Markdown source

Transcript: Building Agents with Amazon Nova Act and MCP - Du'An Lightfoot, Amazon (Full Workshop)

Source Video

Local Cache

Transcript

[Music] Building agents with Amazon Nova ACT and MCP. I'm excited today because we're going to build intelligent autonomous AI systems that can help you build, scale, and improve your applications and business. My name is Dewan Lightoot and I'm joined by swap. Swap. Yeah, there we go. There you go. My name is Dwan Lifford and I'm joined by Hey, I'm Banjo Bami. I'm a solic architect here at AWS. Now, this is the AI engineer worldfare and I've been in tech over 15 years and right now is the most exciting time for me in my entire career. And one of the reasons for this excitement is agents. How many of you right now are been building agentic systems? I love it. So when we talk about agentic AI, I think it's important that we level set from an AWS perspective. There are three key terms we need to think about. First, the ability to plan. A agent gets a prompt. It gets an objective and it determines the actions that need to be taken. So it creates the plan and then it takes actions on those actions by using things like tools. Now the last piece, the third piece and probably the most interesting is the reasoning where the agent is able to evaluate the results and determine if it needs to update the plan and take additional actions until the objective is complete. This is an agent. Now when we actually break down the architecture, I think it's important to take a look at this because we have the user input, we have the agentic system, we have the possibility of some type of human in the loop and then we have the generator response. Now when we dive a little deeper, there's some components of this agentic system. We have the LLM. We have a knowledge base with external information that we want may want to provide. We have guardrails to say to the model don't do this or to ground the model with the truth from our knowledge base to say okay is this actual relevant information. Is this accurate to the information we're receiving from the knowledge base? And then we have access to additional tools, memory, or we may need to talk to additional agents or LLMs like Amazon Nova ACT through something like MCP. And we have the ability to design our own flows for these systems. Now, the most interesting piece that I think a lot of us are probably focused on when we're building these systems is around the continuous evaluation framework. Like how do we know if we're using the right LLM? How do we know if our prompt is consistent, accurate, or even optimized for the performance we're expecting? And then how do we even judge our system? How do we rate that and determine that that it's actually solving the problems that we need or intend? Now, once we have this, we need to log this information and then have some type of subject matter expert and determine how can we improve this system. And this is the iterative approach. So we're always trying to improve and optimize our agentic system. Now continuing on this continuing on with this story. Now there are some use cases that we should be building these systems for. Like if it's complex task and we don't know which tools should be used, how many tools should be used and we want the model to leverage his reason and capabilities. Well, this is a great use case for a gentic system. But if it's something that is just one step, our traditional if this then that approach is probably the best solution, right? We don't always need to provide some type of agentic system for something that can be done with a traditional solution. Now when we talk about agents on AWS, there are three approaches and perspectives we should think about. First is going to be to specialize using something like Amazon Q. How many of you are have used Amazon Q? The there's Amazon Q in the console to help solve your problems on AWS. In the console, there's Amazon Q developer inside of your IDE. And right now, one that I'm I think most excited about is Amazon QLI agent. How many of you have used that? For me, if you if you are into increasing your productivity, using a CI a CLI agent has helped me tremendously. You from editing a video, it can do that. Summarizing a document, reading my entire codebase. Like today for one of my demos, I had some code and I was trying to figure out why wasn't it working. I said, "Analyze this code and tell me what you see. Let me know the APIs that it's calling." Well, I looked up the APIs. Well, it didn't match my APIs in the API gateway. So, when the code was deployed, it wasn't deployed with the right APIs. So, the agent was able to help me save a ton of time by just analyzing the code and tell me what it saw because I never seen the code before, right? So, that's what these tools are able to um to help us do. The next is fully managed. If you're using Amazon Bedrock, you're able to leverage Amazon Bedrock agents to build and manage agents inside of AWS. And today what we're going to be focusing on is the DIY the do-it-yourself approach by using strands agents. This is allows you to not just leverage Amazon bedrock but also leverage models through other providers using light lm. Now when we talk about strands agents strands agent was announced about a month ago. I want to say something about a month ago. This is open source extremely lightweight. So if you use other agent FL frameworks, it's like that. But the implementation is you'll see in the code how easy it is to build a aentic system or a agent itself in a few lines of code and already get started. I built a multi- aent solution in about under 50 lines of code. And so when we break down strands agents, there are three components. We have a prompt, we have a LLM, and we have tools. So you create a function called let's say a get weather tool right you define your agent you give it a prompt and it's already implemented and you'll see in the code as Banjo goes through it here in a moment now taking it a step further as Danielle presented today on Amazon Nova Act these models are able to do some really cool things and this is another thing that I'm excited about Amazon Nova Act is a research preview model. And the capabilities of this allows you to use a prompt or give instructions and take complex tasks and do things like browse the internet to find research or to research or to search on Amazon.com to find the top list of widgets, right? And then return them and then add them to your cart. So you'll see how we can leverage this not just using the SDK for Amazon Nova ACT but also by leveraging MCP which leads us into the last piece which I think when we talking about agents I don't think we would be here today as fast as we have moved if it wasn't for MCP. How many of you are leveraging MCP today? Modern contest protocol. How many of you have built your own MCP servers? I built several um I got two that I use all the time. One, how many of you use Obsidian? Okay, so for my documentation, I built the Obsidian MCP server. This allows me to save all my documents, reference all my documents, and just my entire workflow is streamlined because of this MCP server I use right there. But I also use one for my bookmarks. I built the bookmark manager because every Friday I'm restarting my computer and I lose my bookmarks. I save them and I forget about them. But now I can just say save this bookmark. It gives it a description, gives it a title, give it a date and I can even add notes so I can remember where this bookmark. So now when I open up QCLI, I can say hey I'm looking on the top. I'm looking for um some information on MCP. Can you tell me all the bookmarks that I have? Then it'll find it. Can you tell me the ones I saved last week? And so these this is the power that we have today. But with that being said, I