WEBVTT 00:00:00.120 --> 00:00:04.570 2026 has been the year of agents from open claw at the beginning of the year to now 00:00:04.653 --> 00:00:08.338 platforms like muse and grokbot and instincts that are getting people 00:00:08.421 --> 00:00:12.270 to actually take advantage of these incredibly powerful autonomous tools 00:00:12.353 --> 00:00:16.327 that are getting increasingly large portions of their work done for them. 00:00:16.410 --> 00:00:20.528 We really have gone from agents being the next big thing to just being here. 00:00:20.612 --> 00:00:23.071 The problem is our work isn't just done alone. 00:00:23.155 --> 00:00:26.610 We tend to work in teams with other people. And yet up till now, 00:00:26.693 --> 00:00:31.088 most agents have been solo affairs, only covering the portion of our work that we 00:00:31.171 --> 00:00:33.520 do on our own. I think that is shifting now. 00:00:33.604 --> 00:00:37.750 A trend which I've talked about as multiplayer AI or shared or team agents. 00:00:38.070 --> 00:00:40.309 But what does it mean to even build a team agent? 00:00:40.392 --> 00:00:42.821 What are the types of considerations that go into it? 00:00:42.904 --> 00:00:46.234 And how different is it really than just building an agent for yourself? 00:00:46.317 --> 00:00:50.025 Those are the questions that I get into with Nufar Gaspar on this Operator's Cut 00:00:50.109 --> 00:00:53.722 edition of the AI Daily Brief. The AI Daily Brief is a daily podcast and video 00:00:53.805 --> 00:00:56.405 about the most important news and discussions in AI. 00:01:08.070 --> 00:01:12.069 All right, friends, quick announcements before we dive in. First of all, 00:01:12.153 --> 00:01:15.925 thank you to today's sponsors, KPMG, Blitzy, Harbor, and HyperAgent. 00:01:16.009 --> 00:01:20.235 To get an ad-free version of the show, go to patreon.com slash aidailybrief, 00:01:20.318 --> 00:01:22.530 or you can subscribe on Apple Podcasts. 00:01:22.620 --> 00:01:24.649 And to learn more about sponsoring the show, 00:01:24.732 --> 00:01:27.032 send us a note at sponsors at AIDailyBrief.ai. 00:01:27.660 --> 00:01:30.053 Just a couple other notes before we get in. Obviously, 00:01:30.136 --> 00:01:33.445 this is a pre-recorded episode. There are a bunch of things cooking today. 00:01:33.529 --> 00:01:36.884 We will have a lot to talk about, so we will be back with our normal format 00:01:36.967 --> 00:01:41.917 tomorrow. I also wanted to share a couple of upcoming opportunities. First of all, 00:01:42.000 --> 00:01:46.203 this Thursday, October 1st, we have a free live webinar all about building 00:01:46.286 --> 00:01:47.797 your personal AI benchmark. 00:01:47.880 --> 00:01:52.392 The whole idea is that when you get a new model like Opus 5-5 or Sonnet 5-5 00:01:52.476 --> 00:01:57.417 or Gemini 4 or whatever model comes next, this will help you put together your own 00:01:57.500 --> 00:02:02.135 standard benchmark to better understand where that model is going to fit into 00:02:02.218 --> 00:02:05.664 your own process. That is completely free, and if you register, 00:02:05.747 --> 00:02:08.910 you will get all the materials after, even if you can't attend. Again, 00:02:08.993 --> 00:02:11.017 that is coming up this Thursday, October 1st. 00:02:11.100 --> 00:02:14.238 Now, speaking of training, if you want to go a little bit deeper, 00:02:14.321 --> 00:02:18.252 the next cohort of our super intelligent executive AI and agent training programs 00:02:18.336 --> 00:02:21.969 is coming up. The executive agent leadership program is where you learn how 00:02:22.053 --> 00:02:24.101 to build AI agents for real business needs, 00:02:24.184 --> 00:02:28.034 as well as building a playbook to scale them safely across your organization. 00:02:28.380 --> 00:02:31.645 And if you feel you need a little bit more background before you get into that, 00:02:31.728 --> 00:02:34.078 you can also do the executive catch-up program. 00:02:34.170 --> 00:02:37.048 The next agent leadership cohort starts on October 5th, 00:02:37.131 --> 00:02:41.330 while the next executive catch-up program starts a week later on October 12th. 00:02:41.580 --> 00:02:45.730 All right, with all that out of the way, let's talk about how to build team agents. 00:02:47.220 --> 00:02:52.027 All right, Nufar, welcome back to the show. We got an operator's cut today. 00:02:52.110 --> 00:02:56.864 Yes, happy to be here again. This one has its genesis in some conversations we were 00:02:56.948 --> 00:03:01.469 having as we were coming up into the fall around what we wanted to do with the, 00:03:01.552 --> 00:03:05.690 you know, this fall's edition of a free self-directed training program. 00:03:22.110 --> 00:03:26.706 in between people's shared workspace. And this kind of just follows the natural way 00:03:26.789 --> 00:03:29.975 that people work. A lot of your work is done individually, 00:03:30.059 --> 00:03:34.102 but then lots and lots is also done at the intersection with other people, 00:03:34.186 --> 00:03:38.819 and that's where team agents can live. And as we were building out that course that's 00:03:38.902 --> 00:03:43.202 available right now at Multiplayer AI and just thinking about this concept more 00:03:43.285 --> 00:03:47.585 broadly, one of the things that we kept coming back to was that this is nascent 00:03:47.668 --> 00:03:51.857 enough that what it means to actually build a team agent won't necessarily be 00:03:51.941 --> 00:03:56.407 super obvious. And so the goal of today's Operator's Cut is to help actually think 00:03:56.490 --> 00:03:57.600 through how to build 00:04:01.800 --> 00:04:04.733 are, different from or I think probably what we'll argue here, 00:04:04.816 --> 00:04:08.597 similar to the types of agents that people might have already built and where they 00:04:08.680 --> 00:04:12.680 can go from here. So super excited to have you back and excited to dive in here. 00:04:12.810 --> 00:04:16.773 Amazing. So I'm going to broaden your definition and I'm going to call them team 00:04:16.857 --> 00:04:20.264 agents. And the concept is teams that your entire team can work with, 00:04:20.347 --> 00:04:24.411 whether it's because work happened between them or just because they are something 00:04:24.495 --> 00:04:25.810 that can be shared across. 00:04:26.070 --> 00:04:30.184 team members. And kind of the short version is that some agents should stay 00:04:30.267 --> 00:04:34.101 yours and private, while others should become the team's level agents. 00:04:34.185 --> 00:04:38.298 And the ones that do become the teams need a few decisions made on purpose. 00:04:38.382 --> 00:04:42.160 Some of them, as you said, overlap with any good agent configuration, 00:04:42.243 --> 00:04:45.629 and some of them are more unique or at least more intentional. 00:04:45.713 --> 00:04:50.218 And that's what we'll walk through. And I wanted to start as a means of motivation 00:04:50.302 --> 00:04:54.639 to give you like two stories that you will probably recognize from your company 00:04:54.723 --> 00:04:59.571 or your ecosystem. So the first is about a person that everybody that I work with, 00:04:59.654 --> 00:05:03.837 every company that I work with has at least one like that. And this person, 00:05:03.921 --> 00:05:08.104 they really know how their price and exception work or what the data is all 00:05:08.187 --> 00:05:12.143 about or how our biggest customer setup was configured three years ago. 00:05:12.226 --> 00:05:16.979 And when they're swamped, then work has to wait for them because they're the only one 00:05:17.062 --> 00:05:20.733 who knows. And when they're on vacation, someone still calls them. 00:05:20.817 --> 00:05:24.230 And when they leave, a piece of the company lives with them. 00:05:26.070 --> 00:05:30.203 work with. They had, I think, a person like that for each and every domain. 