252 | How to Use Microsoft Copilot to Standardize AI Workflows Across Your Organization with Nate Amidon

0:00Hello, and welcome to another episode of the Leveraging AI podcast, the podcast that shares practical, ethical ways to leverage AI to improve efficiency, grow your business, grow your business, and advance your career. This is Isar Maitis, your host, and we're going to cover an incredibly important topic today. And that is the topic on how to build tools that delivered standard results across the organization. Now, one of the big issues that companies are facing as they start implementing AI is that they're basically generating lots of local chaos because there are a few people who are excited about AI who create local initiatives that they start using, which means many different people are doing many different things in many different ways, And the bigger the organization, the bigger the problem becomes, because as an organization, you need to have standardization.

0:47You need to get consistent results. Otherwise, you can't run your business regardless of what you're doing, whether you're writing project plans, generating reports, writing proposals. You want them to always be standard. And so you can actually use AI in order to increase standardization and actually get consistent results better than even humans on their own before AI was ever created. So this is obviously music to the ears of any manager, whether middle management or senior management, of how can we use AI to create consistency across the organization so there are standards that everybody's actually following and they're not just in a folder somewhere.

1:30And to help us to learn how to do this effectively, we have with us today Nate Amidon, who is an incredible person with a really unique history. So he started his career as a C-17 pilot in the US Air Force. Those of you who don't know what a C-17 is, is one of the most impressive airplanes ever built. It is gigantic and yet incredibly powerful platform. And as a Air Force pilot myself, I can tell you that it's a big deal to know how to fly these things. Now, after that, he spent 10 years in leading large projects in companies such as Boeing. So he has the right experience to know what large organizations actually need, how they work, what are the pitfalls and how to solve them.

2:14And in the last seven or eight years or so, he's been running his own consulting company where he helps enterprises develop effective teams and processes, implementing what he learned in the Air Force. He's also hiring ex-people from the military, which I highly appreciate, again, as a veteran myself. So that by itself says a lot about him as a person. Now, what he's going to share with us is two different automation tools that he has built for actual clients, for enterprise clients that help deliver clarity and consistency across multiple aspects of the organization. And he's going to show you exactly how you can develop these on your own so you can do this as well.

2:54So this by itself is a very important topic that I'm sure you're excited about. But to make it even more exciting, he's going to show you how to do this in Microsoft 365. Now, why do I find this exciting? Because we very rarely do Microsoft 365 co-pilot things in the show. We've touched on Gemini and Claude and ChatGPT and open source models, but we very rarely do anything with co-pilot 365. And I know many of you are co-pilot users because you work in large enterprises. and about 70 % of large enterprises use Copilot. So there's two very good reasons why you should stick with us and listen to this episode.

3:30One is because we're going to show you how to build consistency across processes and projects in the organization. And the other is we're going to show you how to do this with Microsoft Copilot. You can obviously take this to any other tool you want, but if you are in the Copilot universe, you get another bonus. And this is why I'm really excited to welcome Nate to the show. Nate, welcome to Leveraging AI. In the next few years, AI technology will change our world dramatically. Whether you are a business executive trying to catapult your business forward, or just somebody who refuses to be left behind and want to advance your career, this is the show for you.

4:10I'm your host, Isar Maitis, a serial entrepreneur and an AI enthusiast. You'll hear invaluable practical tips from innovative business leaders, AI practitioners, and some of the brightest AI minds in our world today on how you can leverage AI in ethical ways to advance your career and grow your business.

4:33Hi. Thanks, Isar. Happy to be here. You know, one thing you missed on the intro was that the C-17 is the best looking aircraft as well. Debatable. Debatable. Hence why I did not mention that because I knew this is going to go somewhere. This may derail the podcast, but it is an incredible, incredible platform. I will definitely give you that. Okay. So tell me, let's really dive right in and let's talk about the first example that you want to share with us. And you can maybe start with how maybe some of your clients are using it and then we can dive into or what it is, how your clients are using it.

5:15And then we can dive into actually how to build it. Yeah, right. One thing you said in your intro that I think is really important is that AI can really just create chaos. It can in some ways be a chaos generator. And especially the larger your organization, the more people you have that can be off creating their own things. And as these tools become more readily available and user-friendly, pretty soon they're going to start sharing those out. Right? And if you think about the person in your office who you definitely don't want creating the standard AI, that person could be the one that carries it out.