think it's time that we all start building. Banjo's going to take over. But if you you open your laptops and log on to this link, this is going to take you to a workshop environment where you have access to an Amazon account where Banjo is going to walk you through building out today's workshop. I thank you for your time. Cool. All right. So, uh, this is going to be a hands-on workshop. So, we've provisioned an AWS account for everybody here. So you don't have to install anything on your computer. Everything is going to be done through the browser. And I always say the hardest part of the workshop is just getting started. So some of my colleagues are also here. So raise your hand AWS folks that are here to support. Uh so we're going to take some time to just get logged into an environment. We're going to set up a VS Code server, enable models, uh get the Nova Act API key. So again, this is the hardest part of the workshop, just getting started. Uh so let's take some time to just get into the environment and I'll follow along as well. So, and this is uh again everything is you don't have to install anything on your computer. You don't have to use your own AWS account. Everything is provisioned for you. So, but while that's loading, let me briefly walk through the three modules of the workshop. Uh so, the workshop is really about how you can use Nova Act. So, the first module is just getting started with Nova Act. We're going to make an API call that the second part of the module is going to make an MCP server that can leverage a Nova Act. And then finally, we're going to use the strands agent to hook everything together. So that's kind of the the three steps you'll go through at this workshop and all the code is available via the link on GitHub so you can try it out on your own as well. Uh but yeah trying to get started here if you can't follow along I'm going to be doing up here so don't worry too much and again all the code is available so you can try it outline uh offline. Okay, so the first things first, uh, if you're following along, make sure to click this open AWS console button. Again, we provision the AWS account. You know, don't log into your own AWS account. Don't try to create a new one. Everything is uh previsioned here already. So, going to click clicking that button to open up your AWS account. So, logged into my AWS account. So the first thing we do in an AWS account, we're going to enable uh Amazon Bedrock models. So Amazon Bedrock think of as a serverless API to access different foundation models and you can build lots of gen applications in it. So it has capabilities like knowledge bases, guard rails, you can build agents on top of it for anything you need to build uh AI agents or geniary applications. Amazon Bedrock has capabilities for that. But for this workshop, we're just going to enable specific models. So going to enable specific models. You can click the Amazon models and we used the Claude 37, 3.5 IQ, and 3.5 sonnet. So those are the ones we're going to use for this workshop. And that's going to request access there. And again, all the instructions are also in this workshop as well. Uh, so we could follow along, but I'm just going to go through it just for sake of time. And then the next part once we get the model access, there's a VS Code server that has everything set up already. So I'm just going to go in there and if the URL and password is there, you can log in to your VS Code server with everything installed. and I'm also going to log into Amazon Q. So, Amazon Q is our U ID extends in to help you write code. U we have time you can sign up through a builder ID completely free. You don't need uh AWS account. You don't need to put in your credit card. You can just uh log in through there. I already have an account so just feed it up but it puts uh nice little AI agent there. I can ask questions, update code, etc. So it's uh I'll show you some examples of go through some of the code. So So who's gotten to this point setting up all the models workshops because this is once you get all this done then that's when the real fun begins. So does getting a pulse if I need to slow down or slow down a bit. Okay, I'll wait a bit again. raise your hand if you're stuck anywhere. Questions, we have uh agents that can come around and support you. So, I'm going to pause for a little bit. Any general questions while we're waiting? Oh, yeah. So, this workshop uh again all the code is available online. Uh this workshop available as well. So, you can also look through that. There's a website called workshops.awws. AWS and when you go there you can do something like uh Nova act and then it's the only worktop that shows up. So you can always go to workshops.Waww search nova act and this workshop will show up so you can see all the instructions all the code and run this uh on your own. Okay. And then the last thing, uh, because we're going to use Nova Act, we actually need to get a Novaact API key. So, if you go to Nova, Amazon.com, it this is a website that you can use the Amazon Nova model. So, you can do like chatting, generating images, uh, speaking with Nova, uh, generate videos, but then also this is where the the ACT API key is generated. So, if you're following along and you want to generate your key, again, it's free to log in. You can use your Amazon.com uh like when you order something on Amazon.com account to log into this and then you can just generate a key here and it'll be able to access that Oops. Okay. So, I'm going to walk through what module one is. Uh before I get has anybody got in here? Just quick pulse check. If not, you know, I'll continue. I know the Wi-Fi is slow, so it might be hard. So, I'll just continue on. Uh but yeah, the first one we got to see how Nova Act works. Uh how how the actual code looks like. Uh generated the key. uh need to export the key and then kind of running the first script which is actually going to open amazon.com uh and we're actually going to look for the first coffee maker. So let me see how that uh code looks like. Let's go here. Make this bigger. Oops. So very simple code uh with Nova Act it's again it's all on Python SDK I so I decide what a page to go to. So go to amazon.com I say I want you to search for a coffee maker. I say select the first result and I say get the title of that product page. So uh very simple if you ever done kind of web automation before of something like uh Selenium or Playright you probably have to like look for this diff tag you know look at this H1 tag grab this information. a lot of manual processes of actually inspecting the actual website. Here I'm just saying click the search bar, find something like I don't have to specify click this tag, do that. So it makes it much more easier to engage with the website as a natural human would instead of like looking through divs and trying to find this P tag specifically. So uh this is a great way to just uh you know use Nova Act right out of the box. So I'm going to uh run this so we can see examples. All right. All right. So, added my key. Going to what happens when I run this file. Give it a second. Oops, we failed. All right, let's start over. One. Ah, okay. I know. Got to run out of this. Let's start that over. Yeah, question. So just to explain why is Banjo running that command? It's running F XVFB. It's a frame buffer where it runs your X11 system. What happens there? Nova act actually goes and clicks a mouse on a browser. That's why it needs to be run like that. Otherwise, it has no guey. So this is just kind of a way to emulate um a graphical user interface on this Linux box. Thank you, Darko. Yeah, since we're running everything in the the cloud on a browser, I'm saying, you know, open a browser again, but it's already in a browser. So that's why it crashed. So I had to put that frame