All right. So, you built an agent, you launched it, everything works pretty well in a demo, everyone is happy. But now let me ask you a few simple questions. So, how do you know if it's actually working out there? How do you watch across hundreds or thousands of real conversations every day? How do you feel or understand the health of the system? How do you make it better? How do you find the holes that you don't know are there yet? And that's the thing, right? So, most of the talks about the agents end up the moment when you ship. So, apparently it did work, the end. But I think the shipping is the moment when the real work begins. And somehow only a few people are talking about that. And I'm calling it the missing layer. So, let's dive into it. So, that's the world that we're living. So, you can create the whole product, you can create a whole startup in a couple of days, in a couple of weeks. You can write 100,000 of lines of code. You can spend a lot of tokens. And to be honest, it is the easiest part today with the help of the latest models. But I think the shipping is the moment when the real work begins. Because you need to close the loop as soon as possible. So, after you launch, you need to have some control and understanding of the system. And uh from my experience, the loop is uh at least as important as the product itself, sometimes even more. Because the tight feedback is the one that helps you to make product better every single day. And that's the missing layer, and that's what the rest of this talk is all about. So, what happens after you launch? And this is not something surprising. We had the same questions in the classical old software. You need to monitor what is happening, you need to understand how it behaves, you need to have some logs to detect the problems and fix them. Uh and for agentic systems, each one of those are even harder, and sometimes uh they turn into something genuinely new. So, let's talk about why this is hard and why this is hard now. So, the agent is not a normal software, right? You don't have a few features and several buttons. You don't have a predefined flow that you can test before you go to the live. Uh and the coverage is endless. So, think about like cloud code or codex, they can do a giant range of stuff whatever user needs and most of the agents do the same, right? So, you give the instructions and they can handle it. And you cannot write all the conversations in advance. So, this leads to a detailed part of the problem. The part that keeps me up all night. Which is you lose the feel for your own system. So, after you build the product, you need to have some kind of understanding, does it get better or worse? So, we need to monitor and understand what is happening. And the problem is that the normal safety nets don't save you here. Uh and believe me, we tried a few stuff. We built the unit test. We had some regex, some rule-based checks. We even created some scripts to simulate the customer conversation. Uh and yeah, it helps in some ways. Uh but at the end of the day, it is like only one slice of the whole problem. Because customers always do something different. Uh you cannot write it all down. They are too many and they are all different. And Harrison for it in the same way. So, you don't know what your agent will do until it is in the production. So, why this is a new problem? So, as you know, LLMs are not deterministic. The same input can have a different path. Even slight modification of the input can cause a different trajectory and the coverage is endless. You cannot list it all down. You cannot pretest until you go in the production. The second and the scariest one is the failure height itself. So, let's think about what happens when the agent is running for a long time. It struggled in the middle of a task. Uh it has some problems but it was lucky. Uh it was recovered. It finds some workarounds. Uh try some other tool calls or whatever. And you don't get any red alerts, any problems on a dashboard. Everything looks fine. But you know, this is a early warning for you. This is a problem that is hidden and that lives in your codebase. And you need to fix it as soon as possible because if you're talking about reliable agents, it shouldn't be depend on the luck, right? And also as Anthropic mentioned in the blog post, sometimes the agent love to make marketing features as complete without checking they worked. The next one is the tool calling, right? So, the tool surface is a huge. So, long-running task needs a hundred of tools and thousands of tools. Um sometimes it have a several summarization in the middle. It use some sub agent, writes a lot of code. It use a terminal for sure. It calls some other company services, third-party libraries. And uh they work pretty different way uh all the time. So, actually you don't know what you're looking for. So, sometimes finish doesn't mean it is helpful for the user. Maybe there wasn't any problem. So, agent finished, everything looks good. The answer was successful. But what happens like for example for our use case, sometimes user asked to build the itinerary. Agent run the flow. It built the trip. But it took a different service. It made a lot of mistakes in the calculating the price. So, user is not happy. So, technically it's successful but still failing the task. And as I mentioned, the unit test don't save you here. And production is the place when you learn what you need to test on the first place.