00:05:30.287 --> 00:05:34.251 So no one gets to take vacation without getting a call from their peers. 00:05:34.335 --> 00:05:36.613 And obviously, that's not a desired state. 00:05:36.696 --> 00:05:39.480 The second scenario is work that nobody fully owns. 00:05:39.564 --> 00:05:43.247 So a customer can move from sales to marketing to customer success. 00:05:43.331 --> 00:05:46.845 And then sales made them a promise during the deal conversation. 00:05:46.929 --> 00:05:50.781 And marketing is running a campaign with slightly different messaging. 00:05:50.864 --> 00:05:52.270 And then customer success 00:05:56.070 --> 00:06:00.313 the renewal and each team has their own piece and nobody has the whole picture 00:06:00.396 --> 00:06:03.252 because the work sits between them. So to your point, 00:06:03.335 --> 00:06:06.469 and even if they are using AI in each step of the process, 00:06:06.552 --> 00:06:10.906 these agents don't talk to each other and only worsen the problem in many cases. 00:06:10.989 --> 00:06:15.454 So an agent that is built for the whole team can help with both of these problems. 00:06:15.537 --> 00:06:18.310 And they are, of course, quite different problems. 00:06:18.630 --> 00:06:23.182 So there is another reason, I think, why this matters right now and why you should 00:06:23.266 --> 00:06:27.592 pay attention now, even if you feel a little bit like this is above your head. 00:06:27.675 --> 00:06:32.171 And that's the pattern that I think what we're starting to see across the most AI 00:06:32.254 --> 00:06:35.337 forward companies. And it goes in basically three steps. 00:06:35.420 --> 00:06:39.464 The step one is that everybody builds their own agents and they are happy 00:06:39.547 --> 00:06:41.887 with their productivity boost only with technology. 00:06:41.970 --> 00:06:45.735 Enough of those running around, we kind of get into an agent's poll. 00:06:45.819 --> 00:06:49.641 Lots of agents doing overlapping work, each maintained by one person, 00:06:49.724 --> 00:06:52.584 each with slightly different picture of the company. 00:06:52.667 --> 00:06:57.055 And each one stops being useful the day that the owner loses interest or leaves 00:06:57.139 --> 00:07:00.791 the company. And then what you see in the most AI forward company, 00:07:00.874 --> 00:07:04.610 they started to merge some of those agents into team level agents. 00:07:11.970 --> 00:07:16.032 people and ideally refined over time as the team learns what they should 00:07:16.115 --> 00:07:19.140 and shouldn't do. And this is happening very publicly. 00:07:19.224 --> 00:07:22.019 There are many companies already talking about it. 00:07:22.102 --> 00:07:26.567 I think you mentioned Avery's experience. They started by giving every employee 00:07:26.650 --> 00:07:31.230 an agent early in the year and then by May they have moved to shared team agents. 00:07:31.313 --> 00:07:34.511 Sierra merged many of their agents, specialists into one. 00:07:34.595 --> 00:07:38.970 Shopify is internal agents. So we see a lot of these in very public speaking 00:07:41.970 --> 00:07:44.233 see are probably either in step one or two, 00:07:44.317 --> 00:07:48.490 but I think that it's very important for all of us to look at these AI forward 00:07:48.574 --> 00:07:52.747 companies and understand how to get to number three and how to do it properly. 00:07:52.831 --> 00:07:57.168 And that's the entire purpose of today. So to make sure that we are talking about 00:07:57.251 --> 00:08:01.370 the same thing, because there are multiple names to basically the same thing. 00:08:01.454 --> 00:08:04.427 Some people, including yourself, call it multiplayer AI. 00:08:04.510 --> 00:08:07.730 You probably also heard shared agents. Some people refer to 00:08:11.970 --> 00:08:15.881 into the mix or interchangeably used to mean agents being used with shared 00:08:15.965 --> 00:08:20.146 knowledge across the company. I'm going to refer to them throughout the episode 00:08:20.229 --> 00:08:24.572 as team agents. And what I mean by that is we have one agent that many people talk 00:08:24.656 --> 00:08:27.973 to with shared knowledge, shared memory, and one configuration. 00:08:28.057 --> 00:08:32.130 The instructions, the skills, the access, and the owner, they are all shared. 00:08:32.213 --> 00:08:36.394 And you might be thinking when you hear me saying that we already share skills, 00:08:36.478 --> 00:08:40.335 right? Most companies have an amazing skill library or working on a skill 00:08:40.419 --> 00:08:41.887 library. And that's awesome. 00:08:41.970 --> 00:08:46.113 and that's great standardization of how you do the work in the company. 00:08:46.196 --> 00:08:50.695 But a skill is a playbook for a specific task where a team agent is something 00:08:50.779 --> 00:08:54.029 that your whole team works with on diverse set of tasks, 00:08:54.112 --> 00:08:58.016 ad hoc as well as repeated stuff. It does carry the team knowledge, 00:08:58.100 --> 00:09:02.480 remembers what it learns, and using the team level skills if you have them. 00:09:02.564 --> 00:09:06.409 Those, of course, can also tap into skills marketplaces and so on. 00:09:06.492 --> 00:09:09.563 So a skill library perhaps is one of the ingredients, 00:09:09.646 --> 00:09:11.670 but they are not one and the same. 00:09:11.970 --> 00:09:16.542 And I want you to today think about how and when to start building your next team 00:09:16.625 --> 00:09:21.197 agent. And one more note on scope, because there is a lot of excitement right now 00:09:21.280 --> 00:09:25.679 about all of the personal agents. I'm talking about Muse and Instinct and some 00:09:25.762 --> 00:09:29.874 of the other in this category. Those are for like a home or private life. 00:09:29.958 --> 00:09:34.644 Today, the focus is going to be on work. So that's one thing to make sure that it's 00:09:34.727 --> 00:09:39.210 clear about the scope. We're talking about agents that you build for your job. 00:09:41.970 --> 00:09:46.926 A new study from KPMG in the University of Texas at Austin found that when people 00:09:47.009 --> 00:09:50.783 work with AI, similar skills don't guarantee similar outcomes. 00:09:50.867 --> 00:09:55.449 Researchers studied more than 500 early career professionals and found that 00:09:55.533 --> 00:09:59.927 the best performers consistently amplified the value of AI by guiding a 00:10:00.010 --> 00:10:02.250 evaluating and refining its outputs. 00:10:02.500 --> 00:10:05.329 These top performers, called AI amplifiers, 00:10:05.412 --> 00:10:10.205 weren't defined by what they knew alone, but by how they worked with AI. 00:10:10.289 --> 00:10:15.353 Learn more about what separates AI amplifiers from everyone else at kpmg.com 00:10:15.436 --> 00:10:17.400 slash us slash AI amplifiers. 00:10:18.900 --> 00:10:22.170 Blitzy deeply understands your code base before it writes code. 00:10:22.253 --> 00:10:25.660 Here's the first place that pays off. Security in the age of AI. 00:10:26.140 --> 00:10:29.735 Vulnerabilities don't live in isolation. They live buried inside millions of lines 00:10:29.818 --> 00:10:33.189 of interconnected code, where patching one thing quietly breaks three others. 