buffer command. Uh and yeah, the workshop kind of walks through why we did that. But you can see uh what is going on when Nova act says, I'm going to search for a coffee maker. I'm at the Amazon homepage. My task is to search for this. So it's understanding what it's doing. I see the search spark has copy maker. I'm at the search spark here and now it actually puts the actual log of the actual HTML file. So it's taking screenshots. You can see what it looks like. It got the first results. I'm on the copy maker page. It selected it. And now I got the title of the now it says, you know, what's the title of this product page? All right. Got this Black Decker 12 copy maker. my task to return the title of the product page product title. It got that and it ended the session and then it also creates a a video log that I can actually look at to see what it did for each for everything it did in this webm file. Yeah. Question. Yeah. So the question was does it reason about the page in terms of pixels or in terms of text? Yeah. So it's actually looking through the actual uh the page itself. So you see in this video it sees it looks at the page. I can see what's in the page. So it's it's a large language model train. So it can actually see the actual the page is doing. So it's not looking at like like the H1 tag or whatnot. It understands the context of that particular page. It can see that's a search box. Okay, I'm going to go click through that search box. So yes, it understands the pixel level of what's on that actual page. So this is kind of the video. It's hard to see. Make it bigger. Sped up. So, it opens the page. It goes to the is able to type in coffee maker there. Um, it gets that information, clicks the button. So, even with all the ads and everything, the video can understand the task, clicks that, and it gets the information back. So, that's and that was a couple lines of code. So, you can extrapolate to other type of workflows you can do for searching through things. Sorry, I have a and I have a question. Yeah. So when you what I have experienced with these kind of frameworks is that when you run this on a server environment um services like Cloudflare will block the access and maybe do a capture challenge. How do we solve that using Q? Yeah. So with uh so using Amazon Nova so it doesn't do captures. It doesn't do things of that nature. So it's it's meant for like workflows you understand but yes it's not going to bypass captures and other things of that nature as well. So it's made for like going to amazon.com or look through a booking site. But if something that's like requires like a human or it wants to you can't bypass that you you wouldn't use Nova Act for that use case. If you need to pass a capture of something else that use another technology this is not meant to like overtake humans, you know, it's more like I'm helping them augment things but not if there's a capture involved then you have to use a different technology for that. It's also a preview. It's also a preview. Yes. So this is a research preview as well. So if that's a very good use case, you know, leave feedback on the Nova the website. So is is human and loop possible at all with it yet? Well, with this this one, it's no because I'm writing all the code here. So but again, this is Python code. So I could probably put in something here like, you know, ask something, make an API call here. So this is, you know, it's a Python code. you might be able to create some type of uh workflow that might augment like wait for a human response or whatnot because the browser is happening in like headless mode but could you make it work with a browser to human is also seeing at the same time? Yes. So it can pause and wait for somebody put in like a password or credentials or do a capture and then once it receives that works continue on the workflow. You could do yeah because right now I I ran it in headless mode but yes it can also run uh you know it would open up the browser. If I ran this on my MacBook, I would open up a Chrome browser and go through that session. Also, if you're running it and you wanted to bypass something that has two factor, if you're already logged into say Amazon.com and then you run a code, it's going to use your credentials in that browser session to continue on to perform that task. So, that's something that you can do as well. Cool. So, let me Oops. And then one other thing you can also do multi- uh you know parallel execution. So my last my next example is actually I'm trying to find multiple monitors and I wanted to compare them all at once. So I'll show you how that code looks like so I can check for the monitor extract information. I'm setting you know I want I'm defining what I want. So again, I'm, you know, saying I want to find the price, the rating, the size. Uh, go to amazon.com. Uh, I set it headless mode this time. So I don't need to do the frame buffer. I start multiple threads. It looks for each monitor simultaneously because each of these are individual tasks. So I can paralyze them instead of waiting it to to go through. I I define the list of monitors I want to go through, start the thread, and then it starts executing and finds the the results of the monitors. So I can run that in the background. So starting the three parallel threads and it's so again it's running in headless mode so it's going to be able to do this in the background where we can see kind of what the model is thinking how it navigates through the web page. Yep. I I have tried to use Nova uh in the past April and uh it worked for the first time but once I did it again it triggered the capture. Is this something that has been already resolved or is this happening because I think the website and it was Amazon in this case it was detecting it was a bot and uh is there like an LLM.txt or robots.txt txt that can declare it. So Nova actor is a GitHub repo. So you could go there and just grab that. But it's it's working now. Like I'm running it, you know, I just I this is just live code I'm doing right now. Like uh I just exported my API key, started running it. So uh you can try it in the workshop. Yeah, I mean it's it's ready to go. We're building right now. And you can kind of see that it's going on in the background what it's doing. Uh I've looked at this monitor, the Dell monitor. I'm at the Amazon homepage. It's like it's going through looking through the search results. It's saving things. So, you can see it's running in parallel. It got the information for the one of the first ones. So, it's going as I just set that up and it can execute that. So, if you have some type of uh I don't know like daily news thing. You need to go to the website and get news or something and like have a report Nova and there's no API for that. This is one way you can encodify how to do that kind of search and get the information. Have a question. Yeah. I'm wondering so how successful is this in terms of like more ambiguous test because I I ran the Amazon demo and that worked but I'm wondering could I just add Google there and and how like how vague and sort of how much does it know when it's navigating through like I was thinking like if I wanted to return a pair of sunglasses that broke would I would I be able to just say like start in Google and then find this company's website find a way to you know engage support open a ticket like how much sort of like how vague can you be and how smart is it currently would that would that yeah I mean the more instruction you give obviously the better but it's able to understand how to navigate a website that's what the model's trained on so if you say you know go to this sunglasses website it doesn't it probably wasn't trained on a specific sunglass website but it can understand that button support you know this but click a ticket so understand