it’s valuable and the right thing to do.”

The future of Microsoft 365 Copilot

Anderson herself can’t wait to see what happens in the world of work as Copilot and other AI tools get better and better.

“I’m really excited about the use of agents, where a string of Copilots are working on our behalf,” she says. “Eventually, I want to be able to dictate to Copilot and say, ‘Send my team a communication about this topic, and distribute it to all the relevant Teams channels, and then create a nice flyer in order to incentivize people.’ And then Copilot will go off and do that for me.”

Anderson believes that this is the true power of AI: to free up humans so they have the time and energy to pursue things they are truly passionate about.

“It’s definitely changed my life. Because of Copilot, I’ve rediscovered my love of writing and being creative again. I’d forgotten about all of that,” she says. “And I hope I can empower others to unlock something inside of them that they’ve forgotten about and give them the time and freedom to pursue the things that give them joy. That’s why it’s so exciting to be at Microsoft, at the forefront of AI.”

Here are some tips from Anderson on how you can get started with Copilot prompting:

• Diversify: Add variety in sentence structure or vocabulary to your prompts.
• Elaborate: Add more detail or explanation to a given point.
• Explain: Make the meaning of something clearer in the rewrite.
• Exaggerate: When you want to add hyperbole in the rewrite.
• Illustrate: Provide examples to better explain the point.
• Paraphrase: Useful when you want to avoid plagiarism.
• Reframe: Change the perspective or focus on the rewrite.
• Simplify: Reduce the complexity of the language.

• Try Microsoft 365 Copilot.
• Make a difference. Become a Champion.

Check out some Anderson’s top Copilot-related tips and tools:

• Check out this example of Anderson’s favorite and most effective productivity hack: time-blocking.
• Want to be more productive? Here are tips from Anderson on how to do exactly that.
• Break out of your Friday routine with these tips from Anderson that will give you a boost that lasts through your Mondays.
• Here’s how to get time-blocking right (and what not to do).
• Check out and sign up for Anderson’s newsletter.

Check out these suggestions on how to get more out of Microsoft 365 Copilot:

• Here is where to go to get started with Microsoft 365 Copilot.
• Read our guide for deploying Microsoft 365 Copilot at your company.
• Learn how we’re tackling Microsoft 365 Copilot governance internally at Microsoft.

• Want more information? Email us and include a link to this story and we’ll get back to you.
• Please share your feedback with us—take our survey and let us know what kind of content is most useful to you.

The post Transform your IT operations with Microsoft 365 Copilot: Insights from a champion appeared first on Inside Track Blog.