In the Monday Ecosystem, on any given task in particular. And what I'm going to show you today is very powerful lessons learned that we have in our experience building agents. And it was said earlier today by the HRVA team and I think others that to build very successful agents, you have to focus on product and user experience.

And we have a saying on Monday that "The biggest barrier to adoption is trust." It's actually not the common. And I want to show you a few examples of things that we've learned. So, when we think about autonomy, we think, you know, we're all engineers and we love to think about autonomous agents and, you know, agents doing everything around the clock, but actually the opposite is true.

We know how our users are using agents and what they think. Imagine that every company, every user has a different risk of data. And when you build AI agents, you should give users a control. And what we've learned by applying this is that we've actually increased adoption in the same way, by giving the control and the users have to decide how they want to control their agents.

Secondly, is entry points. Now, if you're building a startup from scratch, that's something else. But as a huge company like Monday, one thing that we've learned is don't rebuild and be new user experience. Try to think how you can create these experiences within your existing products. So, when you think about how agents can work at Monday, we already have people working at Monday, on Monday.

We just assign people. So, we can do the same with agents. Just think about how you can assign original workers or agents to actual tasks. And by doing that, our users have no new habits that they have to learn. It's seamless within their experience. Another super important thing that we've learned.

So, originally, when we released these agents, imagine that you can ask in the chat and say things like, create this board, create this project, modify this item. So, for our users, Monday boards are production data. I think a very good example I'd like to give is think about Cursor AI, which is an amazing product.

We all buy the code and introduce it earlier. But imagine if it's Cursor AI, instead of you as developers seeing the code, imagine it was pushed straight to production. I assume that none of you, maybe most of you, would have not used it. And that is just how important user experience is, because technology, technology-wise, you could do that.

Cursor could have done that. And what we did is that we saw users onboarding, testing them out. And once came the time to actually push content to the board, that's where they chose. So, we introduced a preview. And this preview increased adoption by insane. Because users now have the confidence that they know what's going to have this guardrail before they actually save it.

And they know what's going to be the outpost before they see it save it. So, when you think about building AI experiences, think about previews. Think about how users can have a control and understanding before AI releases the production. And lastly is expandability. Now, expandability, we've heard a lot.

Think about expandability as a way for your users to learn how to improve their experience with the AI over time. Because when they have an understanding of why the outputs happen, they have an ability to change the outputs. So, these four are super important components that you actually produce in your products that increase adoption more.

Very, very nicely. Now, let's talk about the tech. So, we actually built our entire tech system of our agents on LangGraph and LangSmith. And we've tested out various frameworks and we found LangGraph to be the number one by far. And, just a few examples. So, what's great about LangGraph is that it's not really appealing, but it still does everything you don't want to deal with as an engineer.

Like interrupts and checkpoints, persistent memory, even the loop. Those are critical components that we don't want to deal with, but we have that. On the other hand, we have super great options to customize it just for what we need. and we'll show you an example in one second. And, initially, native integration, we now process millions of requests per month using LangGraph and it's proven to be super scalable.

So, let's take a look at how this is handled. So, we have LangGraph as the center of everything we're building. And, around our LangGraph engine, which uses also LangGraph and LangSmith for monitoring, we also have what we have built as what we call AI blocks, which is basically internal AI actions that we've developed on Monday.

We've actually built our own evaluation framework because we believe that evaluation is one of the most important aspects when you're building an AI. And, I think that enables a lot of that evaluation as you can see. So, I'm not going to dive into that. And then, we also have our AI gateway, which is our way of preserving what kind of inputs and outputs are enabled in the system.

Now, let's take an example of our first digital workflow that we released, which is the Monday Expert. So, basically, what you see here is a conversational agent using the supervisor methodology that our system involves four different agents. We have a supervisor with a data retrieval agent, which is in charge of retrieving all data across Monday.

For example, knowledge base, board data, we also use web search. Then, we have our board actions agent that does actual actions on Monday. And, lastly, we have the answer composer that, based on the user, the past conversations, tone of voice, and all kind of other parameters that are defined by the Monday user, actually composes the final answer.