kind of the the general knowledge of how to navigate the website but if there's something very intricate about that website you're going to have to encode it in the text like make sure you click button an experts or whatever. So, it understands how to navigate websites. Got it. And does it understand when it's failed? Yeah, sometime sometimes I've seen it sometimes get stuck in a loop and like, oh no, I keep scrolling. I keep scrolling. I keep scrolling. It doesn't know when to stop. So, it again, this is in research preview, so things are getting better. The model's getting updated behind the scenes, but it's not like it's not AGI. So, that's got it. And one last question. Um, h how is it in terms of navigating like distrustful parts of the internet? I mean there's a lot on the internet that we see and we know is not to be trusted or it's something not to be followed. H how have you sort of worked around that problem? Yeah because again it is a model in the background so it's going to understand like if you're doing something it's not going to want to click that or might be there safeguards in place. So that's built into the model but again uh it is in research preview. You still have to explicitly say what buttons to press for certain actions but again the model it isn't LLM trained. is going to be able to understand the nuances and say if it can't take this action or can't do that that that could happen. But I haven't seen that use case. But if you keep pushing it, maybe you'll find those those things. Well, the thing I had in my mind is like if you go to a site where you have to download a link, sometimes there's an ad that says download a link and you know that that's just an ad trying to get your attention would the model know or is that some is that like for example like in the the Amazon.com it shows an ad for something but it said find the first thing. I was able to scroll past that ad and click something. So the model understands the task you give it. So yes, it can understand that. Thank you. All right. So this this just finished. Yeah, that's really quick. It showed it was able to find all the models, give me the size, the rating, the price for each of the monitors. So again, it it executed that on parallel. It got me the nice information. And that that's kind of the idea of like it can do parallel execution in the background. So you don't have to wait for it and don't see it actually clicking through the the task and you get your information. All right, one more question then we'll move on to the MCP part. So Nova is specifically meant to be used with a browser. Correct. Uh so Nova act. So Amazon Nova is a family of models on Amazon. So if you go to this website Nova Amazon.com uh you see there are different foundation models like Nova Pro, Premiere, Light Micro. These are like the text understanding models. So like your typical LLM calls. There's also an image model called Nova Canvas can generate images. There's a video real called Nova Real where can generate uh videos uh and then it's also a speech model text speech to speech called Nova Sonic. So Nova is a foundation of found uh foundation models by Amazon to do all these type of tasks and acts as just another one for browser automation. Are there plans to expand this like beyond the browser so that we can someday take actions in Slack or IDE or anything outside of the browser? Maybe some of the team is here so maybe talk with them later. Right. Thank you. All right. So I'm going to move on to the MCP part. Banjo. Yep. Nova Act is only available in US. Yes. Right now, Nova Act is only available in the US. It's in preview, so it's just getting started. So, if you log in from like a different uh account like address like UK or something, it might not it won't work. So, it only works in the US at the moment. Yes. Right. One more question over there and then I'm going to move on. Samsung might be Oh. [Laughter] Your Amazon.com is different. I don't know. Yeah, because it is opening up a different browser. So, it could have clicked something differently. Yeah. So, yeah, that's right. Look at the video preview video playback to see what your results were. Right. Yeah. Oh, one more. Okay. One more quick quick one. Are there plans to support persisting browsing data such as cookies in the cloud browser? So right now it's opening up its own uh browser, but you can also set like your own like Chromium profile and open up that browser. So everything you have saved there like if you want to log into your stuff, you can set your own custom browser, but by default it opens up a new like completely new browser without anything saved. All right. So I want to show uh I actually made an MCP server for Nova ACT. So a module tool is going through uh MCP and I can kind of show you what I did for the MCP server. Uh in fact we can use Amazon Q here. So I'm going to ask it uh can you tell me about the Nova ACT MCP server? Tell me what it does and oops. So tell me about the Nova act MCP server. So you can see it's going through um integrates Nova act browser and MCP. It has the browse session tool, browser action, execute parallel task, take screenshots, close browser, list results. So I created these different aspects of the MTCP server. So I can use something like claw desktop or cursor or Amazon QCLI to say you know open Amazon.com and find information for me. So it's it's portable. It understands uh so I don't have to actually write code. I can say so go to amazon.com and find me the co the first coffee maker. It will actually write all that code I did in the initial one to do that or the multimonitor. So I wrote wrote a bunch of code to do this. If I just said you know get me these three monitors to get the price. it would actually write all the Nova act code it needs to do that using the MCP server. So that's kind of the power of MCP that I just describe a task and then I can it will encode the actual browse action things it needs to. So and I also made an MCP client that can actually interpret that. So oops uh it connects to the MCP server it runs the code and it's able to use query bedrock. uh I am using a model so I'm using cloud 3.5 sonnet here because I'm is an MCP client and needs to have an LM behind that and then it's able to you know understand which tools to use uh run the code and open up the browser and whatnot. So let me just run the example here. So module two. So we are open the file. Just did that. We ask Amazon Q to explain the file to us. And now we're actually going to run it. So Python 3. And then I can open this up. Okay. So, let's be adventurous. So, somebody give me a query to try since anyone has an idea. Yeah, I'm going to just ask it and do something. So, someone give me an idea of what to run another act. Fix Wi-Fi. Uh, how would you fix the Can you find a website to find fix website? can find let's see website to fix Wi-Fi use headless mode I spelled it wrong but let's see all right goes to google.com how to fix Wi-Fi problems troubleshooting guide in the box and press enter return a list of the websites title descriptions All right, it's going through that. So, it open google.com. Uh, how to fix Wi-Fi problems. I see an empty search bar where I can type queries for search information. I should type how to fix Wi-Fi problem. So, you can see it's understanding what to do. It oh, it hit a recapture page. So, okay, the search results are not viewable. Blah blah. So, so see it looks like it got stuck on a recapture page. So, this is like a headless agent. So, someone asked a question about can I pass captures? What now? You see that it's it got stuck doing that. It looks like it's stuck in a loop now. So, it sees the capture again. So, I should skip the clip button to skip the capture window. The capture is still open. So, it it's probably going to be stuck