Agent Governance Explained- How IT Can Enable the AI Agent Revolution with Thomas Zou [Microsoft]

We can. Yeah, welcome back to the MC65 and podcast, the podcast where we explore Microsoft AI, co-pilot, power platform and the technologies that jet in the future of work. Over the past years, we have seen an exploding of AI agents, but thousands of agents, potentially being created inside an organization, comes a new challenge, who go of them, who secure them, who decide what they can access. Today's guest is helping define the future. Joining us, joining me today is Thomas Stoo, product marketing manager for Microsoft co-pilot studio with a strong focus on agent governance, helping organization scale AI safely, while empowering innovation. Today we'll discuss about co-pilot studio governance, security, lifestyle, a life cycle management, compliance, IT leadership and why governance is not the blocker. It's a foundation of enterprise AI success. Yeah, welcome Thomas, today ends the 65 podcast. Well, thank you for having me, Marko. And thank you for giving me this opportunity to talk about governance for agents. Yeah, it's really interesting. But before we deep dive into the topic again, can you tell a little bit about your journey, how you end up on Microsoft? Yeah. Well, I started as a journalist. So it was born, raised, John, a startless journalist. So to me, storytelling and narratives are always very important to me. And that is fundamentally how I think about my work is tell stories of the product, tell stories of the users of our product. And then I, after graduating from breast school, I went to a startup for a couple of years, and then in 2022 I enjoyed Microsoft. My journey within Microsoft has been full of adventures as well. So I was a PMM working on the security side of things. So defender. And earlier, 2026, I joined the COVAILA studio team as the PMM covering governance for the platform. Yeah, what does a product marketing manager actually do? Yeah, that's a great question. So my way about thinking product marketing manager is really, if you divide the traditional founders role into two parts, one is more technical, one is more go-to-market focused, then you would say that the more technical side of the product owner might be the product manager. And then the more go-to-market, the more sales or enablement side of the product owner or founder would be the product marketing manager. There are really two sides of the same coin. More specifically, what I do on a day-to-day basis is a couple of things. One is the positioning and the messaging of the product. So, you know, different people have different opinions about what the product is good at, whether the product is not good at, or how to differentiate. But what we would potentially want to do is to summarize a systematic way to talk about what makes the product unique. And then make sure that we convey that value clearly with our core audience, which is IDM. The second one is go-to-market strategy. So, defining how do you sell the product, defining how can you engage with our customers so that they can trust you, so that they can understand your value proposition. And the third one is content strategy. So similar to what we're doing right now. So we use different content forums. We use different content formats to talk about the value proposition and the differentiation of the platform. Yeah. And did you sell views for co-pilot in your daily work? Oh, yeah. I join this team because I'm a big fan of the product. And I just felt like there's such a wave that I cannot miss. And I felt like, you know, generate a Baye and Agentic Ai is the future. And I really wanted to be a part of it. That was one of the bigger incentives. Yeah, interesting. So actually, I say everyone, every company wants AI agent by the few organizations have a governance strategy. So what exactly is an agent, what exactly is agent governance? Right. So there's so many different ways of defining agent governance and different, depending who you ask, the practitioner view and leadership view and analyst view, but maybe different. But from my side, my personal take on it is a quite simple one is, how do you enable makers to innovate? Right. So it's the, you can't say it's the policy. You can say it's the process. You can say it's the technology. But ultimately, the goal of governance is not to become the police and then say, well, you cannot do is really to build a foundational infrastructure and framework so that your makers who are the adoptors of agent within organization can feel confident about how to innovate, how to experiment and how to deploy, how to scale. So those, those sat of rules or policy or process, however, call it together makes up to the agent governance. Did you see, yeah, misconceptions companies have about agent governance? Yeah, all the time. I think a lot of people when they think about governance, they have this very bleak and this dear view of someone that's really strict about policy and tell people, hey, you cannot do this, you cannot do that. Or people think that governance is really just about blocking everything or governance is about turning off things, not allowing makers to innovate and build. Right. In fact, for the longest time that is governance, that is how you prevent risks from happening without giving the right channels and opportunities for makers to innovate and