WEBVTT NOTE Sentence-level transcript of https://www.youtube.com/watch?v=YNT7Plf9KIg NOTE One cue per sentence. Cue ids are the line anchors on /transcripts/YNT7Plf9KIg.html. A cue ends where the next begins, or 2 s after its last word. s1 00:00:01.309 --> 00:00:03.309 [music] s2 00:00:18.160 --> 00:00:21.880 All right, it is 11:10 so officially time for our session. s3 00:00:21.880 --> 00:00:23.360 Thank you so much everybody for joining. s4 00:00:23.360 --> 00:00:31.400 I know this is the last day of the conference so I really appreciate for for all of you that that actually wanted to come on Thursday and and listen to our topic. s5 00:00:31.400 --> 00:00:37.200 My name is Matt Gibiits and I'm the regional director of solutions engineering for AI native at Dynatrace. s6 00:00:37.200 --> 00:00:41.480 With a show of hands, anybody knows what Dynatrace is? s7 00:00:41.480 --> 00:00:44.480 All right, we got a we got a couple hands, okay. s8 00:00:44.480 --> 00:00:51.560 We are an observability platform, AI powered observability platform, but we're not going to be talking much about Dynatrace today. s9 00:00:51.560 --> 00:00:58.240 Because what we want to address today is a little bit different topic and the topic that I want to address is, as you see the title of the session, s10 00:00:58.240 --> 00:01:02.880 that your AI agent has no nervous system. s11 00:01:02.880 --> 00:01:07.960 Probably an intriguing title and you're thinking, well, of course it doesn't have a nervous system, it's it's not a person. s12 00:01:07.960 --> 00:01:15.520 Well, but if you really think how AI agents are being used today, we are using these agents to replace things that people used to do. s13 00:01:15.520 --> 00:01:20.320 And a lot of times, in order to do that, we need the reasoning. s14 00:01:20.320 --> 00:01:31.360 And when we really think about it, if we need reasoning, we need these agents to be able to actually not necessarily behave like humans, but have enough input to understand s15 00:01:31.360 --> 00:01:38.400 what they need to do to actually help us in our organization and not just automate things that aren't necessarily working very well today. s16 00:01:38.400 --> 00:01:41.560 So, with that said, let's let's break this down. s17 00:01:41.560 --> 00:01:47.040 With a show of hands again, how many developers do I have in the room in here? s18 00:01:47.040 --> 00:01:48.960 Okay, perfect. s19 00:01:48.960 --> 00:01:51.400 Any team leads? s20 00:01:51.400 --> 00:01:52.440 Okay. s21 00:01:52.440 --> 00:01:54.640 And okay, the last one might be a little bit tougher. s22 00:01:54.640 --> 00:01:56.320 Do I have a head of engineering in here? s23 00:01:56.320 --> 00:01:58.680 Would would you call yourself a head of engineering? s24 00:01:58.680 --> 00:01:59.960 All right, perfect. s25 00:01:59.960 --> 00:02:01.080 I got one. s26 00:02:01.080 --> 00:02:03.760 So, if you take a look at these questions, we're not going to go through all of them. s27 00:02:03.760 --> 00:02:06.160 We only have 18 minutes left in here. s28 00:02:06.160 --> 00:02:15.080 But, if you take a look at these questions, has any of you ever ask yourself a question or been asked a question, why am I stuck in a loop with my agent? s29 00:02:15.080 --> 00:02:26.640 How many of you have used, for example, Claude, and it just keeps repetitively doing the same thing over and over, consuming tokens, not giving you the result that you want? s30 00:02:26.640 --> 00:02:27.800 Anybody experience that? s31 00:02:27.800 --> 00:02:29.200 Everybody has, right? s32 00:02:29.200 --> 00:02:38.920 Now, if you think about it from a human perspective now, if you as a human do research, and you get results that that are not what you want, you will change your approach. s33 00:02:38.920 --> 00:02:41.040 You approach it from a different angle. s34 00:02:41.040 --> 00:02:46.200 But, our AI agents today, they're not smart enough to do that. s35 00:02:46.520 --> 00:02:49.000 All right, let's let's shift to to another question in here. s36 00:02:49.000 --> 00:02:51.080 I like the one under team lead in the middle. s37 00:02:51.080 --> 00:02:53.880 How can I handle operational issues? s38 00:02:53.880 --> 00:03:02.840 Are you thinking about that yet today, or right now are you still in the boom of let's just get things deployed, let's just get get things going, and we'll figure out everything else later? s39 00:03:02.840 --> 00:03:07.400 Anybody in here having operational issues with your agents? s40 00:03:07.840 --> 00:03:09.720 Here and there, maybe. s41 00:03:09.720 --> 00:03:11.360 Okay, uh let me throw a twist in here. s42 00:03:11.360 --> 00:03:14.519 How about security concerns? s43 00:03:15.200 --> 00:03:16.640 That That was a layup, right? s44 00:03:16.640 --> 00:03:19.360 I think everybody Everybody raised their hand in here. s45 00:03:19.360 --> 00:03:22.320 And so, again, a a very important questions that we have to ask ourselves. s46 00:03:22.320 --> 00:03:26.880 And the last one that I want to try with you guys, let's look at the the head of engineering in here. s47 00:03:26.880 --> 00:03:28.239 I love the middle one again. s48 00:03:28.239 --> 00:03:33.800 Does our app or does the agent bring value to our users? s49 00:03:35.800 --> 00:03:48.600 I think we we jumped in so quickly to the AI world and at the AI era that a lot of the times I see customers and and spending 3 days in here talking to folks, everybody has that AI buzz, this AI agent buzz, but s50 00:03:48.600 --> 00:03:51.320 how do you measure value? s51 00:03:51.320 --> 00:03:56.680 Do you have instructions already today to how to measure value of your AI agents? s52 00:03:57.440 --> 00:03:58.560 No, right? s53 00:03:58.560 --> 00:04:08.720 And and I almost think that as much as you want to run fast and get there, we have to take a little pause and understand what are we really trying to accomplish and how can we measure the success of our agents? s54 00:04:08.720 --> 00:04:19.840 Because if we're spending our engineering resources, time, effort, money on creating these agents and and and utilizing them in a way that we believe helps our organization, we need to come up with measures s55 00:04:20.160 --> 00:04:22.240 that'll help us do it. s56 00:04:22.240 --> 00:04:34.080 Now, with all these questions, hopefully I I I I set up a picture a little bit in here to to to really jump into the next topic that I want to discuss, which is led in here by a quote from my CTO, Bernd. s57 00:04:34.080 --> 00:04:37.960 And I'm not going to read the whole thing, but just highlight what we see in blue in here. s58 00:04:37.960 --> 00:04:40.040 The agents operate at speed. s59 00:04:40.040 --> 00:04:40.919 Would everybody agree with that? s60 00:04:40.919 --> 00:04:43.360 That they're pretty fast? s61 00:04:43.360 --> 00:04:46.080 But without sight. s62 00:04:46.280 --> 00:04:58.720 And what what we mean by that is these agents today are only as good as the data that is available to them to make the reason to make the reasoning to make a decision. s63 00:04:58.720 --> 00:05:09.200 If the data that is provided to our agent is missing context, is missing details, is missing the right permissions to pull the data from some of the tools in your environment, s64 00:05:09.200 --> 00:05:14.080 you start entering the the very buzzy word out there like hallucinations. s65 00:05:14.080 --> 00:05:22.480 You start doing processes and automating things in your environment that now probably don't bring in value because there's not enough context in your environment. s66 00:05:22.480 --> 00:05:38.640 So, what if I told you that essentially what we want to do in here is we actually don't need your agent to necessarily have nervous system or sight to be efficient and be productive. s67 00:05:38.760 --> 00:05:41.800 There's obviously a little twist on the title of the session in here. s68 00:05:41.800 --> 00:05:49.880 But what they need is actual context of your environment. s69 00:05:50.000 --> 00:05:52.160 You can pick any agent that that that's out there. s70 00:05:52.160 --> 00:06:01.920 You can just pick the the easy scenario of Claude and trying to automate things with um Claude inside of your um SDLC life cycle. s71 00:06:01.920 --> 00:06:13.640 And as you do that, if Claude doesn't have access to the context of your environment, if it is not able to understand the