here unless I close it. So, you can see there are limitations. It's not going to pass captures and whatnot. But that that was a good query to show that it Oh, did it fill it? It's still open. So, it's going to be stuck here. So, I'm just going to close it out. But you can see, you know, it it can't pass everything. and can't navigate through websites. So something like that was will not work. So that was a great test example to show. If I use the the bakedin one, you know, find that copy m under $50, it'll be able to go through that and use headless mode. But any questions on that? Seeing how the MCP server is working. I didn't have to write code. I just said do something. It actually wrote the code to to do it for me. Question over here. Yeah. Yeah. So, a question about if I can actually go into the browser and do it myself. Yeah. If I ran this locally on my machine, it'll actually be able to it'll open up the browser and I can actually click the button and it'll continue doing that. Right now, I'm running it within the browser. So, I'm de everything in headless mode. So, we can't interact with that. So, you can see it's able to find search under $50. It can actually look at the website. It's found search results on Amazon.com. So yeah, so that for that use case where we're not passing captures is able to continue and find the information there. So a question about can I actually order something? If I used my own browser session and like logged in at to my Amazon.com account and said yes, order this for me, you know, click through, it'll be able to understand that thing. But I would have to put in I would have to use my own browser sessions like I wouldn't want to log in by myself. Yeah. A question. If you give Nova act the authentication for Amazon for example like you give it your login details then can it log in and complete that action for you? Yeah, if I if I like say this is my username, this is my password, enter that into that field and you'll be able to understand, you know, this is a signin button and I have this information. But again, this is all Python code. So yeah, you can encode it, you can make it an environment variable so it won't read it directly. So a lot of ways to do that. Does it also like understand 2FA? Let's say it asks you to go to your Gmail and you will it then open the Gmail website, check the email if you're logged in again on your session and then input it or is it and you can well if there's no capture like we just thought of the capture. Yeah. So there's no nothing blocking. So but yeah again Nova Act is free to use. So there's a lot of creativity in this room. So I think we should have like a Nova Act hackathon. I think that would be you know do something crazy with Nova Act. All right. So, one more question. Yep. One more. Can I book a flight when my price alert is less than $100? It's like a continuously check. You could probably use something else for that. But yeah, I mean, nobody can open up that website. You can just have a query every day, you know, open Google flights and look at the quickest things and if something is below this threshold, you know, send me an email. So, again, this is all a Python script. So, you can set up something that triggers like once a day like in a lambda function and so yes, totally possible. So, Novax is very flexible and because it can run in headless mode, you don't need to have that UI. So, that's really what makes it helpful for interacting with websites that don't have a native API. Thanks. Yeah, this is pretty cool. I'm a little bit confused. Like, we have the Nova SDK SDK API key and we were also doing some stuff in bedrock. Ah, yeah. So how does this actually work? Yeah. Yeah. So in the the Nova API key separate but for this MCP client I did it actually needs a large thing with model to understand what's still happening. So if I go to claude oops I actually said I'm actually using claude sonnet 3.5 for my MCP server. So that's how because I just asked it you know find that website for me. How how does it know that without any of the code doing that? So it's using a large language model underneath the hood to actually find that information. So that's where we use bedrock for trying to find it in the code but sonnet. Yeah, I set the model ID. So you're an AI system helping you have tools you're using cloud 3.5 sonnet. You're making an API call a bedrock whenever something happens. So that's where the the LLM we're using. But Nova act is separate from that. So this MC like if you're using you know claw desktop it's running an LLM inside of that to be able to understand that for the MCP server question here question. Uh the question is uh does it integrate with browser plugins as well? Like could it integrate with LastPass? If you have the LastPass plugin, fill in the credentials through LastPass and then continue. I haven't tried that. But again, it does you can set up to use your own browser. So if you do that and that's integrated, it might be able to do that and click through that. But I have not tested that, but something to try out. Thank you. And the biggest problem you would face is two factor. Like even if you gave it a password like if you're using something like Google authenticator or something that would be like the biggest problem or capture but other than that if you provide it environmental variable or if you give it instructions on how to access LastPass in the browser it should be able to do it right and uh oh one more question then we'll go on to the last module. So clearly there are a lot of different uh agent architectures you could use. Um and I can imagine using this as uh like you have a coordinator agent set up somewhere that's running in the overall app and then when something pops up and says hey you need to go and look this up online go and check it. uh it should mod so my question is how modular it I mean it's just python so it should be pretty modular right is that the way in which you're imagining the architecture to be is just if I was coding a coordinator agent in lang chain or lang graph for example it would then call your sub agent and get and and run its stuff and then get and then get a textbased output that I throw into my message queue that's how it all integrates together is that right Yeah, that's one way you can do it. So, Nova act again, right? It's just Python. So, it could be a tool, it could be an API call. And the next module, we're actually going to show you how to actually make an agent from that. So, good good tea app right here. Uh, so Dan talked about the strands uh at the beginning. So, strands is a new agentic framework launched by uh AWS. So, let me open up the link. Uh, it's easy as a pip install strands and the first agent is like agent equals that. So it's very it's a model first uh way of interacting with agents. If you use a lot of agent frameworks in the past, there's a lot of bootstrapping and making sure everything is correct and like but that was necessary for kind of the older models like if you think back to like like Llama 2 for example, like how how far models have evolved since then. So but now we we can pass a lot of the you know bootstrapping we did previously. The agent can figure that out. So we don't need all these very uh heavy weights and like you know make sure everything's typed and every so whatnot. So here's a very simple example of how I actually spun up uh and also it has MCP native support. So in this example I actually have two MCP servers. Uh I have the AWS documentation and AWS diagrams MCP server. So if you go to this like AWS labs MCP, these are their official um AWS MCP servers and there's a bunch of different ones from like a cost analysis, Nova Canvas, diagramming, cloud form, uh lots of different ones here. Uh so again, it's all on GitHub, AWS Labs, MCP, but the