build. But with modern technology, with infrastructure that you have, with co-pilot studio or other products, you can really have that granularity and layers of management and governance so that you don't have to always trade off one another between innovation and risks. You can have good control over risks while also enable or facilitate innovation. That is ultimately, I think, what makes up good and bad governance. And when or where should governance begin? Yeah, I would say it usually, for less, less, use a fictional organization, as I said, as an example. One thing would typically tell our customers is that from our observation, the adopters and the facilitators or the administrators of the adoption within an organization are usually not the same people. And the people who are responsible for hair governance a lot of times are ITAMX. And you asked the question of where to begin. I would say that it should begin with IT. It should begin with IT having a very good view about the reality and the readiness of the organization in terms of a couple of aspects, right? AI strategy, whether they have a good foundation for AI education, readiness for different and technology and business strategy, do they have good business process mapping? And then do they have the good cultural and behavioral enablement for their organization and employees? And the movement out from there is more so the governance and security. Okay, now if your organization is already ready for AI agent adoption, do they have the right and the full back mechanism when things go wrong? There's a process of what in there, she should think about adoption and governance and security. And then we have some really good content around this called AI readiness, agent readiness framework or agent readiness assessment that helps ITAMX to go through a survey for free and then quickly understand where they are in their agent adoption journey. But yeah, I think it should start with IT assessing, understanding their reality and then setting up a plan for their entire organization to adopt agents. Is it something like a maturity model? You have there for for for, yeah, measure the readiness or how it works. Yeah, you're right, Michael, it is like a maturity model. So we worked with analyst firms and also our internal customer adoption teams to basically summarize and synthesize the patterns of which the major customers are adopting agents and then we identified different stages of readiness and maturity for these customers and then we also have recommendations for what customers should do when they have identified there in a certain maturity model. So because when you are, when you, when it's the first time for you to hear about agent, then you're caught through actions and mechanism to adopt agent might be very different from a team that already have like three different tenants running for different governance models that needs to be consolidated. So we try to be customizable, we try to be flexible with our guidance and any development. Ultimately what we're trying to do in here is really to establish a AI center of excellence we found a lot of the times, agent adoption doesn't come from the bottom up necessarily. It's a it's a two way street, right? You need to have interest and passion from makers, but you also need guidance from what we call it like a governing body or a group of people who have a lot of expertise and best practices that pass down those knowledge and upskill the rest of the folks. Like the champion program, right? Exactly, exactly. I think when it comes to governance, there are two teams in the innovation team and the control team. So how did we find the balance between innovation and control? Yeah, that's a great question. In fact, we have a good content series on YouTube, specifically on the Power Platform community channel and the co-hosting YouTube channel talking about this. It's called agents under control. It talks about IT's point of view on how to potentially adopt and govern agents. But to answer a question, we just talked about this in an episode called what is zone governance? The answer is basically zone governance. And it's a term that is not invented necessarily by Microsoft. It is really an industry or a grid upon pattern. I'm sure you have heard of it. First brought out by Gartner and other analyst firms, but really it's a model for setting different governance policies and different boundaries for different types of innovation and adoption. Let's say if you have a group of users that are really, really experimental, they just want to play, they just want to have a sense of understanding of the product, then the risk tolerance level for this group of users might be very different from workloads or apps or agents that needs to go into production that connects with actual business data and it's exposed to the customer. So the idea is you define different innovation and risk tolerance based on different policy controls within what we typically use PowerColiform M in Center or Microsoft 365 at the center. And then you set the different policy talent for these zones. So we typically zone into three or four buckets, typically three, agree zone, the yellow zone and the red zone and the risk based on the colors, but restrictions and governance level of control also increase. So the idea is that for lower risk agents, innovation, you can put them into an