Construire avec Claude Managed Agents et les coéquipiers IA d’Asana

Hi everyone, I'm Ara from Asana and I'm here to talk to you about how we've built Asana's AI teammates on cloud managed agents. Our vision at Asana is to bring forward this promise of the agentic enterprise where human beings and AI agents can work together to get complex multi-step work done whether you're in IT or operations or product or marketing. Our vision is the AI agent is an actor in the system. It's got a deep set of skills. It's got all of the context required and it can work handinhand with other human beings to get multi-step work done. Things like approvals, complete end to-end workflows, getting to real world outcomes. So that's what we've been building and AI uh teammates within ASA are generally available as of March. What we see today though in the enterprise is almost everybody is experimenting with AI agents. They're building AI agents. There's a lot of like utilization of them. But most most companies are still using AI agents in the single player way where an individual can go ahead and interact with the agent, get an outcome, and then they pass it on to someone else to complete those multi-step processes. You don't end up with compounding knowledge. You don't end up with this concept of a a shared enterprise memory. Uh you don't end up with concepts like uh true multiplayer, multiple human in the loop interactions. And uh throughout this presentation, I'll showcase like what have we done that sort of set this up and how does claude's managed agents capability help us complete these complex multi-step uh multi-step workflows. So our vision is like full multiplayer mode. You have agents that are real actors in the system. They've got sharing and arbback controls just like you would be onboarding a new teammate, a new human teammate into the system. They have the context. Uh they can work with multiple people. they can get nudges and interactions with multiple people and they can complete uh complete these end-to-end jobs to be done. In fact, like one funny anecdote is I was just chatting with Hannah before I got on stage and there are a bunch of like former Asanas who are now at Anthropic and one of them had built an AI uh teammate for us uh that's a competitive intelligence researcher and so now even though they're no longer an asana uh we still use it on a day-to-day basis and all of the historical interactions that he had to set up the context and the knowledge when you know we were doing competitive responses to RFPs is ingrained in that agent and it's just getting better and better as more people join the team and keep using it. So that con that concept of uh enterprise memory uh and then the shared ability of the ability for multiple people to use agents has been phenomenal for us internally in our use. The the other concept that we've been working on and you know again is available is this ability to ensure that the agent gets complete context about how your enterprise works. Who does what by when and why, historical decisions, approvals, ways in which people have had back and forths on a particular campaign brief or a project plan that have finally led to its approval. Those decisions are tracked inside Asana and we provide those to the teammate in a way again that preserves security guard rails auditability so you can get real world results in action. So Asana is the system of action for work and it's that sort of binding layer where once you start introducing agents you can treat them like human beings in your team. You know, like we've have a workcraftraft that we've been building for over 17 years. And it's this idea that every company has a mission and vision that is tracked by goals. Goals are in portfolios. Portfolios are delivered by a multitude of projects. Each project has a set of tasks. And those tasks could have approvals, workflows, and other things embedded in them. And as you build out this context graph that is uh designed for both human beings and AI agents, human beings have a easy to comprehend way a UI to interact with like how your work gets done. And then agents have a way to represent themselves and get that uh get that context they need to get work done and perform in a true multiplayer way across multiple human beings following the right security and guardrails required by your enterprise. So we've been building all of this out for context shared memory and ensuring agents are real actors in the system. The place where we leverage Claude's managed agents capability is to complete those multi-step actions in a way where where anthropics tooling is allowing us to go complete the task. So, in the demo that I'll showcase, what you'll see is a multi-step interaction between a marketer who's releasing uh a new campaign as well as m multiple people on their team. And that campaign requires them to not only write a brief, but also start producing a few mock-ups for what that landing page is going to look like so that the human beings on the team can get to a shared understanding of whether that's good to go or not. So it involves creating you know a complex document using the right set of enterprise context uh required to produce it as well as in uh creating multiple iterations of what that landing page the public website should look like. So it's like generating HTML. It's a multi it's a multi-step action. So with the managed agents capability there's a few different things that uh we use to make AI teammates far more powerful. So it helped us reduce our prototyping costs like we got much faster prototyping for these actions and skills. Uh it comes builtin with a verification loop so we know that the quality of the content we'll get at at the end of the process is high. And then it has this built-in grader where once Asana passes in the outcome it wants to uh cloud managed agents you know we know that the grader will go ahead and iterate through that outcome multiple times to ensure that we're getting a high quality output. So again, this is allowing us