example I do here is I'm actually uh I made like a solutions architect agent. Your role is to help customers understand is building on AWS. And I define these two MCP servers here. I give it the prompt and I say this agent has all the tools in the MCP server. It has a bedrock model. I'm using claude haiku here. And what's cool about strand is it can also use like light lm and o lama. So it has access to launch of different things or you can run it locally and of course it has access to Amazon bedrock. So that's what we're using here. So all those three things makes the agent, the tools, the model and the system prompt. And then I can say uh get the documentation for AWS Lambda and create a diagram of a website that uses Lambda. So let me run this code. CD. Okay. Okay, so it uses UV to install the MCP server locally. A lot of people I where does MCP run. This is running locally, but there are other ways to run it like in a lambda function and whatnot. But for just testing it out, it pulls down the the MCP server locally and runs it. And you can see it's already executing. So let's make this a bit bigger. Uh so it says, okay, I'm going to help you with that. First, I'm going to search the AWS Lambda documentation. uh read the documentation, then I'll create a diagram illustrating a static site. So you can see it does a post request to do the search. So the MCP server defines where everything is. I don't have to like feed it in the well architected framework. The AWS documentation is always updated. So it just knows called the search function. It got the Lambda welcome file. It it put that in. It's able to generate the diagram. It it generates the diagram. It tells us what is going on, how the workflow looks like. It tells me it saved the diagram to this location. I can open it up. Generated diagrams. Oops. And oh, it's very small. Let me see if I can make this bigger. There you go. So, it was able to generate the diagram for me. So, all through that about uh you know 40 lines of code. I have two MCP servers. I have my prompt and it's able to understand that get that and just generate something for me with that. Uh so that's very easy to get started with strands of building a agentic workflows. I know agent means a lot of different things to different people but you know you have tools the model the system prompt do some type of action and strands makes it extremely easy to do that. If I use other frameworks it could be a lot more code to do something like that especially integrating MCP natively like that. I'm going to pause here for any strands questions. It's coming. Um I know Bedrock already had it kind of agents SDK. So is strands replacing that or is this now the is this replacing that or is it supposed to complement that? Like is this the preferred way of creating agents with models in bedrock? Yeah. Well, when it comes to preferred way, it always comes down to your use case. So the bedrock agent has a lot more I guess opinionated ways to do things. It's you can do it through the console. It has built-in support right there in AWS. Well, strand is more as an open source framework. So you can download the code, you can use other models through that like light lama. If you use bedrock agent, you can't run that offline. So there's different use cases, different developer tooling. I mean me as a software engineer, I like you know code first doing things. So it does depend on your use case, what you're trying to do in your experience. Can can you show the code real quick? Yeah. Yeah, this is the code. Yeah, just show the agent. So, this is an open source framework. If you go where it says agent, you and it says model. Right now, we're using a bedrock model, but you can use another model with light LLM. Yep. So, you don't need AWS at all in that instance. Right. Yeah. So there's documentation anthropic lightm uh lot of different model providers lama open aai. So it's an open source framework so you can use it whatever you want. So but yeah that's the idea with strand open source model agent development kit. One question suppose I want to build a tax to SQL agent and I have um say 15 tools already built in that I want this agent to be able to use. If I use this framework, um, how can I make sure that the agent know when to use the right tool and the sequence? Yeah, great question. Uh, so I didn't this example I have a weather agent. So one thing you said you already have tools. What I like about strange a lot is I can write a Python function I already have and let's put this tool decorator and that's it. You know, you don't have to put anything else. it understands this is the uh what you need to do and then when I'm going to that agent I have this tools and it has put in the the native tools we're going to be using http request is a as a standard tool in the strands framework so in this example I'm like asking what is the weather in Seattle and then also how many words are in this response uh this open API uh API weather.gov gov where you don't need an API key and it can find the information for you. So, I'm gonna just update this San Francisco and this show wrong, but it's a figure it out. Weather example, weather word count. And I was very specific, you know, find the weather first and then how many words are in the response. So, it's able to use that tool. It gets the forecast and then it knows to use that word count tool next. So, we're passing a lot of the information to the model. The models are very smart now. We don't have to say do this, do this, do this. The let the agent figure it out. That's kind of the goal of the agent. You give it the context and the tools necessary, it figures out the best way to solve the problem. But then wouldn't it be prone to hallucination when you give it 20 tools and then because we've tried that with AWS bar know the similar things when you bind more I think more than 10 tools it's going to sure there's always you know a balance but I again the models are much better like try using claw force on it. Is it hallucinating as much? Like these newer models are much better for understanding the concept and understanding what tools when. The older models sure they get confused. There's so many things. But I'm very confident on these newer models they can understand your use case and what tools available and figure out the best way to solve the problem. So then with this framework there wouldn't be a way for you to orchestrate a customized flow but more like you give the control to the agent. You could if you want to have like specific like do this specific way uh there are different ways in strands uh with something called workflow mode where you actually say uh you know this is the workflow I want to do research results analyze things write a final report if you have to do something very sequential a strands has that I won't have time to go through all the different you know ways to do multi- aent collaboration and whatnot but this for that particular like I wanted to do xyz first the workflow way can do that. So yes, then is it possible say um I I don't have a predefined workflow but I know it needs to figure out the right workflow then then that's what I just did there. You know I just gave it a sentence and figured it out. I see. I see. Okay, perfect. Thank you on it but um Cloud 4 has something called interle thinking. I believe that's what it's called where it can handle multiple tools processing much better than most models today. So if you're passing in 20 tools, it's able to work through the agentic loop to really figure out which tool to run. And it's also able to run parallel tool calls. So rather than just say, okay, here's the objective, let me run this tool. It can say here's the objective, let me run this tool, this tool, this tool, then this tool, and then process the results and