All right. so what happens after you launch the product, right? So you need to monitor and you need to understand and improve the system. Uh and what's the source of the truth, right? This is a log. Everyone has the logs. Everyone loves the logs. You have structured information. And uh you know, those machines are the best to understand and explore the logs much better than any human, much faster, taking rise and scripts to filter the giant of walls. Um And this is the most obvious way that you can hand it to the agent. Uh but as soon as you start working on that, maybe you build an agent or skill or whatever, you you quickly understand this is not as easy as you imagine because it needs a lot of reasoning. You need to understand the problem to uh differentiate if it's a real bug or a noise, to deep dive into the fresh trajectory, understand if it's a symptom or a root cause. So actually, you'll find out that the operate operating agent itself is an agent problem. So this is a look like end-to-end. So we have a traces, you have trajectories, you give the agent to access the code base. It diagnose the problem, understand what is happening, and send the PR. And then you can have a skill or sub-agent or whatever that controls the PR uh because you know, most of the agents are pretty eager to send the PR. They love to fix the problems. We prefer to have a separate agent which has a like fresh context. It try to check um the PR on different angle, on different view, run the um the focus test. And uh it is not biased of the problem itself. It tries to criticize call the PR. And uh sometimes it uh requests the changes. Maybe it close the PR directly and it helps us to to filter those problems. Uh and then you have the human in the loop, sometimes you don't. Uh and we can talk about this later. But, you know, this is the most obvious thing that you can hand it to the agent, which is which seems like a pretty obvious for most of the people. And uh a lot of teams use the same practice, but I think people don't appreciate how important it is, and you you need to spend some time on that. You need to calibrate. You need to make it reliable to trust the loop. And this is the fastest loop that we ever had. So, you know, after you build this simple simple system, you uh already have the feeling and understanding how behaves, what is happening. You detect the problem, some local fixes as soon as possible, and you can have the PR in PR ready in half an hour, and you can uh easily understand what is happening. So, let me walk you through uh how I'm handling this. Everything is not optimal, but I think this this will help you to to get some point. So, actually we have a two main flow. The first one is the fastest loop that helps you to to detect and uh fix the problems as soon as possible. And another one is like more on a zoom out that helps you to have a on a high-level understanding, and it helps you to have hand on a pulse. So, the first one is a log monitoring agent, the one that I already mentioned. So, you have trajectories, so we have logs, we have the access to a code base, and it runs every hour or uh uh every few 15 minutes, and it try to understand the problem. It deep dives in the in the logs, uh understand does the user user end up stuck, and uh send the PR, or sometimes send the Slack alert. And this is this is pretty uh important because sometimes the problem is uh, uh so critical so we need to fix them as soon as possible and yeah, it works pretty well. So, this is the one example how the PR can look like. So, you have a nice description, a short explanation what is happening, you have some metadata, you have a nice diagrams, mermaid or ASCII tables, maybe you will have some HTML artifacts that helps you to give you a glance of the problem and quickly understand what is this PR for. So, this is the example how a static analysis can look like. It helps you to quickly give you a feedback, detect if there are some critical problems. Sometimes it it is just like heads-up or you know, there are some warnings, there are some problems so you need to check them when you have some time. And as I mentioned the review agent is uh, pretty critical because it tried to check the problem in different angle. It always tried to criticize the problem, score the problem and as soon as it's ready, it send the PR to the human. And sometimes people talk about that if we need to have a human in the loop because you know, still human in the bottleneck in this case. In our case the the the the PR agent and the review agent send 10 times more PR than the three of us every day. So, we need to have some clean system how we're going to handle this to not be a bottleneck in this system. But from my experience as I mentioned this PR and the review agent helps me to have a nice description, some artifacts that helps me to quickly understand the problem and maybe I spend a few minutes to at least understand what is happening. So, I think at this time it's okay but maybe we'll remove it in the future. And yeah, people are talking about that so you need to you need you don't need to be a person like in this problem. Some of them prefer to remove the humans in this loop. But you know, the trend is that you need to close the loop first. So, let's make the problem when you are the bottleneck and then you can remove yourself pretty easily, I think. So, this is our some examples how the review agent feedback can look like. As you know, it requests some changes, you have some summary, you have some diagrams, explanation, what are them some risks, some edge cases. And sometimes after a few iterations of the code in the loop where the key where the key is ready, so we don't need you don't need to have any more changes. So, after that the human will jump into the loop. For the previous agent as I mentioned, that is especially good when you want to fix some local problems. For our case, it runs every hour with the chance on the one hour window of the logs and it doesn't have any high-level understanding of the problem.