environment with a lot more components allowed with policy setup like Vesca and I call see let's say API fireworks, etc. Firewalls, but you don't allow that environment to be accessible to a lot of people. Maybe that is just personal environment that is only accessible from that user itself. So you can play with it, but you cannot share as much, you cannot expose that those innovation as much to people. The yellow zone is kind of the middle zone where you have some testing going on, where you have some sharing going on, say an individual has already built an agent that is the key things or she thinks is ready for testing and wanted their IT admins to take a look and can put that particular agent into the yellow zone. The yellow zone have a little bit more sharing flexibility, but also comes with that is more scrutiny with regard to its data with regard to its sharing policy. And the red zone might be it production zone where everything is business centric, where everything is sensitive. So if you want to put things in there, you have to go through the approval of IT admins. So by defining those different zones, we help IT admins and their makers really adopt different level of risks quite quickly. >> You're a product manager for Co-Pilot Studios. So how did Co-Pilot Studio support governance today? >> Co-Pilot Studio itself is a largely, it's an agent building platform. So the governance structure around it is across different places. Because there's a product born out of the power platform family, a lot of people know this. The majority of controls and amin knobs, if you may, exist in the power platform and the power platform is a play where you do what we just call a zone governance control, which is at the environment level. If you want to have 10 level, like umbrella level control over how agent would act after it's been deployed, then you have another control plan, which is the Microsoft 365 and the Microsoft 365. You might also have part of agent 365, which is the new control plan for the operational stages of agents across different platforms built within or without within or outside of the Microsoft ecosystem. So you can also provide governance for third party agents, let's say, from our partners. So you really need this layered approach for the full int and governance. I would recommend ITNs to start from the power platform, I'm a senator, to get familiar with the controls and policies that are in close vicinity with Co-Pilot Studio. But if you want to have anti-end journey taken care of, especially advanced security controls integrated with Entra, Defender and Perview, I would say the, Mac, the Microsoft 365 and the center and if it's a five control plane, it's somewhere that you need to take a look as well. And so I think a little bit, who owns an agent? Is it the business or is it an IT topic? It is a very interesting and complicated question. I would say this is a very diplomatic answer, but ultimately it needs to be a combined ownership and different teams should own different things, right? And this is what we talked about in the IT center of excellence or AI center of excellence concept as well is that the enable Asian innovation is really a team effort. Let's say there's a business team who understand the business process and their day to day routine intimately. They are the ones who would feel the benefit and the impact of agents efficiency and day to day process automation the most. And then they understand their challenges and their pain, their pain pullings have inefficiencies the most. So they are the ones who should be responsible for summarizing the business process that needs to be automated, that needs to be consolidated into Asian workflows. So they are the one who needs to provide the business logic and knowledge. And obviously there is the IT team. IT team needs to give the business team or the frontline team the knowledge and make them feel comfortable and confident about turning those knowledge and business process expertise into tangible agents and technology that they can replicate for the rest of the organization. And obviously there is also the executive team who are responsible for sponsoring these activities, making sure that IT have enough resource, enough influence over other teams around how to do governance around how to do security around how to implement vast practices and not promote agents sprawl. As we know if you don't have Asian governance structure in place that people still innovate, it's just they create shadow agents, they create shadow processes and automations and it becomes really hard for the security measures to be in place because who knows what would happen if the employee connects a sensitive data set. Let's say with their customers names and social security numbers directly with a public facing agent and the agent does not have any prompt injection, production mechanism and anyone can ask questions about their users, social security or even credit card information that will be not in that scenario. So again, back to your point, it should be a collaboration between different teams and it should be a trusted platform and excellent center of excellence structure. And from your experience, how should organizations manage the agent life cycle? That's a good question. Again, I'll go back to the origins of power platform. Power platform introduced the concept of application