00:10:33.272 --> 00:10:36.553 That's why surface-level scans fail. Blitzy starts from its Knowledge Graph 00:10:36.636 --> 00:10:40.141 of your entire application, identifies and surfaces CVEs across the full estate, 00:10:40.225 --> 00:10:42.609 proactively recommends patches, and can execute the PR. 00:10:42.692 --> 00:10:46.018 Each fix is grounded in how your systems connect and validate so nothing new 00:10:46.101 --> 00:10:48.350 breaks, and the Knowledge Graph dynamically updates, 00:10:48.433 --> 00:10:51.107 keeping you ahead of an ever-accelerating threat landscape. 00:10:51.190 --> 00:10:55.439 One Blitzy customer resolved 21 active CDEs across 6 core microservices in 4 00:10:55.522 --> 00:10:58.574 days. Zero compile errors, every validation scan clean, 00:10:58.657 --> 00:11:01.450 months of planned work fixed in less than a week. 00:11:01.600 --> 00:11:05.497 Security remediation grounded in real architectural context at the speed 00:11:05.581 --> 00:11:08.096 of compute. Harden your codebase at blitzy.com. 00:11:08.179 --> 00:11:10.418 That's B-L-I-T-Z-Y dot com. Every episode, 00:11:10.501 --> 00:11:14.509 I talk about the competition between OpenAI, Anthropic, SpaceX AI, Google, 00:11:14.593 --> 00:11:18.822 and Meta. And if you've been listening for a while, you might have a favorite. 00:11:18.905 --> 00:11:21.697 Maybe you think OpenAI and Anthropic can stay ahead, 00:11:21.780 --> 00:11:24.600 or perhaps Meta's open source strategy can win out. 00:11:24.790 --> 00:11:28.760 Whatever your view, every AI lab creates a different investment opportunity. 00:11:28.843 --> 00:11:33.187 Harbor Capital Advisors AI Lab Ecosystem ETF Suite lets you invest in the ecosystem 00:11:33.270 --> 00:11:35.030 behind the AI lab you believe in. 00:11:35.260 --> 00:11:38.448 Search Harbor AI Lab ecosystem ETFs wherever you invest or follow at Harbor 00:11:38.531 --> 00:11:41.414 Capital on X to learn more. Visit harborcapital.com for a prospectus 00:11:41.497 --> 00:11:43.856 containing investment objectives, risks, fees, expenses, 00:11:43.939 --> 00:11:47.389 and other important information. Read and consider it carefully before investing. 00:11:47.472 --> 00:11:50.485 Risks include principal loss and artificial intelligence related risks. 00:11:50.569 --> 00:11:53.102 Harbor ETFs are distributed by Foresight Fund Services, LLC. 00:11:53.186 --> 00:11:56.461 Harbor is not affiliated with AI Daily Brief and the funds are not affiliated 00:11:56.544 --> 00:11:58.467 with, sponsored by, or endorsed by any AI lab. 00:11:58.550 --> 00:12:01.433 This is a paid advertisement and not personalized investment advice. 00:12:01.516 --> 00:12:04.616 Investing involves risk, including possible loss of principal. 00:12:05.260 --> 00:12:08.129 This episode of the AI Daily Brief is brought to you by HyperAgent, 00:12:08.212 --> 00:12:11.262 where you run fleets of agents your team can manage together. 00:12:11.380 --> 00:12:15.193 Forget local agents and chat workflows waiting on your laptop to be prompted. 00:12:15.276 --> 00:12:17.672 Hyperagent deploys always-on agents in the cloud, 00:12:17.755 --> 00:12:20.505 doing real work across the tools your team already uses. 00:12:20.589 --> 00:12:23.440 Marketing agents turn competitor moves into landing pages. 00:12:23.523 --> 00:12:26.526 Sales agents enrich leads, draft emails, and updates the CRM. 00:12:26.610 --> 00:12:29.208 Ops agent chases the paperwork and tracks the budget. 00:12:29.291 --> 00:12:33.003 Every agent has access to shared context and follows your rules about scope 00:12:33.086 --> 00:12:36.292 and approvals. It's time you add agents that feel like teammates. 00:12:36.375 --> 00:12:37.640 Hire yours at Hyperagent. 00:12:41.380 --> 00:12:46.412 all right i want to make sure that we understand like who i build the episode 00:12:46.495 --> 00:12:51.727 for and i think it's built for everybody and not just the frontier professionals 00:12:51.810 --> 00:12:56.510 that are building the absolute cutting edge if you're about to build one 00:12:56.593 --> 00:13:01.758 of course pay attention because it will provide you or verify the full playbook 00:13:01.842 --> 00:13:06.160 it's also aimed at people who are not quite there yet because the 00:13:11.380 --> 00:13:14.068 Team agent just makes some of them even more critical. 00:13:14.151 --> 00:13:17.763 And even if you are working solo and you have a team of agents or you're 00:13:17.846 --> 00:13:21.303 contemplating building a team of agents, you have the same decisions. 00:13:21.387 --> 00:13:25.409 The other player in your ecosystems are probably not your peers because you work 00:13:25.492 --> 00:13:29.617 alone, but perhaps you're building it for your customers or you're building it for 00:13:29.700 --> 00:13:33.465 a future you to make sure that it's robust enough and representative enough 00:13:33.549 --> 00:13:37.500 of diverse set of work. So that's the motivation or who should pay attention. 00:13:41.380 --> 00:13:44.339 very clear is that not every agent should be shared. 00:13:44.422 --> 00:13:47.556 There is a dial here or a spectrum with three settings. 00:13:47.639 --> 00:13:52.411 We have a private agent that's yours for your work with your taste and your access. 00:13:52.495 --> 00:13:55.512 For example, my own social media agent stays private. 00:13:55.595 --> 00:14:00.367 I'm probably not going to be able to share it with anybody because I'm the only one 00:14:00.450 --> 00:14:03.701 that wants to share or write in social in a specific way. 00:14:03.785 --> 00:14:07.855 So nobody should ever sound like me. And then we have shared knowledge. 00:14:07.938 --> 00:14:08.771 Those can be 00:14:11.380 --> 00:14:15.762 meaning the team maintains one body of knowledge. For example, what we sell, 00:14:15.845 --> 00:14:19.757 how we work, what our words mean, often with a shared skill library, 00:14:19.840 --> 00:14:22.460 and everybody points their own agents at that. 00:14:22.543 --> 00:14:25.632 But this is where the skill library lives, by the way. 00:14:25.716 --> 00:14:29.686 And it's often the right answer, and it's the easiest place to start. 00:14:29.770 --> 00:14:34.210 Another concrete example, say every salesperson has a prospecting agent tuned 00:14:34.294 --> 00:14:36.854 to their own style and their own preferences. 00:14:36.937 --> 00:14:38.700 Keep those agents as they are, 00:14:41.380 --> 00:14:45.370 voice, but give them all the same well-maintained picture of the ideal 00:14:45.453 --> 00:14:47.872 customer and the messaging for the company. 00:14:47.955 --> 00:14:52.294 So that's a hybrid mode that some companies or some use cases should remain. 00:14:52.378 --> 00:14:56.950 And lastly, we do have the team agents, where we have one agent that many people 00:14:57.033 --> 00:14:59.801 work with that has its own job and its own owner, 00:14:59.884 --> 00:15:04.689 and agents can move along the dial. And if you have a scenario where your colleagues 00:15:04.772 --> 00:15:09.020 keep asking to borrow your private agent, that's probably a sign that you 00:15:11.380 --> 00:15:16.359 to consider sharing it with others. So the next question that I want to answer is, 00:15:16.442 --> 00:15:19.076 are all team agents from the same archetype, 00:15:19.159 --> 00:15:23.521 or do they all follow the same type of use cases? And the answer is not. 00:15:23.604 --> 00:15:28.274 Like across the teams that I work with, I can roughly categorize the existing 00:15:28.358 --> 00:15:32.966 or future built team agents into four kinds. And knowing which your kind is, 00:15:33.050 --> 00:15:37.412 it helps you not only identify use cases, but also refine the use cases. 