to focus on the things that is unique to Asana, the human interface layer to go ahead and coordinate across multiple people, the system of context that we're building out, the security that we're building out so that if you're using the same agent as me or Nigel or Tony, and we are, you know, we are in different work graph objects or different projects, the agent won't leak information across the other. So we focus on that. And the quality of the output is something we're leveraging cloud managed agents for. So again like if I compare and contrast the way in which AI teammates is working today with cloud managed agents versus the messages API that we were previously using. Uh we're getting again faster prototyping because we're not having to build a ma manual agent loop file management code execution. Uh the verification process has gotten way better with this uh with this sort of built-in product. And then we can also enable multiple agents in parallel to work independently because a lot of these like knowledge worker actions like require multiple agents to work in parallel to produce a full plan and to iterate through it. So uh again like as of today there are over 21 pre-built agents uh called AI teammates within ASA. uh we designed the pre-built ones to match our ideal customer profiles across the uh office of the PMO uh within marketing within IT within HR within R&D and they can do things like they can help you with launch planning they can help you with uh you know writing specs they can help you with goal management they can help you with resource management and capacity planning and so they're using all of these existing constructs within ASA for uh you know tracking portfolio goals for tracking Tamline updates and they're taking real action within them as well as in downstream systems. So they can pull in data from Google Drive and Office 365 and we're adding a whole bunch more uh integrations over the coming weeks and they can take action within them as well. they can produce slides, they can add comments, uh they can create full HTML and a lot of those like capabilities are possible because we've invested in managed agents and it it sort of allowed us to run that verification loop and and multi-step uh multi-step workflow. Um so like another example I'll give you is uh we've been obviously dog fooding this internally asana for months now and uh over over those months I have an agent for the product management team which is me and my directs and it's like it's the product or thought buddy and it's got all of the context around you know why we made certain trade-off decisions what the strategy is and things like that and so uh when our marketing team for example has questions about hey we are planning work innovation Summit London, which is our next event that's coming up. Here is a draft of the keynote speech. Uh could we get the product team's input on it? The first thing they do is actually they create a task in Asana and they assign that to the product or thought buddy and it has all of the trade-offs, the current road map, all the uh context for how our road map works within ASA and it produces a plan and it produces a a set of feedback on that um on that keynote speech that is like highly optimized for the way in which we work and is is correct and it's accurate from the perspective of it's using all of the real time context next. Um, and again, it's done in a multiplayer way. So, everybody in the product team can see that response and they can react to it. They can give it nudges and it'll remember that across multiple runs. So, that's a lot of talking about like what we've done with uh pre-built agents, the multi-step workflows and outcomes that are possible with cloud managed agents, uh, enterprise memory, shared memory. We should see it in action to like really get you a sense for what we're talking about. So, let's uh let's roll the video and I'll talk you through it. So, in this video, the the human the human being is a is a marketer and they're trying to launch a new campaign and they're going to use AI teammates that are leveraging clause managed agents under the covers and the way they'll kick it off is uh you'll see them in a conbon board inside Asana and they'll just create a new task saying hey I'm going to go ahead and and uh plan for a new campaign brief. So, let's roll the video and see that in action. Yep. So, this is a person uh they're like, "Okay, I I I've got this like task to go ahead and create a campaign brief and prototype a landing page." Like, it's not only a document, but it's also a product for a landing page. And perhaps they haven't used EIT teammates before. They go to the teammate gallery. They choose one of the pre-built teammates that have all of their behavior guidance and description in it. And when they go in over here and they customize it for their use, it will automatically pick up the right workg graph objects like the previous campaign projects or portfolios to to add to that teammate's memory so that it can it can go ahead and produce better content. So it's the teammate has gone ahead and and sort of first planned out its response uh and it's created a a document which is its campaign brief. And you'll notice it's also created uh an HTML file which is the landing page mockup for this new campaign. And again, if you track all of your processes in Asana, it'll automatically pick up that context. This is showcasing what you would see in the cloud console. Right? So in the console we pass in the outcome uh to the managed agents product and then uh what we can see is uh the runs within the console to to highlight that managed agents is is actually running the greater to uh to ensure that the verification loop is complete and the outcome is is as appropriate. So again like the combination has allowed our development team to ensure that we're getting highquality outcomes that's delivering on the customer promise that we have which is you're getting uh all the security benefits of arbback controls and app actors like