lifecycle management through pipelines. Typically, there are the idea of solutions within the power platform where you can build a solution, essentially it's kind of like a repo and GitHub. And then you can move the solution along with its dependencies through different environments with different level of control as we just talked about the zone governance concept. And you can do lifecycle management that way. You can put a solution into a experimentation zone and then a yellow zone and then red zone. And then the IT would set up governance policies around what are the requirements for the red zones and what does mean for an organization to take a solution into production. So those are the concepts that exist within power platform. Obviously within the innovation community of COVA Studio, we also try and make the platform more accessible to third party integrations. So it is not uncommon to see people use GitHub as another tool for source control or Azure DevOps, which we always recommend and to take experiment with because you never know which platform works the best for your organization's unique reality. So I would say that if you are someone who is thinking about version control and lifecycle management, try different things, try different templates and then there are plenty of guidance from the COVA Studio adoption side or the COVA adoption teams on back practices and blog that you would found really helpful. I'm sure a lot of audience of this podcast have heard of them and used them. So if you have any questions, don't hesitate to reach out to us as well. We have tech community where we answer questions and aka forums. So yeah, those are all great resource thinking leverage to understand those resources. Yeah, I think we are now in an era where we have to agent to agent or multi agent, or build this stuff. I think organizations can have hundreds or thousands of agents. Does there a good way organization can monitor agent usage? Absolutely. Again, it goes back to what we just talked about, the layered approach in governance and security. By the way, when we talk about governance, I'm losing this term very loosely. When I say governance, there's really a couple of things. It's about the administration of how agents are created, how they can be created, and then how they are secured and protected. And then how can we scale agent across to what we just talked about, the pipeline and then the transformation of culture and behavioral patterns of the organization adoption journey. So when we look at those four things, I think one good thing for the IT Amons or anyone who's interested in governing them to think about is what tools is available to me and how should I combine those tools. Again, it goes back to you have Power Platform, MS Center and then you have A3,5. You can set up different levels of policies within those two platforms and then use those combined efforts to give you a good granularity, but also umbrella control. Yeah, I think yeah, traditional IT management devices, tomorrow IT, they manage a couple of these AI agents. How is the IT department changing? I think IT is also using agent workflows to automate their governance. As IT may fail overwhelmed by the amount of innovation that is going on now that not only agents are being populated, but also all kinds of agent work loads or tools. Let's say get up co-pilot. It allows agents or applications to quite possibly to be built so fast and erase so fast. So it's no longer a realistic expectation for IT to be the gatekeeper to manually approve or deny everything. They cannot have one-on-one meetings with every innovator every day to walk them through the best practices. They need to think about automation and scale as well. Again, it goes back to the Center for Excellence concept is that IT is really a nibbling function rather than a policing function. You need to figure out are the unique and repeated business fractions in your organization, in collaboration with your client or business owners and then proactively reach out to them about how to use agent work loads to automate. And then when it comes to say risk management and governance, you should also have probably agents built for your own work loads like IT, Q and A, maybe is a good use case. Where you summarize the governance, brass practices, business process, approval process, application process into a set of grounding documents and then use agent to answer preliminary questions or another good example is approval. Let's say a user wanted to submit an agent for publishing. What are the rubrics? What are the criteria for you to prove or deny that agent? You should make that explicit and then pass that knowledge down to users so they can basically do a self-check before they submit everything for you. So if they can self-identify certain risks or governance loopholes, then they will solve them themselves or you can set a set of requirements, hey, is this agent, does this agent have authorization? Does this agent have basic sensitive data control over what type of connectors has been connected? Does this agent have basic prompt injection protection established as a part of the platform? All those things should be embedded into those process requirements and then from there you would found the escalation rate would reduce by quite a lot. Another good thing that IT can start to do in response to this change is to not