00:15:37.495 --> 00:15:40.520 And also it can tell you what to pay attention to 00:15:41.380 --> 00:15:46.150 right. So the first type of team agent, I'm calling it the expert agent. 00:15:46.233 --> 00:15:50.194 It's the one person's know-how or one small team's know-how. 00:15:50.278 --> 00:15:52.247 It's available to everyone who 00:15:52.330 --> 00:15:56.506 Depends on it. You'll recognize it by the person who can take the vacation. 00:15:56.589 --> 00:15:59.970 You remember from the beginning, if you want another example, 00:16:00.053 --> 00:16:04.172 it can be the data agent that can answer any data question across multiple 00:16:04.255 --> 00:16:08.545 departments in the company or a pricing and deal desk agent that serves a lot 00:16:08.628 --> 00:16:11.838 of go to market organizations, compliance agent and so on. 00:16:11.922 --> 00:16:16.495 In order to get it right, the knowledge has to come from the experts that holds it 00:16:16.578 --> 00:16:17.430 in the company. 00:16:17.800 --> 00:16:22.618 They need to be interviewed and they need to you need to collect the answers they 00:16:22.701 --> 00:16:27.277 already gave in multiple forums, whether those are direct messaging or emails 00:16:27.360 --> 00:16:32.299 and other places. And they have to be they the experts have to be involved from day 00:16:32.382 --> 00:16:36.656 one, because for them, this is what finally makes the vacation possible. 00:16:36.739 --> 00:16:41.640 But also a lot of job insecurity. So tread carefully when working in this domain. 00:16:47.800 --> 00:16:50.808 similar recurring work with one shared way to do it. 00:16:50.891 --> 00:16:55.682 The way to recognize a use case that falls into this category is when three people 00:16:55.765 --> 00:16:58.773 have each built their own version of the same agent. 00:16:58.856 --> 00:17:02.280 You can think about a team research and meeting prep agent. 00:17:02.364 --> 00:17:05.966 That's a very classical one. Or marketing teams content agent. 00:17:06.049 --> 00:17:10.424 And I'm sure you can think of others. In order to get this archetype right, 00:17:10.507 --> 00:17:15.061 you have to agree on how work is done. And it's easier to say than to actually 00:17:15.144 --> 00:17:15.977 execute 00:17:17.800 --> 00:17:22.096 three versions. And that's really a conversation about what you agree in terms 00:17:22.179 --> 00:17:26.644 of the standard for the company. So an interesting conversation at the very least 00:17:26.727 --> 00:17:29.844 once you start contemplating unifying an agent like that. 00:17:29.927 --> 00:17:34.392 And then we have the bridge agent. That's the work that flows between roles where 00:17:34.475 --> 00:17:39.052 nobody can do it alone. You'll recognize it when the handoffs break and every stage 00:17:39.135 --> 00:17:43.431 has to explain the context or the agents have to somehow work together between 00:17:43.515 --> 00:17:44.348 different 00:17:47.800 --> 00:17:51.705 solution, customer success and delivery. That's a very classical one. 00:17:51.789 --> 00:17:54.653 And to get it right, we have to have each function, 00:17:54.737 --> 00:17:58.295 their own piece of knowledge that is being fed into this agent. 00:17:58.378 --> 00:18:01.937 And people with different access will be eventually using that. 00:18:02.020 --> 00:18:06.619 So we have to also pay attention very, very carefully to permissions and you have 00:18:06.702 --> 00:18:10.434 to work hard through that. And lastly, we have the chief of staff. 00:18:10.518 --> 00:18:13.035 That's the agent that own the team operating, 00:18:13.119 --> 00:18:15.720 like operationalizing of the day-to-day work. 00:18:17.800 --> 00:18:21.907 status onboarding and you will recognize this one when the team keeps repeating 00:18:21.991 --> 00:18:26.363 itself and new joiners take weeks to find their footing and in order to get this one 00:18:26.446 --> 00:18:30.607 right what you need to do you need to clearly define what it is allowed to learn 00:18:30.690 --> 00:18:34.320 how can it learn their processes and the ongoing and how does it do so 00:18:34.403 --> 00:18:38.457 automatically which is not very trivial and then there are also of course many 00:18:38.541 --> 00:18:42.436 questions around permissions and so on so while you're thinking about these 00:18:42.519 --> 00:18:43.580 archetypes and which 00:18:47.800 --> 00:18:52.346 about. And before I give you the playbook on how to actually build these team 00:18:52.430 --> 00:18:56.676 agents, a quick detour, because I do want to give a quick reality check. 00:18:56.759 --> 00:19:01.606 There are some signs that a team agent is the wrong move or at least not the right 00:19:01.689 --> 00:19:05.935 move for you at this moment. So one indication where you shouldn't build 00:19:06.019 --> 00:19:09.423 a team agent, at least yet, is when taste beats standards. 00:19:09.506 --> 00:19:13.932 If different people truly need different answers or not willing to agree on 00:19:14.015 --> 00:19:16.180 a standard and their own judgment or 00:19:17.800 --> 00:19:22.448 those need to remain private agents so people can remain authentic and not have 00:19:22.531 --> 00:19:27.299 to fight about the ground truth. And the second indication not to build is nobody 00:19:27.382 --> 00:19:28.700 can own the knowledge. 00:19:29.080 --> 00:19:33.371 If the team cannot agree on how the work is done or nobody is willing to own 00:19:33.455 --> 00:19:35.904 and maintain the shared knowledge over time, 00:19:35.987 --> 00:19:39.185 the agent will drift within weeks, sometimes within days. 00:19:39.268 --> 00:19:42.927 So sort out the ownership before you go and build the team agent, 00:19:43.010 --> 00:19:45.632 because that's going to be a no go. And lastly, 00:19:45.715 --> 00:19:49.201 whenever you're realizing that trying to build a shared agent, 00:19:49.284 --> 00:19:53.921 a team agent only complicates more than it simplifies because you have conflicting 00:19:54.004 --> 00:19:56.940 needs or tangled permissions, endless coordination. 00:19:59.080 --> 00:20:02.100 work than what the agent can provide for you, 00:20:02.270 --> 00:20:06.325 That's the answer. Don't build it, at least not until you are able to untangle 00:20:06.408 --> 00:20:10.410 some of the complexities. And of course, notice what's missing from the list, 00:20:10.493 --> 00:20:14.707 sensitive data and high stakes. Those are design questions and they shape how you 00:20:14.791 --> 00:20:16.936 build it, which is where we're going next. 00:20:17.019 --> 00:20:20.755 So I don't think that when data is overly sensitive is a reason against. 00:20:20.839 --> 00:20:23.673 It's just something that needs extra careful attention. 00:20:23.757 --> 00:20:27.652 In order to build the candidate use case that hopefully you've gone through 00:20:27.736 --> 00:20:30.070 the decision checklist that I shared before, 00:20:32.270 --> 00:20:36.336 design decisions for your agent. It goes to what it does, where it lives, 00:20:36.420 --> 00:20:39.576 what it knows, what it can touch, and how can you run it. 00:20:39.660 --> 00:20:43.214 These are the core questions. In order to make it more concrete, 00:20:43.298 --> 00:20:45.886 I'll use one example, the whole way throughout. 