dependencies of your services, if it is not able to understand how your applications s72 00:06:13.640 --> 00:06:29.480 are being used by your users, it will start coming up with decisions and advices that might seem right at that point, but they won't be right in the long term because there's not enough context for that agent s73 00:06:29.480 --> 00:06:33.080 to understand how your environment really looks like. s74 00:06:33.080 --> 00:06:38.960 So, what I want to sum up this slide with is this one sentence in here, context is king. s75 00:06:38.960 --> 00:06:45.800 And what context is, it is that nervous system that we that you can provide to your agents. s76 00:06:45.800 --> 00:06:57.200 So, as they're communicating, as you're automating things, as you're creating new processes, that connective tissue of a context is driving all of the processes that you're automating with your agents. s77 00:06:57.240 --> 00:07:00.200 So, let's take a let's take a look at a couple examples. s78 00:07:00.200 --> 00:07:06.240 So, keeping that in mind, what what what I want to present to you is Blue Box by Dynatrace. s79 00:07:06.240 --> 00:07:15.640 And what a Blue Box is is essentially an agent that will now be able to be integrated in the middle of any of your life development life cycle to provide context s80 00:07:15.640 --> 00:07:21.480 to any of your AI coding agents or other proprietary agents that you're developing in your environment. s81 00:07:21.480 --> 00:07:23.000 I have a couple slides that we're going to go through in here. s82 00:07:23.000 --> 00:07:30.120 I'm not going to go through every single scenario in here, but I'm going to point out the most important things that that I believe are helpful in here. s83 00:07:30.320 --> 00:07:32.000 Let me Let me run this scenario by you. s84 00:07:32.000 --> 00:07:41.640 How many times you as a developer develop a feature, maybe even develop a feature or skill for an agent, and you test it locally, and it works great. s85 00:07:42.200 --> 00:07:43.400 Locally, everything works great, right? s86 00:07:43.400 --> 00:07:45.080 We're happy, it's awesome. s87 00:07:45.080 --> 00:07:52.600 And then what we do is we merge to to a main branch, we push it out there, and all of a sudden three other services are broken. s88 00:07:52.600 --> 00:07:55.480 Has that happened to any of you? s89 00:07:55.760 --> 00:08:04.280 Where your impact, even though locally it worked fine, once it was merged with other agents, with other applications, now it broke a process in your environment. s90 00:08:04.280 --> 00:08:08.600 That is one of the most important things that Blue Box by Dynatrace can provide in here. s91 00:08:08.600 --> 00:08:17.320 We will be able to bring that essentially services and dependency mapping for every single one of your agents, every single one of your AI workloads. s92 00:08:17.320 --> 00:08:23.880 So, as you're developing and as you're making changes, you're not just talking about testing things locally. s93 00:08:23.880 --> 00:08:29.919 We'll actually be able to now use Blue Box to bring the production context into your local testing. s94 00:08:29.919 --> 00:08:43.719 So, now you know whether the feature that you develop not only works locally for you and what you're trying to automate, what you're trying to achieve, but also that it won't break and impact negatively anything else that that your agent that your workload is connecting to. s95 00:08:46.160 --> 00:08:51.320 Let's take a look Let's take a look at another um example in here. s96 00:08:51.320 --> 00:08:55.520 I This is honestly one of my favorites just in the entire world of observability. s97 00:08:55.520 --> 00:09:05.760 I've been doing observability now for 8 years, and I think if there's one goal that I ask any of my customers, like, what would you like to achieve with your observability strategy with now AI? s98 00:09:05.760 --> 00:09:09.120 And when it comes to issues, I think this is everybody will say that. s99 00:09:09.120 --> 00:09:16.240 Find issues before they're real issues, before they impact my organization, before they impact my users. s100 00:09:16.240 --> 00:09:23.000 This is now exactly what the context