5:52So I think organizations need to be thinking a lot about, hey, how are we actually going to handle this? How are we going to build our own internal governance process to make sure that the AI is being used in a way that we want, that fits our culture, that fits the objective of our team, of our program, of our organization? and uh and so i think leaning into these early is going to be a good idea so yeah so yeah i i i think the the the grassroots aspect of ai is awesome from the aspect that it allows more people to be innovative and do things for the organization for sure as long as you can control it once you lose that then like you're saying it's just going to create more chaos than you had before, which is definitely not the goal.

6:43The goal is to create more productivity, more efficiency, more better results, but not to create more chaos because we usually have enough chaos in organizations as it is right now. Yeah, absolutely. And it's really a balance because you want to let people go off and do science projects. You want them to experiment and come up with things that are valuable. And a lot like in the software development realm, like you know those hackathons even those are valuable for software engineers because you just come up with ideas that could be implemented and save the company huge amounts of money but at the same time you can't have a team that's spending six months building a science project that isn't validated and isn't something that you know is so it's a huge balance and I think AI is going to look a lot a lot like that I think we we need to do AI with a lot of the agile principles that we used in software development and we should treat AI we should treat our AI agents as software products because that's what they are yeah yeah yeah so what we've been doing with our clients and let me just preface I'm not a software engineer I don't have really strong technical chops all right I mean I'd I get scared with Excel macro sometimes okay so like I don't go super deep in the hands-on keyboard realm.

8:01But we really think a lot about optimizing process and driving alignment in an organization. And for us as Air Force pilots, it's really important to know what the mission is, who's doing what. And when you have multiple aircraft in the airspace, they all have to be coordinated and talking. And that same principle applies to technology organizations or really any organization that's in the complex domain. So we've always done automations through like Azure DevOps and Jira and through, you know, just through general processes. And so when what's really happening is with especially Microsoft and Gemini and GPT are doing the same thing, they're kind of democratizing some of the technology ability to people that aren't that aren't hands on keyboard engineers.

8:47So a lot of things I'll show you, you could have built before AI. AI is not really unlocking it. It's just making it a lot easier for people to do it themselves without a ton of technical background. A hundred percent. Yeah. So let me just give a quick overview of kind of our philosophy of how we do this. I'll do it really fast. But I think it's really important to kind of set the stage for what these are. Because like I said, these aren't really technically impressive. It's more of how they're applied inside the process. So we have kind of four key areas that we focus on. The first one is that we should be building these AI solutions to make humans better, not replace humans that should this should be enhancing human ability and that's important from a change management perspective when because that a lot of times that can stop people from even adopting uh we anytime we're going to build an automation it has to be valuable which is the biggest common sense thing ever but it has to be valuable we define that as it saves time but or it increases quality so you could create an automation that makes takes longer for someone to do something, but it's more valuable because the end product is a lot better.

9:57And that improves the systematic value. So we need to think about big systems and value. And they can't create bottlenecks. So if you can automate your task and do it really fast, but it causes 10 other people to make their task a lot longer, you haven't added any value, right? You've just moved your work to somebody else, if that makes sense. So valuable is important. And then we think about this incrementally. So we don't always try to build the fully complete automated solution. We'll do things in like an 80 % stance. So if you can automate parts of your task, you should do that. It's okay to roll out small pieces of functionality and automation instead of trying to build a big thing.

10:43And then the final thing is we should always think about sustainability, especially in these larger organizations. If you build automation that that doesn't adapt and change with underlying business processes or changing market conditions, and no one's managing those, they're going to drift and become best case useless, worst case counterproductive. Yeah, great points. I think the interesting thing about what you're saying is that all of it makes perfect sense. And yet, a lot of people and organizations do not follow these things. But yeah, I think human-centric and value is two really critical aspects.

11:22You want to give people superpowers, and then they will be A, happier employees, and B, more productive, which will drive the organization as a whole. And you want to make sure that what you're developing is not just a cool project, but actually provides value to the organization. And the interesting thing is, and I'll say my two cents, and then I would love to hear yours, how do you measure value, right? Because value can be measured in several different ways. So when I work with clients, I measure value. Three of them are very obvious again. You know, one of them is it drives up the top line.