00:20:45.969 --> 00:20:50.149 So it's going to be a customer agent, and it's going to be the bridge kind, 00:20:50.233 --> 00:20:54.185 meaning one that holds everything the company knows about each customer 00:20:54.269 --> 00:20:58.676 and everything we've promised them. And it's probably going to be used by sales 00:20:58.759 --> 00:20:59.593 and 00:21:02.270 --> 00:21:07.300 on. they will be using that example agent to do various customer-related activities. 00:21:07.520 --> 00:21:11.266 So let's break down some of these decisions to make it actionable. 00:21:11.349 --> 00:21:14.804 So first, the decision that you have to make is what it does. 00:21:14.888 --> 00:21:19.155 A quick caveat here, there is a lot of scoping that is very similar for any 00:21:19.239 --> 00:21:23.796 serious agent at work. It needs to have a clear job and a definition of done and 00:21:23.880 --> 00:21:25.620 a list of what it does and do. 00:21:25.730 --> 00:21:30.269 I'm going to stick here to what changes when it's built for a team versus an agent 00:21:30.352 --> 00:21:34.835 that you build just for yourself. So the first decision is who it serves by role. 00:21:34.918 --> 00:21:38.386 For example, sales asks it different things than delivery does. 00:21:38.469 --> 00:21:42.614 So write down each role and what they'll come to the agent for to make sure 00:21:42.697 --> 00:21:44.670 that you're covering all the scope. 00:21:44.780 --> 00:21:49.119 And of course, you can aim for one broad area of work because I think the team 00:21:49.203 --> 00:21:51.897 agents should be quite capable agents. Otherwise, 00:21:51.981 --> 00:21:55.016 it's harder to justify their existence. In our example, 00:21:55.099 --> 00:21:59.495 I would expect that the customer agent will be able to prepare meeting answers. 00:21:59.579 --> 00:22:04.031 Where do we stand with this customer? We'll be able to flag promises that commit 00:22:04.114 --> 00:22:08.397 other teams and draft every handoff. For example, I have quite a broad scope. 00:22:08.480 --> 00:22:11.005 And what keeps it focused is the area of work. 00:22:11.089 --> 00:22:13.640 And that is primarily in our case, customers. 00:22:14.780 --> 00:22:17.690 Also to pay attention to the team don'ts list. 00:22:17.774 --> 00:22:21.335 This is the part people often tend to skip. For example, 00:22:21.418 --> 00:22:26.411 it never makes commitment on someone's behalf or it never settles disagreement 00:22:26.494 --> 00:22:31.617 between people. Those go to its owner. You can think of another such examples in 00:22:31.701 --> 00:22:36.498 your case. Also make sure that the don't list includes permissions and data 00:22:36.582 --> 00:22:41.965 handling stuff. So, for example, it never carries information from one private space 00:22:42.049 --> 00:22:43.220 into a shared one. 00:22:44.780 --> 00:22:49.534 customer in another customer space. And it doesn't speak for one person to another. 00:22:49.617 --> 00:22:53.613 And of course, like with any agent, ideally start with narrower scope, 00:22:53.696 --> 00:22:58.525 reading and drafting. Only when it earns sufficient trust and was validated enough, 00:22:58.609 --> 00:23:02.087 then you can increase the scope as you gain more and more confidence. 00:23:02.170 --> 00:23:05.235 So that's the first decision and we can move to the next one. 00:23:05.318 --> 00:23:07.816 The second question will be where the agent lives. 00:23:07.899 --> 00:23:12.080 And this is the question that gets asked most. So let's be a little bit concrete. 00:23:12.470 --> 00:23:15.854 Basically, if I'm trying to make it as simple as possible, 00:23:15.937 --> 00:23:20.398 there are roughly three ways to share an agent from the simplest to the most 00:23:20.481 --> 00:23:25.121 involved. The simplest method will just to create a shared folder with your own 00:23:25.204 --> 00:23:28.289 tools, like the tools that your company already owns. 00:23:28.372 --> 00:23:33.132 And then each person just point their own tool to the shared agent and the folder 00:23:33.215 --> 00:23:37.795 will include instructions and potentially how to store new information as part 00:23:37.878 --> 00:23:40.090 of the way the agent overall behaves. 00:23:42.470 --> 00:23:46.320 But as a stepping stone to building shared agents and team level agents, 00:23:46.404 --> 00:23:50.745 that can be a very good start, especially if all of your team members are already 00:23:50.829 --> 00:23:55.171 using similar agentic tools or agentic tools that can point to folders as sources 00:23:55.254 --> 00:23:58.612 for their information. So that's the first and simplest method. 00:23:58.696 --> 00:24:02.437 The second way that we can do that is using a vendor ready-made agent. 00:24:02.520 --> 00:24:04.841 And we're increasingly seeing more and more. 00:24:04.924 --> 00:24:09.102 And we believe that we will continuously see more and more in the coming weeks 00:24:09.185 --> 00:24:12.190 and months of the year. We'll talk more about it later. 00:24:12.470 --> 00:24:16.675 But the way this works is that the vendor hosts it and you configure it. 00:24:16.758 --> 00:24:20.367 And in this category, we have many very recently famous tools, 00:24:20.450 --> 00:24:24.000 including CloudTag. OpenAI has their ChatGPT workspace agent. 00:24:24.083 --> 00:24:27.871 Copilot has their own offering that can be used like that notion. 00:24:27.954 --> 00:24:32.337 And many others are already offering shared spaces with agents that you can 00:24:32.421 --> 00:24:36.864 work together on. And it's just a matter of you configuring their specifics. 00:24:36.947 --> 00:24:41.509 And lastly, and that's, of course, the most sophisticated is an agent that you 00:24:41.592 --> 00:24:45.926 host, That's something that you run. It can be, for example, 00:24:46.009 --> 00:24:50.973 an open source agent like OpenClaw or Hermes on your own servers or on a list 00:24:51.056 --> 00:24:56.347 cloud. Or some companies are even building their own custom harnesses specifically 00:24:56.431 --> 00:24:59.625 for these needs. So that's the most sophisticated, 00:24:59.708 --> 00:25:04.934 but obviously has the most technically demanding requirements as well as the most 00:25:05.017 --> 00:25:10.177 freedom to build around that. So that's the three broad strokes options of where 00:25:10.260 --> 00:25:15.651 these team agents can live. On top of the decisions of how to build or the tools, 00:25:15.734 --> 00:25:19.370 there are two additional questions that come with them. 00:25:19.730 --> 00:25:24.072 The first question is who can see each person's conversation with the agent. 00:25:24.155 --> 00:25:27.624 Maybe it's only the people who are conversing with the agent. 00:25:27.708 --> 00:25:31.584 Maybe it's the entire channel or everyone in the session. Over here, 00:25:31.667 --> 00:25:35.835 there is a lot of differences between the different tools. In some tools, 00:25:35.918 --> 00:25:39.503 everybody can read every chat. For example, in Claude in Slack, 00:25:39.586 --> 00:25:43.987 everyone in the channel sees what the agent does and what the agent converses 00:25:44.070 --> 00:25:46.050 with others and can also steer it. 00:25:49.730 --> 00:25:51.992 sometimes a design decision by the vendor. 00:25:52.075 --> 00:25:54.672 Sometimes it's something that you can configure. 