that Blue Box brings into your agents will be able to do for you. s101 00:09:23.000 --> 00:09:24.640 And how do we really get that done? s102 00:09:24.640 --> 00:09:33.280 We are able to now again understand end-to-end the interactions of your agents within your application, within your ecosystem, within your organization. s103 00:09:33.280 --> 00:09:43.960 And what we are able to do is we are able to use the historical data from your environment, the historical the historical loads to understand what regular what normal looks like. s104 00:09:43.960 --> 00:09:56.320 So, when things start to deviate from what normal looks like, we are able to now get ahead of it and inform your agents, let's say in your IDE for your developers, s105 00:09:56.320 --> 00:10:05.320 that one of the services that belongs to them now it's acting slower or all of a sudden it's throwing errors that it didn't throw. s106 00:10:05.320 --> 00:10:10.840 Now, what Blue Box will also do will be also integrated in the middle of your code repository. s107 00:10:10.840 --> 00:10:17.080 So, as you do that, we will now also have the context of what was changed in your ecosystem. s108 00:10:17.080 --> 00:10:18.520 What was changed in your application? s109 00:10:18.520 --> 00:10:20.840 What was changed in your workload? s110 00:10:20.840 --> 00:10:31.200 So, now be able to overlay that data and understand that the issue that might be happening in your environment was actually caused by a change that somebody pushed out there. s111 00:10:31.200 --> 00:10:34.200 Maybe by a merge that wasn't successful. s112 00:10:34.200 --> 00:10:36.200 Okay? s113 00:10:36.600 --> 00:10:42.520 So, as we dive into the next um scenario in here, we discovered an issue. s114 00:10:42.520 --> 00:10:44.080 We We started with creating context, right? s115 00:10:44.080 --> 00:10:45.480 So, we have the context of your environment. s116 00:10:45.480 --> 00:10:50.480 We're able to bring literally production context data to your local testing, to your developers in their IDE. s117 00:10:50.480 --> 00:10:53.760 You bake in Blue Box into your AI coding agents. s118 00:10:53.760 --> 00:10:55.880 Now, we're able to detect the issues early. s119 00:10:55.880 --> 00:10:59.640 We're able to start to be product proactive. s120 00:10:59.640 --> 00:11:00.839 But, what's next? s121 00:11:00.839 --> 00:11:03.440 We have to talk about fixing things. s122 00:11:03.440 --> 00:11:11.320 And here's yet another example where Blue Box will be able to be directly baked in into your SDLC. s123 00:11:11.320 --> 00:11:22.280 So, when we detect that there is an issue, when we know and we have the knowledge of your repo, we know who pushed it, we know what changed, we are now able to again once again provide the context to your developers s124 00:11:22.280 --> 00:11:29.520 and let them know that the service that is now having an issue, that the agent that is now having an issue, that the workload that is now having an issue s125 00:11:29.520 --> 00:11:31.600 can be remediated in the following steps. s126 00:11:31.600 --> 00:11:35.840 So, again, why is the context so important in that process? s127 00:11:35.840 --> 00:11:44.800 Because when we need to fix a bug that's causing an issue in our environment, it is it might be changing one line of code to fix that particular issue. s128 00:11:44.800 --> 00:11:47.880 But after you change that one line of code, what happens to the rest of your environment? s129 00:11:47.880 --> 00:11:50.000 What happens to the rest of your application? s130 00:11:50.000 --> 00:11:56.560 So, again, that context and the dependency of all the other services in your environment is super, super important. s131 00:11:57.840 --> 00:12:07.000 So, as we do that, as we think about fixing things, it's not only about fixing the the issue that we have at hand, but also making sure that we don't cause any other issues in our environment. s132 00:12:08.400 --> 00:12:18.880 Um and the last um um or or two more suggestions that I want to run through is actually briefing your agents before building starts. s133 00:12:19.560 --> 00:12:25.040 That's actually, I think, one of one of my favorites when it