use default environment anymore. So if you have a default environment in the power platform, concept and then use that default environment as where people go by default to experiment that after a quick while there will be a ton of agents from there and it will be so hard for the IT admins to clean it up. So leveraging features within the power platform, like if I'm a routing or personal environment would help that situation by quite a bit. So I think IT should be at the forefront for understanding what new technology and processes and toolings are available to them, quickly adopt them themselves and then summarize those as practice practices and help them to transform their own work as well. And I think we have all so much of our tools for Microsoft. So for an administrator, what roles do Microsoft, ENTRA, ID, place in this new AI agent area? And this is a great question. I think it is to answer shortly is basically the future because you would think about the vision that Microsoft have for agents. Ultimately we would want agents to be able to perform, to have the capability or possibility to perform at the same level as a human employee is not going to replace a human employee for sure. But let's say if I cannot attend a meeting or if I cannot go to a certain conference, then that agent should be able to embody my knowledge, my point of view and my judgment. So in that regard, with that much of agency, you also need that much of control and governance around it. So really the idea behind getting every single agent and enter ID is around, hey, Microsoft, you already have this great infrastructure for managing human employees. And then as you're familiar with in Microsoft 35, MS Center or other control planes, why don't we use those knowledge and vast practices to manage agent take employees as well? And obviously the innovation would keep happen for how advanced how autonomous agents can be. I'm not here to make promises around, hey, down the line for how long agents would be just like humans, but why don't we just slverge the existing technology infrastructure so that by the time we get there or by the time we increase our agent's capabilities, the again, the security can be in place, the policy enforcement can be in place for those agents. So enter ID is really a important step for us to go towards that so that the management of agents can be similar or consistent with how we manage human employees. Yeah. I started with, yeah, Gibo and Microsoft technology, I came from the from the Niger science part. And there were one tool, oh, I hated it. At this time, I hated the most, that's my favorite. But how important is this Microsoft view when we think about, yeah, ag. Yeah, per views is I think one of the important cornerstones of making sure agents are performing securely and protected, right? So per view at its core is about protecting data is for protecting data from leaks is about protecting data from reached. It's about protecting data from intentionally or unintentionally shared without the bound that is supposed to stay with it. Right? So if you think about how an agent acts in runtime, when we are talking about protecting agent, what we're really saying is that we're protecting data, right? Because if the agent does not have access to sensitive data or data that you want to protect, then what is the risk of that agent for your organization really? Is it that it would act in a way that it's going to damage your, um, damage, damage your business process? Not quite likely because you already have a good prompt that's going to set the, the, has been set up to limit that agent's capability. So how do we make sure that first of all the access of that agent is protected is monitored? And then how that agent shares data is protected and monitored is very important. If we use the connector concept within Power Platform to control how agents can access data source and share the data, then on top of that, per week gives security, I'm in Zanitium is really a more granular and more nuanced view on how the agents deal with data. A good example of this is sensitive data labeling, right? So if you ground agents with a sensitive data file, then, and then you set up a policy saying that agents should not share a sensitive data outside, then obviously, per week would help agent to enforce that policy. But if you don't have the sense of sensitive labeling, you cannot do that. And the best part about it is, per week is already integrated with your Microsoft 365 ecosystem. So you don't need to have your employees enforce another layer of manually tag sensitive data labels to refiles to your business processes. This is the first thing, the second thing is, or unintended data sharing, that is so it not supposed to happen, right? Purpose would block you from literally copy and paste, saying that information into external sources. And then such behavior would also be flagged to ITM and so that they can target certain on ethical behavior inside a risk or so on. So all of these is about prevention and also reaction. You should have data security, post-traumatagement to understand what are the risks going on in your organization. And when things do happen, there should be immediate response to those risks and purview is at the forefront of that. And I think some agents have to work with sensitive data or have to write or read data that's sensitive. Is there