11:53So this is simple. The other one is it reduces cost, which reduces the bottom line, which makes sense. The third one is it removes tedious tasks and frees people to do more value jobs. So this is still simple and logical, but not directly immediate correlation to like dollar value. And the last one is even a further extension of that. I believe that having happy employees is one of the goals of an organization because I believe the goal of life is to be happy. And so that's just an extension of that. We spend so many hours at work. We should try to make people around us happy. So whatever we can do to alleviate employees for things that makes them unhappy is valuable, right?

12:39So it may not be captured in a KPI or an OKR or whatever other acronym you want to put on it. I find these things valuable. But this is the way I do things. I'm very curious to see how you organizations you work with capture or define valuable work. yeah so we we work primarily with software development and technology organizations usually in larger to mid to large enterprise multiple team type scenarios yeah um and defining value forget about ai for a second defining value is one of the biggest hurdles uh ever and especially in these really large enterprises right like boeing for example like um there's so many moving pieces and when you get down to the team level the question of what is it that you actually do and how, why does your team exist is a hard question.

13:29And I think it's a, and so knowing, knowing how the smaller your team is, it can be a lot simpler. You have a startup, Hey, are we making more money or not making more money? But like you can't correlate that to maybe a backend API team in a super integrated system in a large enterprise. Like it becomes really hard. So defining value is, is a real problem. And you're what you brought up really made me think about back in the eighties when manufacturing companies just got automated robots into their assembly lines. And there's a book out there called The Game, if you're familiar with that, or The Goal.

14:04Sorry, not The Game, The Goal. That's way before the 80s. Yeah, so it's back there, right? Yeah. That's where we were born. And what's crazy is they had the same problem, which is they're automating things, and they're like, hey, this one task, it's way faster. We're getting a huge ROI. But at the end, they weren't at all because they were just creating... Because there's a bottleneck somewhere else and your ability to create additional capacity makes no difference. Yes. So putting on your lean hat is like the lean Six Sigma stuff is going to become way more important. And the process of implementing AI is going to be more important than the actual AI capabilities itself, especially in the larger enterprise.

14:46Agreed, 100%. So let's dive in. So what's this particular first automation? So, yeah. So let me just say there's two kind of areas that I focus in. These are really lightweight automations. And I'm not going to I'm not going to wow your audience with my technical skills here. But there's really kind of two ways I think that some of these capabilities can help. And I look at them right now as you can have kind of agents that are informational and agents that are kind of process improvement agents. And so I'm going to show you one of each. All right. And kind of just go through what they look like, what they are in the use cases for them.

15:26So I'm going to start out first with what I'm calling it like a ways of working agent. All right. And so the problem statement here is that there's a ton of different process steps in these bigger, larger enterprise organizations. There's so many regulations. There can be so many PMO might have its own structure. You have an agile coach or you have a director and they all want certain things done a certain way. And so following the process isn't hard, but knowing what the process is, is hard. OK, so and so what we've done is built an agent to help make it easier to know how we're supposed to do things and then also to get information about the process.

16:13So that's the, let's set the stage here and then let me share up my screen and we can walk through it. Awesome. For those of you who are listening and not watching this on YouTube or something, we are going to explain everything that's on the screen so you can follow along with us. You can also always go and watch this on YouTube. There's a link in the show notes that can take you straight to the YouTube channel to watch this. But if you are walking your dog or doing the dishes or jogging on a treadmill, then you can stick with us. and we will, or driving for sure. You can stick with us just listening and then we will tell you exactly what's on the screen.

16:49Perfect. I'll try to give progressive directions here as we go. Okay. So first we're talking about is Microsoft Copilot. So if you have a Microsoft account, let's say on the larger enterprise organizations, you probably have Copilot. Okay. So you can get that through your Teams instance on the left-hand panel. There's a Copilot tab or you can get it through your M365 account, which is those nine boxes up at the top left. And when you select these, you can find the Copilot tab, which I already have open here, and it'll pop into your M365 Copilot instance. Now, having Copilot, I'll talk a little bit about licensing.