And, we've even added a really awesome tool that we've learned, which is called Undo. So, basically, we gave the supervisor the ability to dynamically decide what to undo within the actions based on the user feedback. Which is, by the way, proved to be one of the coolest use cases for building.

And, I want to share a bit of our lessons learned as we build this agent in privacy. So, when you build a conversational agent, assume that 99% of user interactions, you have to know how to handle them. And, it's proven statistically right when you think about the innocent amount of things users can ask.

Probably, you've only handled 1%. And, for this, we learned to start with what happens in 99% of interactions that we don't know how to handle them. So, for example, what we did was, if we detect the user's asking some action that we don't know how to handle them, So, we would search our knowledge base and give them an answer for how they can do it themselves.

This is an example of one way of resolving solving solving. We've talked so much today, so if I think about Microsoft VALs, it's the VALs of your IT. Because, models change, technology is going to change so much over the next few years. But, if you have a very strong evaluation, that is your IT.

That will allow you to move much faster than your competitors. Even the loop, critical, we talked about this a lot at the beginning. So, for those who have really shipped AI to production, I think you've seen that it's one thing to bring AI to about 80%, but then it takes another year to get to 99%.

And, this is a very important rule, because we really felt confident when we were working locally, once we shipped the production, we realized how far we are from the actual product. I see some of the aliens resonate with me on that one. All guardrails, we highly recommend that you build outside the element.

Right? We've seen things like the element of the judge. Even back to the cursor idea. By the way, I think cursor is such a great example for a way to build good product experience. because I want you guys, especially with light coding, after 25 rounds it stops. Right? This is an external guardrail you put in, no matter if it's actually really successful.

25 rounds and it stops. Just think about how you can bring those guardrails outside the element. And then lastly, and this is a very interesting one, is that it might be obvious that it's smart to break your agent into sub-agents, right? Obviously, when you have specialized agents, they work better.

But what we've learned is that there is a very important balance, because when you have too many agents, what happens is what we like to call compound hallucination. So basically, it's a mathematic problem, right? 90% accuracy times 90% accuracy, second agent times the third time, the fourth. Even if they're all at 90%, we're now at 70%.

So, and it's a mathematical, it's proven, it's a mathematical, right? So, I think there's a very strong balance between how much of agents you want in your multi-agent system, versus having too much or too little. And it's something that I think there's no, like, rule of thumb. It's something you have to iterate on based on your business.

So, let's talk about the future of work. And we believe that the future of work, and what we're working on Monday, is all about illustration. And I want to give you an example. So, this is a real use case that we try to work on internally. We just had our earnings report, just a few days ago.

And, for those of you working in large public companies, you're probably, or if you're involved in these reports, it's a tedious process. There's so much data, narrative, information, across a company together, so many people involved. So, we said, "What if we automate this? What if we had a way to automate an entire workflow that would automatically create everything we need for earnings?" We agree, right?

But, there's one problem with this, and the problem is that it will only run one support. We invest the entire month building an amazing workflow, and then we run it once, and the next time we run, AI is going to change dramatically. New models are going to come out, everything is going to change in the workflow, and then we have to rebuild everything.

Right? So, you got us thinking about how can we solve this. So, I want you to imagine, what if there was a finite set of agents that could do infinite amount of tasks? Now, the irony is that this is not some big trick, this is exactly how we work as humans, right?

When you think about us, we each have our specialized skills, some are engineers, some are data analysts, and then, every time there is a task at work, some of us do A and some of us do B. So, there's no reason why we shouldn't work with agents and AI.

So, when we think about the future, we think about what we see here. Imagine, that for the same hidden task that we had, I showed you earlier, we had a dynamic way to orchestrate a very dynamic workflow with dynamic edges and dynamic rules, choosing dynamic, very specific agents that are perfect for the task, run the task, and then dynamically dissolve.

So, this is super exciting and one of the things that we are working on with LinkChain, and we really want to see this come to life in the future. So, lastly, we're actually opening our marketplace of agents to all of you, and we'd love to see you join the waitlist and join us in building and trying to tackle this one billion tests that we are trying to take.

So, thank you very much, everyone. It's a pleasure. Thank you. Thank you.