other things, especially when I have these kinds of agents, how organization can secure them? Yeah, I would say again it goes back to the layer approach. The real first layer is you need to have environment level controls. If you feel like certain things that you just want to make sure the agent never touches, then don't allow those data connectors within certain environments and then put that business critical agent into that environment. That's the first thing. The second thing is use or just talked about the, it's a five layer or the Microsoft Security layer, right? You can use policy templates to say, hey, all the agent within my tenant have to be attached to this Entra Access package and then you can disallow certain application access from those packages. So that's the first thing. If you have to expose certain sensitive data to very specific people, then that I would say use the right authentication methods, right? So make sure that you have authentication gates using Entra or other MFA providers and make sure that those people who should have access to that particular agent is bounded by certain security groups and they can configure that Entra security group with the access pattern of the agent. The one big best practice is never allow sensitive data to be accessed through agent that is unauthenticated, right? If you want to make sure that you expose sensitive data to specific people, then authentication needs to come in place with a lot of scrutiny. Yeah, I think what do these things can governance become a self-service? Is there a game? Do you have that question again? Yeah, can governance become a self-service? I think that's the goal. I mean, obviously not 100% of governance will become self-service, but as we talk about, increasingly, the industry is moving towards more automation and there should be certain mount of governance that would become a self-service. And also, like we talked about, governance is such an all-encompassing thing. The approval process should never be fully self-service, right? There should always be human in a loop for deciding what can go to the entire organization or go public. But things like upskilling, things like knowledge transfer, things like business process summarization, or basic rules and guidance, those things should definitely be self-service. And it can exist in the form of SharePoint. It can exist in the form of agents. It can exist in the form of simply a Word document, but ultimately, again, typically IT amens are overwhelmed. So they knew you'd think about ways to reduce workloads for them and make sure that they're not always working. And thank you. In the future, AI will eventually become a AI. Can you say it again? Sorry? Yeah, yeah. Well, in the future, did you think AI eventually become a AI? I think not fully 100% human in a loop will keep being very important, but I do think we're going to keep moving to a direction where that is happening. One good example of this is that if you go to your agent store in Microsoft 365, co-pilot, then there will be an agent called Microsoft 365 Amin Center agent, the Mac agent. And that agent already can help you to govern a lot of the Mac activities. And we're building to or something that is similar to that within the PowerPaf form. So yeah, I do think that those futures and those visions are slowly, but surely coming true. Yeah, especially for me, AI living in Europe, Germany, so there's a topic, the German laws, the rest of the world, not its compliance. How can I think in this multi agent world, and we have the EU AI Act, and they have done a lot of compliance stuff? How can Microsoft or tools help here to get all these regulations done? Yeah, this is a great question. I know it's the top of mind for a lot of the highly regulated industries and NGOs. I first of all, I would say that this is just my personal device. It's probably going to be very comprehensive, but I can provide some thoughts on directionally how can I approach this. And again, it's highly nuanced topics, so don't treat this as like legal advice or anything who does not represent Microsoft's point of view. I would say, first of all, you need to understand your unique reality and the requirements for your industry for compliance. Not every industry, every geo share the same compliance requirement. And from there, you need to consult your legal entities for, like is there a specific framework upon which they need to follow? So the EU AI Act might be a framework and the US might be another. So what are the framework that you need to adhere to? And based on there, there are best practices or industry organizations or product that can help you out. In the realm of co-pilot studio, one simple thing that you can ensure that would help you is autologging. So documenting everything is basically a foundation for compliance. If you don't know what has happened, there is no way for you to do autotrails. There is no way for you to understand your compliance posture. So definitely turn on autologging within co-pilot studio. And then it goes back to the layered approach. Now with co-pilot studio infrastructure hooked with autologging, you also need tools like Perview or Defender for you to understand your security logging so that combining those investigation and locking capabilities, you can then morph and bespoke your compliance reporting to the requirements of your governing