agents is a true actor within the system you're getting the enterprise context and then managed agents is delivering on the outcome. So, they've gone from just an idea or a task, which would have taken them a bunch of time to create the brief, maybe send it over to creative and get a mockup in place for what that landing page should look like, down to a land to to a a page immediately. Um, and then interacting with the agent and asking to iterate on it is as simple as talking to it via comments, right? So let's say uh it picked up green uh as the primary color but the primary color has now changed based on the summer uh whatever theme. You can say this is great but let's make the primary color blue. Uh and you can give it some feedback that this is our new company sort of primary color. This will actually get ingrained into the agents memory. So if a different marketer picks up and uses that agent, it will not make that same mistake again. it will remember that the the new color uh scheme is blue. Uh and so you can see that the campaign brief letter is working on behalf of Sushi admin. Um and you'll notice that the memory is getting created. That's the reason why we're sort of expanding that. It's not something that an end user has to go care about, but we highlight that the memory is getting created. And boom, you've got like a blue uh campaign brief landing page. Now I want to showcase multiplayer in action. So, uh, this is great. So, maybe the marketer feels like this is a a good starting point. They've got a brief. They've got a mockup of the page. Now, they want to bring in, uh, somebody else on their team who can review it and give them feedback. And you'll notice the teammate is going to work in multiplayer mode. So, this new person comes in, um, and they're like, "Okay, uh, teammate, uh, thank you for doing this, but I would pref I would love to see an iteration of it that is more minimalistic in its, uh, in its look and feel." So again just just type it out as if it's a it's a comment and it is a real comment. You can hit go and then again like the cloud managed agents functionality will run in the background and create that minimalistic view. The other things to call out is because this is a shared workspace everything that's happened the interactions between the human beings and the AI agent is also tracked in the task and it's fully auditable. So at some point in time if you need to like bubble this up to your manager or your lead and get their approval, you can simply convert it to an approval. They'll see all the prompts that have gone in. They'll see the back and forth between the AI agent and the multiple humans and it gives them that much more confident that confidence that the right questions have been answered and they're getting the the best possible outcome without a bunch of back and forth, right? Like did you consider a minimalist version? Did you consider that the the decision was made to go ahead and move to the blue color, etc. Um, and again, I'm not showing it here in the demo, but if you go into the the teammates detail page, there is also a concept of uh who owns or manages that AI agent. So, these arbback controls I'm calling out mean that there's a definition of uh the human beings who are the agent sponsors and who can manage it. And so those human beings get a chance to delete memories or change the parts of the Asana context graph that the agent has access to to ensure that it continues to behave consistently going forward. Okay. So again like what you're seeing here is what we have generally available today. It's using uh it's using these sort of multi-step actions. It's documenting everything. It's working in a multiplayer way. The future for us is thinking about more capable more more multi-step workflows, right? like uh what what about entire launch planning processes? What about resource management and capacity planning across hundreds of people? How do you make that better? How do you how do you generate dynamic dashboards? How do you generate risk reports? How do you automatically alert uh end users on what remediation steps they could take to go fix issues and things like that. uh we're partnering with anthropic on learning faster from team patterns and agent skills and we're also identifying opportunities to move work forward more proactively. So proactivity is something we're working on where if an agent is uh or an Asana AI teammate is part of a project or is like looking at your conbon board even if you haven't assigned it any tasks it can automatically wake up and be like hey I can pick that up or I've seen uh this particular issue in a different project before and this is how you go ahead and resolve it. So what this has allowed us to do as a company is, you know, we've been able to focus on all of the aspects that make Asana great. Like the fact that you can define in a human readable way what your multi-step processes as a marketing team or the office of the PMO or in IT and you can interact with these agents in a way that is very human. It feels like you're onboarding a new person onto the team. You're giving them the context with these projects or documents. you're giving them feedback and multiple people can use them. So even in my example of like this person who's like no longer in a sauna, all of the work that they've done and those memories are reusable by people on the team to keep doing that work faster and doing that work better going forward. Okay, so that was uh a primer on how we're using managed agents uh to deliver Asanai teammates. Uh, we have about fiveish minutes left, so I can open it up and take some questions if there's any in the audience. Yeah, good. Thank you. >> Cool. This is our person in the back. >> Great talk again. Um, just quick question for you. You mentioned earlier that the validation of the like the agent itself happens on the anthropic side of things. Just curious what that looks like and what you folks would encode in there. Like you mentioned that Asana has a bunch of domain