determine what needs to happen next. So I would try a cloud for which he like Banjo mentioned. Then last example really quick. Uh again you know strands I made my Nova act MCP server and it can actually run that you know I define this is the MCP server use the Nova MCP you know use the cloud. So same type of thing I can have another agent you know use uh nova act as well. Uh so strands make it very easy to build these agentic workflows. Uh so that's really really enjoy the the developer experience of using strands and you know I already have the MCP server. We see the same exact example before. So once you have the MCP server, it's very easy to plug in into different uh architectures and strands makes it very easy to to accept that. Uh but yeah, those were the three modules really about how to use strands. Uh MCP then Amazon Nova ACT. Again, uh Strand is open source. You can download it pip install strands. Uh if you just type strandagents.com, it'll take you to the documentation. again also Nova act nova amazon.com it's free and log in and then think that's all the time we have but we do have a a survey uh and you can get AWS credit code by filling out this survey so I I have a question about that workflow thing in uh strands when you create these individual agents can you define which tools are passed on to each agents yeah yeah it's a great question Dark about different agents we're running out of time but I'll quickly show uh I have a multi- aent example I believe. Oh I think you had it in the docs. Yeah. Yeah, it's in the docs. Yeah. Yeah. Yeah. Each of these is a different agent. So you know this is an agent. You can have a different system prompt. You can have different tools. So you're just defining the agent and then yeah you can have different tools, different whatever there different models and then the workflow would just call that. So yes, completely customizable. So that's the good thing about Strand. It's very easy to customize and build scalable solutions like that. Thank you. And then again, uh here's the survey. You can get AWS credits for filling out this thing. Tell us how we did, what you liked, what you want to learn more. And now go build. [Applause] Yeah. Any other questions while we wait? I think we have a minute. Thanks for the presentation. Um so as these systems develop I think that it's reasonable to assume that um they would emerge as an increasingly effective vehicle for committing fraud online at scale which would push businesses to implement uh more things like capture which kind of decreases the surface area that tools like this would be applicable. So what is the long-term strategy for that? Well, you already saw we failed to capture today. Like, you know, we're not trying to b capture. We're not trying to break things. You know, a responsible AI is very important to Amazon. So, no, we're not trying to let this tool commit fraud. You know, you have to have an API key, so it could be monitored. So, use cases like that will be shut down. We think we're done. Yeah. So, thank you all. I think it's finished. Oh, we can keep going. We have more time. Oh, the clock the clock ran out. So, I thought we were kicked out. All right. Well, more questions then, I guess. I thought Yeah, another question. Um, so regarding Nova Act, let's say that I have a headless browser in the cloud. Is there a way to connect Nova act to my custom browser instance in the cloud? Yeah. Yeah. Yeah. You can there's a way to like put your own browser instance. So yeah, Nova supports that. So possible. Yeah. Thanks. Let me go to Novak GitHub page. And just some examples there. So yeah, there's a way to set up your own user agent for Nova app. Definitely possible. Questions. Yeah. Yeah. All right. Well, apparently I have still more time. So, I don't know if anyone actually got into the workshop. So, we can still uh build some stuff or I can try some other examples. Try to make Nova act. I tried to make a stream app with Nova Ax. So, we can try if that works. Oops. So, one example I tried, I tried to make a Streamllet app that uh look for like the top five uh PlayStation games on game FAQs and then create an image like a nice graph for me, but it it can fail. So, uh I think that's one of the issues there. I think it failed at one of the steps there. Uh let's see. Oh, that Nova app got an error. So, it couldn't navigate game faqs.com. So, it does it does fail at some of the things. So, that's you know, again, research preview. You have to be more specific on how it goes through things. Uh, but yeah, let me show you where the the code is just so you can have an example. Let me pull up the code. Yeah, let me try let me set up my local machine so we can see how it works. Yeah. Oh, yeah. Go for it. How much does Nova act depend on like uh semantic HTML and like good web design to actually work? I mean it understands the actual page so it can click through those things. But if the if the page like doesn't have like a search box or button and not be able to navigate. So as long as the p it can see the page, understand where to click and then click those correct buttons. So maybe a follow is there any like efforts to do like experimental like engagement on the page? So if it comes on a page that it's not familiar with, maybe it would try and act like a human would to like click on things or try things out depending what you you put in that prompt because again you're creating that workflow what it should do. So if you say, you know, explore this website and find things, it will it'll try to click through that. But again, it's up to kind of what that initial prompt is that you have for it. Yeah. When you're using overact, you're kind of giving it step-by-step instructions when you're using the SDK. So that way, if you kind of know it's an obscure website, you can give it those instructions that it need to perform rather than the MCP server um is using natural language to infer what needs to be done. So it's not specific instructions coming from you unless you provide it. Yeah. So, I'm going to run it locally on my machine just to show an example. Uh, let's see. Oh, let me hide my key for a second because it's been recorded. Python get coffee. Thanks for coming. All right. So, I'm just running it locally on my machine. So, without headless mode, so you can see it opens up the browser. It's able to type coffee maker. So what we're looking at now is not in headless mode. This is actually Nova act actually performing the task in a browser. So yeah a lot of questions about how does it work you know and we can try more complicated examples. I just wanted to show it could work on your machine and you can see the log. You know, I'm looking for and if I like change the page while it's doing something, it's going to like mess up. So, I'm going to click the page and see what it does. Like, so someone asked about click things of that nature. What's it going to do now? So see it crashed now because I brought I changed a different page didn't know what to do. So example you can interact with it when it's going through the motion as well. And then I believe I have an uh can the MCP server I set up a cloud instance. Oops. And then I have a my Nova act MCP server is there. So I'm able to actually you know I click this you can see all the tools it has available. So I can ask it to like navigate a website. So uh anyone have a complex example? You can see the MCP server. So I know some people have been asking some complex examples. So get go ahead and give me one here. You got you got one. You can try it. Do you have a specific website that has like drag and drop? Draw.io. Uh, let's go to draw.io. io and make a cool diagram. Use Nova act. Let's see what happens. All right. So, let's go to draw IO. All right. It opened the page. Do I have to accept something? Nope. It's