17:33essentially the gist is you may not just automatically have access to agents in an M365 copilot instance. So the way you can check is if you look on the left-hand side and you see agents, right, you have it. If you don't see agents, you don't, and you should go talk to your system admin to request a license. They're not overly expensive, okay? They're maybe$20 a month. I think it's somewhere around there. It depends on the contract that you have with Microsoft or your organization has Microsoft. Question to you, as I'm not an expert in the co-pilot universe, if you have the agents on the left tab, it means you can create them and use them.

18:16Or if you just want to use them, you don't even need that kind of a license. It's all or nothing from my understanding, but things are pretty dynamic in Microsoft's billing world. But right now, if you want to use agents, even if somebody else built them, you still need the license. Yes. Got it. Okay. Yes. And so, uh, but I know how big organizations are. Sometimes you have to, uh, create a full business case that takes you more than$200 to build for your$200 license. Okay. Yeah. Yearly, yearly cost. Yeah. I'm with you. So if you have, uh, agents here, um, then basically there's a button on the left that says new agent.

18:58Okay. You can click on that and that will help you create a new agent. Okay. Now, if you're familiar with, uh, GPTs, uh, in the chat GPT ecosystem or the open AI ecosystem, they're very, very similar to a co-pilot agent. And I really use agent loosely here. Okay. But that's what they're calling them. So they're an agent. Uh, and when you, when you get when you open up a new agent okay it'll give you two options you can either describe what you want the agent to do and then it will build it for you or you can hit the configure button and the configure button will let you fill in your own instructions now technique only i like to just fill in my own instructions and the agent and i do that with the use of another llm and so we're exactly the same i've used the the describe option in custom gpt exactly zero times even though i've created dozens of them between my company and client companies and i teach people how to use a regular conversation with whatever your choice of tool is to develop the instructions for the custom gpt so we're 100 aligned and guys we did not coordinate this in advance so two separate people who do this for a living tell you this is the right thing to do maybe that's the right thing to do.

20:16All right. Well, we're both type A former pilots. So that's probably what. Fair, fair. So when you go through, to your point, I like to do that because then I can test it and then update the instructions on the agent. And so when you are creating a new agent, you have to give it a name. I like to give it something that sounds useful. Because remember, I'm building these not for myself. I'm trying to build these for a team or an organization, right? And I'm using these to help an organization become more aligned. So I want it to be named something that makes sense. So there's beyond the make sense.

20:56You said there's a marketing aspect to it. Yeah. Right. It needs to sound valuable. Right. Yeah. And then there's a description of your agent below it. This is really informational. The agent doesn't use this. Okay. And it basically says, what is it that, you know, so someone opens it up, they can to see what it does and then the instructions are where you make your money okay uh and microsoft gives you about 8 000 characters which is enough yeah from my experience okay and remember when i said earlier these need to be valuable and then also incremental so when i'm building these i'm scoping these to a specific business problem and i want to keep them limited in scope that's my technique so i don't want an agent that does five things, I'd rather have five agents that do one thing.

21:44I'll say two things about what you said. One about the last thing, which is I agree with you a hundred percent for two different reasons. A, they're easier to build. B, they're a lot more consistent in the results. If you try to build one agent that does five things, you will most likely get them to do roughly the five things instead of actually doing each and every one of them perfectly. And you can always just then string them together with some other automation tool that will know how to transfer the data from one step to the other, or you can do this manually. You get a lot more control and much better results.

22:15That's one thing. The second thing about the 8 ,000 characters, and I know we're going to talk about it in a minute, but there's also the knowledge base, which is a bunch of files, and this allows you to dramatically extend the instructions. So if you want to give it examples of what good looks like, you don't have to write the example of the instructions. You can say, look at example one and example two in your knowledge base, and this doesn't count to your 8 ,000 characters. And then in one sentence, you added 20 pages of examples. And so this is another way to cut the amount of text you have inside the instructions themselves, if for whatever reason, you hit the 8 ,000 character limit.

22:50No, that's a great point, right? And I'll talk about knowledge base in a second. The final thing, one thing I also mentioned is the other kind of pillar we talk about is sustainability. So the same reason engineers went to microservices is the same reason you should have kind of one task agents whenever possible. They're easier to update. You update one. You don't have to update the whole monolith of an agent. Okay, so you make your instructions, and then at the bottom, you can add in what information you want to train the agent on. You can do this directly off of your SharePoint. And one of the reasons I love this idea of building your own M365 agents is that it's all inside of the Microsoft firewall ecosystem.