00:25:54.756 --> 00:25:58.525 And the second question is what it learns stored and who can read it. 00:25:58.609 --> 00:26:01.541 So an ideal agent is not one that is obviously frozen, 00:26:01.624 --> 00:26:04.668 but one that has a lot of memory and learning on the go. 00:26:04.751 --> 00:26:08.800 And then the question, where is this learning being stored and how does it 00:26:08.883 --> 00:26:11.480 happen? Is it something that happens per person? 00:26:11.564 --> 00:26:14.942 And then the agent evolves just from its interaction with you? 00:26:15.026 --> 00:26:16.310 Or is it per channel or 00:26:19.730 --> 00:26:23.718 and the agent evolves with everybody in public. And of course, 00:26:23.802 --> 00:26:28.972 one thing never costs customers. So do check and choose and tell the team before 00:26:29.056 --> 00:26:33.832 the first real task, what's the status with the team agent that you built? 00:26:33.915 --> 00:26:37.790 Because this is where a lot of trust can be gained or lost. 00:26:38.150 --> 00:26:42.406 And my rule is to pick the simplest option that two people will actually use 00:26:42.489 --> 00:26:46.574 this week. And for our customer agent, that's probably a channel agent or 00:26:46.658 --> 00:26:49.886 a simple like a tool agent because four functions need it. 00:26:49.969 --> 00:26:54.397 And if I will make it overly complicated and people will need to understand how 00:26:54.480 --> 00:26:58.336 to connect to that versus just going into a Slack or a Teams channel, 00:26:58.420 --> 00:27:02.733 it's not going to work. So in our case, that's probably going to be the right 00:27:02.816 --> 00:27:07.392 solution. this decision, I want to move arguably to the most important decision. 00:27:07.476 --> 00:27:11.000 And that's what it knows. And I think if you've built any agent, 00:27:11.083 --> 00:27:15.058 the recipe will sound very familiar. What's different for a team is that 00:27:15.142 --> 00:27:18.159 this is the moment the team agrees on the ground truth. 00:27:18.242 --> 00:27:21.428 How the work actually gets done, which definitions we use, 00:27:21.511 --> 00:27:24.415 which versions of the pricing policy is the real one. 00:27:24.499 --> 00:27:27.290 And I think that that conversation is worth having, 00:27:27.373 --> 00:27:30.530 even if you never ship the agent, because in most teams, 00:27:33.530 --> 00:27:38.074 And it's also where team agents get harder because the moment knowledge is shared, 00:27:38.158 --> 00:27:42.081 then you have more contributors and more contradictions and more places 00:27:42.165 --> 00:27:46.371 for something important to fall through. So the process around the knowledge 00:27:46.454 --> 00:27:49.587 matters even more than it ever did in your private agent. 00:27:49.671 --> 00:27:52.691 So you need to pay careful attention here. And ideally, 00:27:52.775 --> 00:27:54.750 you should go to these four stages. 00:28:03.530 --> 00:28:08.176 where information already resides. And I want AI do a lot of the heavy lifting 00:28:08.260 --> 00:28:11.097 in terms of aggregating and collecting the data. 00:28:11.180 --> 00:28:14.955 So for our customer agents, what I would do is I'll make sure that sales 00:28:15.039 --> 00:28:19.380 and solutions and success and delivery, they all will contribute their own piece. 00:28:19.760 --> 00:28:23.874 And then I want you to refine. I want you to merge the information coming 00:28:23.957 --> 00:28:26.806 from different sources, surface the contradictions. 00:28:26.889 --> 00:28:31.348 I'm sure that you will find five versions of the truth and then date everything 00:28:31.431 --> 00:28:35.775 and keep out what should never be shared. Of course, that includes passwords, 00:28:35.859 --> 00:28:39.857 notes about people, one customer's details in another customer's space, 00:28:39.941 --> 00:28:42.272 and so on. And then we have to approve it. 00:28:42.355 --> 00:28:45.204 Each piece should be signed off by whoever owns it. 00:28:45.288 --> 00:28:47.760 And the agent's owner puts it all together. 00:28:49.760 --> 00:28:52.412 goes tail very quickly, so you have to maintain. 00:28:52.495 --> 00:28:56.970 You need to decide what the agent may add to its own memory based on its working 00:28:57.053 --> 00:29:01.414 experience and what person has to review first when it goes into the knowledge 00:29:01.497 --> 00:29:05.915 and the memory. And we want to make sure that one person's definition of what's 00:29:05.998 --> 00:29:09.360 last year quietly becomes everyone's without any agreement. 00:29:09.890 --> 00:29:14.150 And of course, put the upkeep on a schedule because you want the agent 00:29:14.233 --> 00:29:19.237 to propose updates regularly and a person needs to review and approve the updates. 00:29:19.320 --> 00:29:24.263 And this is really the place to be very, very diligent and disciplined because it 00:29:24.346 --> 00:29:28.916 can totally make or break your team agent if you haven't done a good enough 00:29:28.999 --> 00:29:33.507 and self-sustaining process around acquiring and maintaining and verifying 00:29:33.590 --> 00:29:36.010 the knowledge that the agent taps into. 00:29:39.890 --> 00:29:42.300 very quickly fix anything that goes wrong. 00:29:42.383 --> 00:29:46.753 It can create a lot of havoc in your company if your team agent is not well 00:29:46.836 --> 00:29:51.146 educated enough on what matters. The fourth decision is what it can touch. 00:29:51.229 --> 00:29:55.954 And this is where team agents differ from the private ones because your own agent 00:29:56.038 --> 00:29:59.917 acts as you. and a team agent acts for many people. 00:30:00.000 --> 00:30:04.420 Of course, there are many security 101 that you need to apply here. 00:30:04.590 --> 00:30:09.443 Those that apply to any agent definitely stick for the four rules that are specific 00:30:09.526 --> 00:30:13.785 to, like, I'm going to just stick to the rules that apply to team agents. 00:30:13.868 --> 00:30:17.591 The first thing that you have to decide is whose access it uses. 00:30:17.675 --> 00:30:22.468 And you have three options. You can use the access or to act as whoever is asking. 00:30:22.552 --> 00:30:26.572 So it only sees what the person that was asking the question can see. 00:30:26.656 --> 00:30:31.568 And that's probably the safest choice, but sometimes the most complicated to execute 00:30:31.651 --> 00:30:34.090 unless the vendor already did it for you. 00:30:34.590 --> 00:30:39.105 Probably the right one when people on the team have different access levels. 00:30:39.188 --> 00:30:43.764 The other option that you have is to have its own account set up with exactly 00:30:43.847 --> 00:30:48.605 the access the job needs. And that's right when the whole team works on the same 00:30:48.688 --> 00:30:52.175 shared material. And lastly, it can use one person's login. 00:30:52.258 --> 00:30:56.712 Only ever do that for read-only and non-sensitive material because everyone 00:30:56.796 --> 00:31:00.403 who talks to the agent effectively gets that person's access. 00:31:00.487 --> 00:31:03.270 So I would not recommend to go down that path. 00:31:04.590 --> 00:31:08.759 probably do for our customer agent is to act as the person asking because sales 00:31:08.842 --> 00:31:12.742 success and delivery see different things in the CRM and in other systems. 