So, we found found out that we need to have another system that helps us to to get to get like more than high-level explanation, some kind of a health of the system. And you know, visibility is the easiest piece. Before the agent, it was impossible, so you cannot deep dive or summarize some of the top conversations. But right now, we can have a system that helps you to to score every conversations, understand what's happening and give you a high-level summary of the system. So, this is the session analyzer and the main goal is to just give me the score of the health of the system, right? So, we try to check every conversation, runs a lot of state agents, it spend a lot of tokens, but yeah, it helps us to detect some patterns connecting the dots and try to understand some high-level patterns. And yeah, it also detects some like logical problems, what is the cause, how many tool calls did you use, how many sub-agents, how many summary happened or whatever. But also it gives some AI insights, some entities, so you have an understanding of the problem. So right, as I mentioned, one of the main problem is that you lose the control of the user launch the production. So you need to have the system that helps you to control, at least to have some understanding what is happening, how it looks like, is healthy or what or not. So Actually, let me let me show you. One of the example how how it looks like. So actually we built it ourselves, so there are a lot of other companies and tools that provide the same kind of system, but I prefer to build it myself because I know what I'm interested in for, what I'm looking for. So as you can see, we have the health of the system, we have number of sessions that were analyzed, the cost, we have the average score, some success rate. We have some trends, we have the AI insights, and this is the most important part when the AI when the agent try to connect the dots, find the patterns. If there are some critical ones, you have a description for each of them, what is this, why it matters, what are the root cause, how many sessions affected, and some recommendation fix. So right now this is just a anonymized data, but it comes from a from a real conversations. So we have a score distribution, each company number of sessions or cost we have, the sentiment analysis, some entities, we have analytics about tool calls, all the success rate, how many rejected and why. And you have a detailed analysis of the each session. So, it ranks each one of them, scores. It is how many times it was running, how many messages, how many tool calls, how many summary, and you have a detailed explanation for each of them, what was the problem. It is something that you need attention, and believe it helps a lot, and it helps you to check and watch across hundreds of uh conversations. So, the main goal of this dashboard and the system is not to fix some uh um specific problems or bug. This is more than a high-level that helps you to watch across hundreds or thousands of real conversations. So, you can run it once in a week, two times in a week, or something like that. All right. So, the next one is that mm So, the problem of the previous uh agent that I mentioned is like the first one helps you to detect the specific problem. The second one is to give you a high-level understanding, but both of them works from a angle of the logs or a uh code or a session itself,

but you need to have some kind of user perspective, right? So, that's why we have some computer use agent that helps you to to uh to open the browser, uh to log in, and try to simulate the customer itself, because sometimes you have some problems in the UI. You need to um check if everything looks good. Uh and uh yeah, sometimes code and logs cannot help you uh in this way. So, this is uh example how it looks like. So, you used Codex uh sometimes. So, it used um uh the browser itself. Uh Actually, this is pretty slow. Uh and we try to build a specific skill that know our uh website, our DOM, how it looks like, and that is much faster, and it can open the website, login, open the sessions, send the messages, check what is happening. Uh, and also check, how it looks like, what what are the some artifacts. And, yeah, it was pretty good. But, yeah, you you you need to know that it it it will spend a lot of a lot of tokens. And also, for all of those problems, you need to remember that, you need to give access to all the kind of tools that is needed. So, you need to have a lot of trajectories and metrics, database, UI, so as the humans need, right? So, you need to give all context, all possibilities to understand what is happening. For example, for the computer use agent, when detect some problems, it should be able to analyze the trajectories, check the database, to understand what happened. And, you know, that's why I'm calling it a meta harness, the whole system, when everything is connected, and the PR or the answer from the agents are depend on the depend on the real problem, and they're not casing what is happening. So, the most is not the model alone, and you need to build the agent, or a system, or a harness around it, which which watches itself, understand, improve, and help you at least to at least to monitor what is happening, but also in the ideal case, to close the loop, send automatic PR, notifications, whatever, and help you to speed up the process. So, shipping is the easiest part today. If you want to if you want to build a production agent, you need to close the loop first, because somehow people are not talking about how important it is what happens after you launch, so everyone can have the same model, everyone can have the same agent or harness, but you need to have some internal system that helps you in this process, detect the problems, and give you sense what is happening, and helps to make the product better. Thank you.