body. That would be the directional feedback that I'll have. Yeah, interesting. I think a little bit about AI adoption. I think technology doesn't create the adoption. It's not the tool. It's the adoption. But what makes an organization successful when they adapt agent? I think it goes back to what we just talked about the collaboration between the interpen teams. What we have seen is organizations that are better at others than others at adoption are typically the teams that have very strong vision for what does great look like in terms of AI center of excellence and then have top down support from executive team to sponsor those adoption journey and learning activities. So it needs to be a pull and a push mechanism. But the frontline innovators and makers they need to start experimenting but also experiment within the scaffolding that's defined by IT teams or the executive team or the IT center of excellence. The leadership team should also be very specific about how can the frontline workers adopt these best practices and then endorse the governing. The governance structure put in place by IT teams. Endoors the activity that would upscale more people and quite frankly just put this as a top of line for the company. Because business process automation and efficiency will always benefit the company's organizational efficiency in the long run. So I would say start with the AI center of excellence and go from there. And I think yeah, Microsoft had done a big commitment to AI and there it's coming. So many new stuff, feeling everyday, something new. So yeah, how do you not got overwhelmed with all these information? I do go get overwhelmed by all these information where I go. I'm a victim of that too. Yeah, it's just, you cannot avoid it. We all know that the world of technology is moving so fast and it used to be the case that I can try catch up once a month or once a quarter with newest technology. Spend one Friday on the new tech and feel quite confident about all at least what is going on right now. It's a longer case. The speed of innovation is significantly outpacing the human capacity of learning. So I would say that I just acknowledge the fact that feeling overwhelmed will be a new reality. You just need to know what is your priority and what is your area that you really want to get good at and start small. Another thing is my personal guide that I try to follow is try not to think about knowledge retention as progress because AI is replacing knowledge retention. What really defines progress is your ability to hone your craft and the difference between crafting and knowing is really the process of doing. So I try to learn by doing and try to get deeper on to certain topics based on my own hands-on experience rather than hearing other people's second hand knowledge. And yeah, that's how I deal with all the roping world. What about you? Yeah, I have an agent that puts all from LinkedIn and all other sources next year short briefing daily. Yeah, what I do. That's why I would do it. When we don't think it's overwhelming put in the agent world or in the co-pilot world, I think oversharing is there that this is worth. How can we prevent from oversharing? Well, first thing is you need to know what are the things you don't want to share, defining those boundaries. And that is through in the Microsoft ecosystem, through since they've been labeling, through seeing the right document with the right labels. And from there, the rest of the technology would help you out, right? And for instance, if you are in a Microsoft 3.0.0 planet, then you won't be able to have access to things that you don't have access to. That's the first thing. The second thing is, again, leveraging connector policy and environment controls like we just talk about. And of course, you can also use what we talk about, purview and defender to first prevent excessive data from being leaked. The second thing is when people do try to gel break and do prompt injection or try to host an A or co-worse the agent from giving out information. And you can have some kind of production mechanism. Yeah, Microsoft is an awesome technology company, but is there any technology that's excited you outside for Microsoft? Absolutely. I think to be honest, most of the technology that I'm excited about is a combination of Microsoft technology and open source, right? And you see so many folks from Microsoft contributing to open source, sometimes, casually, sometimes as their full job. I think that's something that I really love about Microsoft is how much it embraces open source over the years. And then you see people like Scott Hanselman who work on GitHub co-videal app as I see right now. And I know that I'm a legendary figure of VP in Microsoft, but he's working in I see capacity I now. And working in open source. And of course, things like open claw, Hermaz agent are no good tools to have. And you can find so many quality technology out there that are just being contributed by both human and agents right now. And that's what I love about agentic broad as well is that you can amplify and extend this human goodwill to the open source community. In particular, I would recommend one specific open source technology that is skills for co-videal studio. This is a piece of tool that is collaborated between Microsoft employees and the open source community. Essentially allows co-videal agent like