00:31:12.825 --> 00:31:16.510 So I don't want to have the agents responding to them with information 00:31:16.593 --> 00:31:20.816 that they shouldn't be able to see. So that was the first rule on what the agent 00:31:20.899 --> 00:31:24.140 can see. The second rule is to decide who can ask it. 00:31:24.330 --> 00:31:28.650 And when the agent has its own account, everyone who can talk to it can use 00:31:28.733 --> 00:31:33.464 the account. And if you put an agent with access to the pricing sheet in a channel 00:31:33.547 --> 00:31:37.280 of 40 people, a few contractors among them, then all of a sudden, 00:31:37.363 --> 00:31:39.770 all 40 can now get the pricing by asking. 00:31:40.170 --> 00:31:43.171 The agent knows more than some of the people who can reach it. 00:31:43.254 --> 00:31:46.104 So decide who can talk to it with the same care you give. 00:31:46.260 --> 00:31:50.679 to what it can see. Okay, so that's something that happens very regularly when 00:31:50.763 --> 00:31:55.124 people don't pay attention. I also want you to decide where the answer lands. 00:31:55.208 --> 00:31:58.992 This one runs the other way. The agent uses the asker's own access, 00:31:59.075 --> 00:32:01.878 and the asker has every right to ask the question. 00:32:01.962 --> 00:32:06.496 The problem is that the answer shows up in a shared space in front of people who 00:32:06.580 --> 00:32:09.729 don't. So this is something that is happening right now. 00:32:09.812 --> 00:32:13.680 If you will look at the documentation of Claudine Slack, it can use 00:32:16.260 --> 00:32:21.595 and after the person approves and the anthropic documentation currently notes 00:32:21.679 --> 00:32:24.736 that it doesn't consider who else is in the channel. 00:32:24.820 --> 00:32:28.973 So if I approve to use my connectors and fetch all the information that I am 00:32:29.056 --> 00:32:33.599 permitted to see, and now the information is thrown at the channel where others can 00:32:33.682 --> 00:32:37.947 see that, that's the reality currently with the existing cloud implementation. 00:32:38.030 --> 00:32:42.406 So if it's sensitive, the answer has to go to the person who is asking privately 00:32:42.489 --> 00:32:46.586 and not in a shared channel. And lastly, keep record of who asked for what. 00:32:46.669 --> 00:32:51.240 And that's an important logging because when an agent works under its own account, 00:32:52.200 --> 00:32:56.288 agent did it, right? And you want to know which person asked so you can backtrack 00:32:56.371 --> 00:33:00.098 and make sure that there are no unexpected behaviors. And everything else, 00:33:00.181 --> 00:33:03.754 like starting with the list access and having a person approve anything 00:33:03.837 --> 00:33:06.174 that can't be undone is the same for any agent. 00:33:06.257 --> 00:33:08.407 So I'm not giving you security one-on-one. 00:33:08.490 --> 00:33:13.313 Okay, lastly, last decision and the one that will make your team agent live beyond 00:33:13.396 --> 00:33:15.430 its first week or the first month. 00:33:15.720 --> 00:33:18.562 That's the full operating manual here. Of course, 00:33:18.645 --> 00:33:23.218 the multiplayer sprint has a much more comprehensive way of thinking about it, 00:33:23.301 --> 00:33:27.533 but These four points are what makes or break the agency in practice. 00:33:27.617 --> 00:33:31.905 So the first thing is one owner. Anyone on the team can handle the work, 00:33:31.988 --> 00:33:33.810 but I want to have one person. 00:33:33.990 --> 00:33:37.192 or a very small group of people who owns the priorities, 00:33:37.275 --> 00:33:41.298 maintain the agent and decide when two people ask for opposite things, 00:33:41.382 --> 00:33:44.173 how to evolve the agent knowledge or feature set. 00:33:44.256 --> 00:33:48.455 They also decide on standing instructions and so on. So that's one thing. 00:33:48.539 --> 00:33:52.738 The second thing that I want to mention is the clear rules of engagement. 00:33:52.821 --> 00:33:55.436 I want you to tell people how to work with it, 00:33:55.520 --> 00:33:58.252 what it does and doesn't do and what it can see, 00:33:58.336 --> 00:34:02.970 who can see their conversation with it and everything that we discussed so far. 00:34:03.990 --> 00:34:08.359 We want to have clear indications of how to correct the agent when it's wrong. 00:34:08.442 --> 00:34:12.926 And I think that people trust the agents that they're using and the team agents, 00:34:13.009 --> 00:34:16.921 the more they know what it's learning and what's the learning process. 00:34:17.005 --> 00:34:21.145 The next thing I want you to do is to put decisions where it can see them. 00:34:21.229 --> 00:34:25.230 So a team agent only knows. what's written down in a place that it can reach. 00:34:25.314 --> 00:34:29.232 And if your team decides things in private messages and hallway conversations, 00:34:29.315 --> 00:34:33.060 the agent will never hear about them. And part of running it smoothly is, 00:34:33.300 --> 00:34:37.587 is to have it be able to tap into what's happening in real time in the team and 00:34:37.671 --> 00:34:41.958 to make sure that the team decisions and the team ongoing day to days are being 00:34:42.042 --> 00:34:46.661 learned by the agent itself. And lastly, I want you to keep watching because you will 00:34:46.744 --> 00:34:51.032 probably start with a small, ideally, you should start with a small pilot group 00:34:51.115 --> 00:34:55.320 and keep a few test questions that you can rerun whenever something changes. 00:34:55.680 --> 00:34:59.880 But I also want you to just monitor because we know that things change very 00:34:59.964 --> 00:35:04.449 frequently. So it's not just about having a proper process for whenever you want 00:35:04.533 --> 00:35:08.333 to introduce a new model or a new tool or a new knowledge or changes 00:35:08.416 --> 00:35:12.788 in instructions, but also just to monitor that everything is working properly. 00:35:12.871 --> 00:35:17.357 And of course, in some cases, we would want to retire the team agent if it's not 00:35:17.440 --> 00:35:20.841 behaving properly as we expected. We covered a lot of ground. 00:35:20.924 --> 00:35:23.780 And if I need to pull it together before we close. 00:35:25.680 --> 00:35:29.978 you that team agents matter for everyone, even if it will take you a while until you 00:35:30.062 --> 00:35:33.943 will actually be building one, and that building them properly is what makes 00:35:34.026 --> 00:35:37.073 the difference. Of course, not every agent should be shared. 00:35:37.156 --> 00:35:41.037 A private agent or shared knowledge and skills with private agents or a team 00:35:41.120 --> 00:35:44.793 agent, these are all valid options and should be used where appropriate. 00:35:44.876 --> 00:35:48.705 We talked about the team agents that are coming in four kinds, the experts, 00:35:48.788 --> 00:35:51.240 the common work agent, the bridge and the chief 00:35:55.680 --> 00:35:57.480 a lot about how to get it right. 00:35:57.600 --> 00:36:00.603 And we also talked about three signs on when to wait, 00:36:00.686 --> 00:36:03.340 whether it's because taste beats the standards, 00:36:03.423 --> 00:36:07.533 whether because nobody can own the knowledge or when it doesn't simplify 00:36:07.616 --> 00:36:11.958 the work. And once you're building, we went over the five decisions in order 00:36:12.042 --> 00:36:14.695 of what it does, where it lives, what it knows, 00:36:14.779 --> 00:36:18.888 what it can touch and how do you run it. And if you take those with you, 00:36:18.971 --> 00:36:22.640 you have what you need in order to get the team agent properly. 