comes to directly talking to the developers. s134 00:12:25.040 --> 00:12:34.160 I think the way too often we see developers going out there, and somebody came up with a feature, and now the developers just go and develop it. s135 00:12:34.160 --> 00:12:42.160 But have we done any research up front to understand what actually that feature needs to deliver to our users? s136 00:12:42.160 --> 00:12:45.839 What are we actually trying to accomplish with with that specific feature? s137 00:12:45.839 --> 00:12:48.280 That's exactly what we'll be able to to do in here. s138 00:12:48.280 --> 00:12:51.280 We'll be able to actually plan before you prompt. s139 00:12:51.280 --> 00:13:04.640 So, when you're building your agents, when you're building your applications, when you're using your AI coding agents, again, Blue Bags will bring in all that context from your application today, from all the from all the agents that you already have in your environment today, to understand that as you're planning for a new release, as you're planning for s140 00:13:04.640 --> 00:13:12.320 a new feature, you'll have enough data to understand what that feature that you're now focusing on needs to encompass. s141 00:13:13.880 --> 00:13:25.080 And the last scenario that I that I want to share with you guys is that at the end of the day, providing context to these agents can further drive automation. s142 00:13:25.080 --> 00:13:31.280 But when we talk about further driving automation, I'm sure some of you start thinking about the concept of human in the loop. s143 00:13:31.280 --> 00:13:38.320 Like at the end of the day, if we just let our agents do everything, I think it'll be a pretty messy world, right? s144 00:13:38.320 --> 00:13:44.760 At some point, we want to be able to have control over what we are doing in our environments. s145 00:13:44.760 --> 00:13:47.320 So, obviously, with Bluebox, you'll be able to do that as well. s146 00:13:47.320 --> 00:13:50.000 And I I I'd like this picture that we have in here on the right, right? s147 00:13:50.000 --> 00:13:51.640 We'll We'll first start with observe. s148 00:13:51.640 --> 00:14:04.840 Observing your environment, building that context, building that dependency mapping, providing that locally to your developers as they're testing, given all the production data, given all the production um details that they need to properly test their code. s149 00:14:04.840 --> 00:14:19.480 Once you have that, and then we detect issues, we'll be able to actually suggest fix, but not just fix for the particular issue that's breaking the agent, but using the context of your environment, using the context of the application that's monitored, using the context of the agents that are being monitored, s150 00:14:19.480 --> 00:14:22.840 making sure that the fix actually addresses what's happening in your environment. s151 00:14:22.840 --> 00:14:36.800 Lastly, we'll be able to drive the the entire SDLC in here by providing the fix, and giving you the control at the end of it, to make the decision whether you want to push the feature out there, whether you want to push the fix fix out there, or not. s152 00:14:36.800 --> 00:14:42.720 So, with that said, um that really brings me to the to the end of our um our a little pitch about uh Bluebox. s153 00:14:42.720 --> 00:14:49.560 And And what I like to finish with is we want to help agents ship code you trust to production. s154 00:14:49.560 --> 00:14:56.640 So, if this is interesting to you, um you can go ahead and go to bluebox.ai, and you can actually sign up for a preview of it. s155 00:14:56.640 --> 00:15:01.040 Um uh as as soon as you do that, we'll be reaching out to you to give you access to the platform. s156 00:15:01.040 --> 00:15:06.360 I also have my back pocket little um things that you can scan, so I'll just walk around the room now and give them to you. s157 00:15:06.360 --> 00:15:08.640 But, with that said, we have 5 minutes. s158 00:15:08.640 --> 00:15:15.120 So, if you there's any questions that that anybody wants to ask, uh we can absolutely use that time for those as well. s159 00:15:17.200 --> 00:15:19.440 No questions? s160 00:15:34.080 --> 00:15:36.080 Mhm.