an opcopilot or a clock code to know how to use the backend of co-videal studio. Right. So if you tell a generic coding agent to build a co-videal studio agent, it might not understand the schema of how orchestration work in the backend for co-videal studio, but would that skill get up co-videal would be able to connect with your actual co-videal studio account. You can read your co-base, you can read your agent inventory, and then it can help you modify agents. You can help you to build new tools, build new adaptive cards, things that you want to automate quite a lot or even e-vals. So yeah, just really leverage both the product itself and also the open source tooling that you have available to you and you would soon become a very capable ITM. Because there are, have you a favorite co-pilot capacity? A capability? Yes. Well, if you're talking about co-pilot in general, meaning that if you're talking about co-pilot as in Microsoft's agentic, who's assistance, then I would say my personal favorite is probably get up co-pilot either in register code or get up co-pilot app. I've been recently experimenting with both and I just found that they both have their quirks and features, but I really feel like if you are someone who is already familiar with GitHub and who loves using GitHub as your main source of operations, DevOps, then you would love get up co-pilot app. It just fits in so well with your grooves, how you think about the entire process, where to a degree where things just make sense, right? Things like you can start a different session with different issue and then the agent would try out for you based on it should relate to automation and then you can basically turn your open source repo into a swarm of agents that helps you to look at issues overnight and then help you to identify things that requires your attention. It would be a dream for maintaining a big open source project and it can save so much energy and time. Yeah, that would probably be my favorite. Yeah, I think it's really strong to get up co-pilot. I'm more the edge of that off span. I hope we get a guess. The co-pilot also was the same strange here in the future. Is there a co-pilot studio feature where you wish more people use or know about it? Yeah, well, co-pilot studio just announced its new workflow builder and also new orchestrator. These are very underrated features so far. We're trying to do a better job at helping people understand the significance of these features but ultimately, you know, take time. But my plug in here would be try it out yourself. What defines the new orchestrator is really it would now be able to think and act like the cutting edge coding agent that you are familiar with like get up co-pilot. It would reason it would have Asian loops will be able to use tools and skills in a more smarter way and you would soon realize that the new Asian orchestrator with a new workflow goes way, way beyond then typical what we call process automation now. It has a lot more thinking power. It has a lot more system compatibility. It has a lot more extendability. We have a lot of resources on co-pilot studio cat team's blog and you should take a look and we have a lot of examples and templates as well. It would be fun. Yeah, awesome. I have to try it out next time. Yeah, so yeah, this was an amazing session. When you say organization should improve one thing tomorrow, what should it be? I would say ask yourself are there people that you would call champions in your order or organization to enable an adoption outside of you? It is like one person organization that does not count. For a typical organization like we talked about having a small group of people serving as the kingling, the seas for more innovation and then have those people to help people out and make sure they are incentivized to do so. Have hackathons, have innovation summits, have competitions and then make sure people feel like innovation is encouraged and incentivized and slowly but surely you will get there. You just need to start trying. Yeah, normally my closing question is if listeners remember one lesson from today, what should it be? I think here we have somebody good lesson, so I do another closing question. What did you think when we meet in a year here on the podcast, what will we discuss then? I think we will be discussing autonomous agents. I think we will be discussing now that agents are becoming more capable as you have seen from Microsoft Scal, which is based on our architecture. How do we govern and secure these increasingly more well connected, well-reasoned and autonomous agents? With greater capability comes with greater responsibility and governance and security needs to keep up. I think that would be a good follow-up. Yeah, awesome. Thank you so much, Thomas, for joining me today on the MC65 on podcast. Today's conversation highlighted something. Every organization needs to hear successful AI is just about building intelligent agents. It's about governing them responsibility, security and scalable. Yeah, and I think we explore how co-pilot studio and the adults enterprises are already AI, why governance, yeah, actually, rather than slow innovation and how IT is evolving from managing devices to managing intelligent digital co-workers. So yeah, thank you so much for being here and for your time. So goodbye. Thank you. Thank you, Marco, for having me. [BLANK_AUDIO]