00:36:27.600 --> 00:36:30.336 First of all, we have the multiplayer AI sprint, 00:36:30.419 --> 00:36:34.623 which is free and will walk you through a team activity of in four weeks, 00:36:34.707 --> 00:36:38.911 configuring everything that we discussed, some of them in greater detail. 00:36:38.994 --> 00:36:43.727 If you want to learn how to properly build seriously team agents and agent rosters 00:36:43.810 --> 00:36:46.311 and how to do that in the best possible way, 00:36:46.395 --> 00:36:50.951 we have another cohort of the executive agent leadership that starts on October 00:36:51.035 --> 00:36:54.500 5th and we'll be happy to see you with all of our builders. 00:36:57.600 --> 00:37:01.698 you go and build agents for teams and rosters of agents and so on, 00:37:01.781 --> 00:37:06.702 we also have the executive catch-up that helps you become best-in-class AI user 00:37:06.785 --> 00:37:11.980 before you go and build those agents. And lastly, everything is changing. Odds are 00:37:12.210 --> 00:37:14.837 that every week we will get a relevant release. 00:37:14.920 --> 00:37:18.757 And by the time you hear this, maybe already something was released. 00:37:18.841 --> 00:37:23.197 But I do think that everything that we cover today holds no matter what chips 00:37:23.280 --> 00:37:27.804 next, because When an agent is built properly and the decisions are made right, 00:37:27.887 --> 00:37:30.519 it's orthogonal to any specific tool or feature. 00:37:30.603 --> 00:37:34.932 It's the business decision and the team standardization that matters much more 00:37:35.015 --> 00:37:39.458 than the tools that will help make it better by design the more releases we will 00:37:39.541 --> 00:37:43.418 have. And if I need to make some predictions for the rest of the year, 00:37:43.501 --> 00:37:47.970 so I think that we will see more and more formalization of what we just covered 00:37:54.210 --> 00:37:58.490 permissions, ownership, and so on, as well as like we can always trust 00:37:58.573 --> 00:38:03.352 the practitioners to share many of their learnings in the public eye so we can 00:38:03.436 --> 00:38:08.526 learn from many of the other AI and like frontier individuals and companies and see 00:38:08.609 --> 00:38:10.230 how it's working for them. 00:38:10.470 --> 00:38:14.682 That's it. Awesome. Great stuff, Nufar. I have a few things that I want to lob out 00:38:14.765 --> 00:38:17.824 there, discussion style, just as we close out. First of all, 00:38:17.908 --> 00:38:21.752 I guess the question, you know, you gave four archetypes of different types 00:38:21.836 --> 00:38:23.250 of agents that you've seen. 00:38:23.400 --> 00:38:27.985 Do you see, are any of them more common starting places than others for teams 00:38:28.068 --> 00:38:30.713 that you've observed? I think that in theory, 00:38:30.796 --> 00:38:35.260 your definition of an agent that lives between individuals or between teams 00:38:35.343 --> 00:38:38.897 sounds the most attractive, but it's the hardest to execute. 00:38:38.980 --> 00:38:43.019 So I think that's actually the ones that will, from what I'm seeing, 00:38:43.103 --> 00:38:46.111 are not the first to go for. And I've seen various, 00:38:46.195 --> 00:38:51.204 very successful versions of the first one of the expert agents that help create more 00:38:51.287 --> 00:38:52.560 redundancy in a team. 00:38:53.400 --> 00:38:57.479 sense and relieve some of the burden on those bottlenecks within the company. 00:38:57.563 --> 00:39:00.290 So those have seen a ton of implementations already. 00:39:00.374 --> 00:39:03.264 And I think the more the tools make it more accessible, 00:39:03.347 --> 00:39:07.318 the easier those will be to build. So those are probably the lowest hanging 00:39:07.402 --> 00:39:11.140 fruits. That's funny because that's exactly where my head goes. 00:39:11.223 --> 00:39:15.090 I'm super attracted to the ones that I think are most difficult to build. 00:39:15.180 --> 00:39:19.806 I've also seen a lot of, you know, very simple implementation of that expert one, 00:39:19.890 --> 00:39:20.797 which, you know, 00:39:20.880 --> 00:39:26.045 we talked about for a long time without even identifying it as this sort of team 00:39:26.128 --> 00:39:31.147 agent is just basically the agentified team internal knowledge hub, you know. 00:39:31.230 --> 00:39:35.208 policies around whatever, like early dismissal, who knows? You know, 00:39:35.291 --> 00:39:39.568 that just the company database of information that you can access through 00:39:39.651 --> 00:39:44.525 the chatbot instead. That's been something that companies have had a ton of success 00:39:44.608 --> 00:39:48.586 with as just an early, easy, fast use case right from the beginning. 00:39:48.669 --> 00:39:51.811 Another question that I have for you is how, you know, 00:39:51.894 --> 00:39:56.409 I'm sure that a lot of folks are sitting there wondering how much they should 00:39:56.493 --> 00:39:59.927 invest in. in building these sorts of things. 00:40:00.010 --> 00:40:06.162 for GrokBot or Microsoft Copilot or one of these sort of core tools that they might 00:40:06.245 --> 00:40:09.257 be using, OpenAI, Anthropic, just drop 00:40:09.340 --> 00:40:12.377 the sort of native version of this. And there's clearly some indications 00:40:12.460 --> 00:40:16.017 that they're thinking in this way. I think Claude Tag being the best example so far, 00:40:16.100 --> 00:40:16.457 but... 00:40:16.540 --> 00:40:21.126 You know, is this one where the value of digging in at this stage is going to be so 00:40:21.209 --> 00:40:25.683 you understand the theory and the ways to customize when better tools come around 00:40:25.766 --> 00:40:28.860 in the future? Or how do you think about that tradeoff? 00:40:29.110 --> 00:40:33.483 I think the heavy lifting is always going to be the configuration and the knowledge 00:40:33.567 --> 00:40:39.329 curation. I would select the one tool that is adjacent the most to your existing tool 00:40:39.412 --> 00:40:40.187 ecosystem, 00:40:40.270 --> 00:40:45.859 and figure out how to implement all the rest and if like new better improved 00:40:45.942 --> 00:40:50.745 tools, come to play will be ready because you already agree on the ground truth, 00:40:50.828 --> 00:40:54.046 on the do's and don'ts of these agents, on the use cases. 00:40:54.129 --> 00:40:57.058 So even if you at first implement them very naively, 00:40:57.141 --> 00:40:59.400 that's going to have your future ready. 00:40:59.830 --> 00:41:04.395 As for going and building these on like a competing product or your own like team 00:41:04.478 --> 00:41:05.970 level harnesses and so on. 00:41:06.250 --> 00:41:10.897 If you have the chops and you can do that easily and you have the justification, 00:41:10.981 --> 00:41:15.155 you can. But I'm not sure that I would have spent my energy now on going 00:41:15.238 --> 00:41:19.058 and building my own version of Claude Tag or similar when we were, 00:41:19.141 --> 00:41:22.577 I think both of us agreed that all of these are coming and, 00:41:22.660 --> 00:41:25.491 will probably be made very accessible and very smart. 00:41:25.574 --> 00:41:29.724 And your moat is probably in everything that these companies cannot tap into. 00:41:29.807 --> 00:41:33.847 Awesome. Well, thanks as always for another great Operators Cut and excited 00:41:33.931 --> 00:41:36.020 to have you back soon. Thank you. Bye.