23:39If you can send it an email, you can build it in an agent. And so I don't deal much with security concerns because I'm just using capabilities inside the fence. Okay, so you can add in different websites, URLs, documentation that's in the SharePoint. You can upload actual documents. But generally... Teams channels as well, right? They're now fully connected into Teams. so you can train it on like a specific channel. Like you said, anything in the Microsoft universe, it could be a source of data for the agent, which is very powerful. Yes. And I'll say Microsoft is rapidly prototyping and updating this.

24:17So this could look totally different than what I said tomorrow. Okay. But generally the capabilities allow you to upload and there's a huge limit on files. Now, if you're doing this in a Gmail Gemini space, right now they're limited to 10 source documents. All right. But Microsoft, it's like 10 ,000 or something ridiculous. Okay. The other piece I want to say that I think is interesting here is this idea of only using specified sources. Okay. So there is a tab underneath the knowledge base. And if you click this tab over to say only use specified sources, you are telling the agent only to use the documentation you loaded.

24:59No guessing, no going out to the internet. And so for the agent I'm going to show you, I think that's a valid button to select because if I'm talking about agile processes and how we do business, I don't want every other agile coach out there giving me their slightly horrible idea of how to run a sprint planning or whatever. So when you select this button, you've essentially turned it into a chatbot. Yeah, so to explain to people in a broader terms to be very specific, you limit the universe of the agent to a very specific data source and only to that data source. So whether it is you're doing agile planning, like Nate is talking about, or you're doing any kind of project management or employee handbook, how do I apply for maternity leave?

25:50Then you want it to just go to these two HR documents and that's it. And this is how you force the AI to do that, which is extremely powerful because in most cases, unless it's a research agent, that's what you want. You want it to only go to the sources you give it. And the combination of that together with the fact it's already in your Microsoft universe, you already have these documents, just makes it really, really easy to work with. Absolutely. And the use cases for that type of agent, which I'm kind of calling an information agent, is really broad. And, you know, I was less excited about it at first, but then when I started using the application with clients, it was like, oh, this is actually really powerful.

26:31The ability to do HR processes, if you have a huge regulatory environment, getting all of the regulatory environment in there so you don't have to spend hours hunting through even a software development space, even like specific user manuals for your software development product. I'll give you another broader example. I have several clients who are in the manufacturing space or in the product space, and they have a product catalog the size of the United States. And you want to know the part number for this and that skew from this and that year for this and that product. And to find that historically, yes, you can open 17 different documents and run a search on each and every one of them until you find the correct thing, or you can write one sentence in this and it will just give you the result.

27:19Yeah. So there's a huge use case for this. And I'll show one briefly here, just to wrap up how to create them. You can also create suggested prompts. I think this is important if you're sharing this across a broad audience of people in an organization. So it lets them know what this agent can be used for. Okay, so you just put a title and enter a message. And then essentially - By the way, these show up as like a button. So people basically see a suggestion on the screen. So if they don't really know how to use it, it gives them ideas on what they can do with it. So your most common use cases can already be there.

27:54And so people just click the button. Right. And then once you feel like you have it, you can test your agent while you're building it on the right-hand side. And then when you're ready, you can create it. All right. And so that's essentially how you build a new, you know build one of these okay so um i i'm going to jump in and show an example here the first one i call it the ways of working guide the context for this is i was working and this is just kind of a replica a demo replica of one i use with the client but you know we built an entire program of how to do software development and all the way from how we get product requirements in to how we do releases, you know, how we do our ceremonies in the agile world, how we do reporting, how we do metrics, all of these things.

28:45And so, but people are always changing in and out of an organization, especially if you have like a hundred person organization. And so having a way to keep everybody standard on the process, knowing what the process is, and then using this agent to help kind of democratize that across the organization. So this agent is trained on some process data, right? And it's process data I built or we built, and it's configured to the ways that we do things. Okay, so I can ask questions like, you know, what sprint are we in, right? and this agent which is i'll show i'll show you the back end after i do a demo here but we'll look through the the documentation and we'll give you what sprint we're on what what uh holidays are coming up um and it's just it's just a quick way to find the information you need okay um you can also this one is actually interesting so i have a question about this because we were talking about information on SharePoint, which is usually static data, meaning like guides and instructions and stuff like that.