knowledge. Does that go into the verification? Sorry, I didn't realize I was talking outside of it. Does that go into the verification process also? >> So I I I only had parts of the question about how do we run the verification process? Do do you mind just >> Yeah, I can re rephrase the whole thing. So you mentioned the verification process happens on the entropic side of things where they're looking at the outputs of the manage agents and seeing if it's in alignment with what like the spec is for the output. Is there a sauna domain knowledge being injected there as well? How do you folks go about managing the contract between the managed agents and what you folks want it to actually providing you? >> Yeah, it's a good question. I think at a higher level what we're doing is we are passing in the asana context as part of the outcome definition uh as well as um yeah that's the place where we're doing that and then as we've been testing it out internally before we release like a pre-built uh capability to our customers the the there's like there's like another level of QA that happens obviously within Asana like with by our engineering team and then in the the the real world use case and utilization of this is again because we are a very like human in the loop system. Uh if there's any issues with the quality of the output for a particular customer because perhaps their context rough isn't as fully fleshed out or isn't as detailed, the more you use it and the more nudges you give it across multiple people, all of that compounds and just keeps getting better. So because we record that back within a p push it back as part of the call to run the managed agent every single time. >> Yeah, makes sense. Thanks again. Great talking. >> Yeah. Hey, thanks for the talk. Uh really insightful. Uh could you speak to a bit more about how you designed the rubric uh on like your like the rubric that your grader sees to iterate uh on the uh outputs that it generates? Were there any learnings there? Were there any learnings about on the rubric that the greater sees? Um I'm curious like do you have a do you have Bradley's on an engineering team? Hi Bradley. [laughter] Um do you have any thoughts on that Bradley that I mean I don't know if we learned anything unique as part of that. >> Sorry question again. >> Uh the question was um the question was if I understood it correctly like uh the the greater exact how do are there any unique ways in which we've been using that? Is that correct? >> Yeah. How is your experience writing a rubric for the outcomes creator uh and having it iterate on problems? >> I I think we want to approach it like we approach any other prompt. So I think in the end all the text that you provide to the model is a different form of prompt and you want to have different evaluations for the outcomes for different um things that we're trying to achieve. So if you're able to instrument that just like anything else, you're able to iterate quickly um and make confident decisions. Great. Any more questions? Right. There's one over here. >> Thank you. Um, thanks for the talk today. I was curious how you're thinking of skill maintenance over time. uh how we thinking about scaling teams or >> skill maintenance skill maintain markdown files. >> Yeah. So uh again like we're a product for like knowledge workers. We want to make it as simple and straightforward for our customers to deploy and use this as possible. And so the way in which I'm thinking about it from a product strategy perspective is Asana will decide what skills get baked into the uh the finished like generally available product and we're adding more uh and we're designing those based off like working backwards from our ideal customer profiles and the uh the advances we're seeing in the in the underlying sort of model provider. Um and that allows us to be very like prescriptive about okay here are the additional capabilities that will be available in a GA way like a generally available way that to the end user like if you're in IT or operations you're thinking about the job to be done for the teammate like I'm trying to go ahead and produce perhaps like a Figma design output or something of that sort and so it'll be marketed and messaged in that way and it's a shrink wrap product. So um again like over time we might open it up so that customers can design their own skills and like highly customize their AI teammates but the the sort of primary go to market motion the primary sort of use cases we'll pre-esign these AI teammates and the val from a skills perspective so they're like shrink wrapped um and then that way we get we get to control on our R&D side the quality level which ones get released uh how the what the life cycle and so on so forth. >> Thank you. >> Yeah, >> great. Um, we have one more. Okay, so maybe this is the last one because I see the counter clock is showing about a minute. >> So, uh, I'm also also building my my product with the CMA as well. And one of the problem I'm facing is um integrating with the third party tools like uh customer always want to integrate to some other things beside beyond our platform. How do you manage that like you integrate that with the ASA level or at the Asia level or how you manage the third party integration? >> Third party integrations for the greater um Bradley what's what's been our experience so far like we've we've got a few of those built out so I'm kind of curious. Yeah. >> Yeah. Yeah, in terms of thirdparty integrations and managed agents, we integrate them at actually both levels. So we integrate them um directly with our own AI teammates agent loop and we also integrate them at the MCP level with managed agents. So we want to make sure that the managed agents when we're using them have the you know all of the context that they need um and that we're also supplying context when we're not using managed agents. >> Awesome. Well, thanks everybody for joining us. Uh we're at the end of our time today and uh yeah, if you have a chance, give AI teammates a try. Thank you.