going. Oops. All right. Open dry.io. Let's see. Make this smaller. Wait for page to load. Look at my initial setup for template selections. All right, it's going. Uh. Oh, it crashed. What happened? Oh, do I have to allow allow always? Oh, it took a screenshot. I need to continue the browser session to see what's available. Let's look at the screenshot. All right, it's opening up again. Uh, it's going to draw.io. Yeah, if I keep clicking away, it clicks back to the di the browser session. So, I need like two monitors. See, is it going to figure out how to use draw io? Wait for pay. Take screenshot. Look for template options. Come with blank pay. All right. It's so it's kind of I didn't give it any specific instructions. I just said make something cool. So maybe that's too hard to interpret for this website. Maybe I have to say click this click the square button and then drag the square to the center or something. I might have to been more explicit for that. It seems it seems to have frozen. All right, it's clicking something. All right, click new. Oh, okay. Hey, it's doing stuff again. It's not like super real time. It's going. It's not like instantaneously, but it it's it is clicking through the buttons, clicking through stuff. All right. Did it do anything? Oh, the CL. So, it looks like it fa So, yeah, looks like Claude failed that one. So, I won't blame Nova for that. But that's the that's the idea. So, thanks for trying to do something hard. All right, another question back there. Oh, yeah. Can we can Can we try another one? Yeah, let's try another one. Sure. Can we do um you know on Google Maps, find the top three rated coffee shops with within a mile radius of this hotel. Top three coffee shops shops near the Marriott Marquees in San Francisco. You'll figure it out. All right. Open Maps Google. Search Mary Marque San Francisco. Wait for results to load. So, it has a plan. It's going to do something. So, let's see. It opened Google Maps. All right. Type MQ San Francisco. So, it's able to type that. Okay. It searched. It found the Marquee. So, there's a copy button. Let's see if it clicks that. I'm curious. Looks like it's frozen. Give it a couple more seconds. What did it click? It got this 15 minutes. I was trying to type in that box. Okay. All right. Just type in coffee shops. All right. All right. It's going. All right. So, all right. It'll open the coffee shops and let's see if we can get those top three. There's a 48 47 another 47. Let's see if it can get that. Did it crash? I think it did it, but I think I'm going to blame Claude. Cloud desktop crashes. might need a zip MCP client. Uh yeah, I think yeah, I think Claude Desktop doesn't like doing that. But again, because it's an MCP server, I can open up a different MCP client. So I can open like cursor, for example, and ask it questions through that cursor. Let me close this. And then you see it has the MCP tools. Oops, it has this up. Let me just open up a new one. I can do the same thing and use Nova act and then it's calling the MCP tool again. So that's the beauty of MCP. I already have this server. I can just use a different client. It can understand all the information it needs to and do the exact same command. So it's going to do the same thing. cursor might be smarter than cloud code. But yeah, it's able to do the exact same type of thing. So a question over here. Yeah, I just got a question. Yeah. Yes. So Novak question was where is Novak running? And yes, it's running in the cloud. So yeah, it's just you get that API key and it's doing the call behind the scenes in AWS cloud. Yeah. So then what what does it upload to the cloud? Well, it's asking the the questions and like you know go to Google Maps and then they say I understand that and it's actually clicking those buttons and doing the actions. So the the actual uh intent of what you're trying to do in the specific action and if I was using it locally, you couldn't use Nova act locally. It has to be uh connected to the internet to use it. Okay. But if I for example if I wanted to look my Yes. Ah yeah I I see what you're saying. Yeah. Yeah. If you I mean it is you know it's a API endpoint. It's been passed to AWS. So you know only pass information that you feel like it's not going to be we're not training the data or taking any of that nature but it's going to the AWS cloud and processing you know what to click on this button locally on your like browser. So looks like it's not. Yeah. See, now it's even certain the rating. It actually knows which rating to press. So So the Nova act is going to just give the plan, right? Yeah. Yeah. Well, when Nova act is is executing like in this MCP server example, I say, you know, find the top three copy stops in Marriott near the Marriott marquee and then I'm passing that information to the the LLM to understand that plan and then it uses Nova act to interact with the browser because like cursor or cloud code or Amazon Q, they can't interact with the specific uh you know website by itself. It uses it uses Nova act to do that, right? But like given a question though like how how does it come uh come up with a plan? Oh the MCP server like the the client so I picked the model in the example we had the MCP client we had this we showed the model I don't use cloud 3.5 that's coming up with the plan same thing here you know I asked you know help me find the top three copies of native Mario marquee this the model that uh cursor is using is coming up with that plan and then I'm using the nova act mcp server to act on it. Exactly. So this is the plan. Search for Mary Marquee. Click the mirror marquee you know search for the things and you see all this information Nova act returned and it actually it returned this time. So I think the problem was with claw desktop but it got the three top three copy stops there. Right. What are all the tools that uh Novaact can do today. Uh so the MCP server is what I wrote. So uh but the idea between Nova act it can interface with the web browser that that's the tool. The browser is the tool and it can anything that on the website can actually click through, go through the example, etc. I see. You got the repo. Do you got an architecture that shows the MCP just so they can see it? Yeah. So, I mentioned uh there's an official AWS MCP servers. So, uh this AWS Labs MCP and a lot of different um MCP servers here. For the one, the Nova Act one, I created my own one. uh go back to the nova act examples or where do the ah here when I use amazon to explain you know the am the mcp server for like what what's going on what tool was the browser session performing an action on the browser so this is a good uh thing to talk about so can you dive deeper on the browser action function and then we can see because this is how it's actually acting So, uh, Amazon Q browser action is designed to perform actions. It has this, uh, what's cool about it, it just does, oops, let's go into the code. It performs a single action in the Nova act browser. So, it's executing that action. It stores this act. act is like what Nova says you know click the search bar do this XY you know why the MCP client understands how to use this act that passes the correct action so we saw the example here one of the actions was like go to Google maps or click this button or do that search that's how it's able you know these actions and then the nova act MCP server is translating that to actually click that button so the MCP server provides all the interfaces it necessarily needs So then these MCP clients can interact and do actions and do things. Yeah. And Nova act is just the model in the background that's able to click those buttons. Extending this question, it so your MCP server so claw uh or um cursor running locally, right? It's calling your MCP server that's also running locally. Is your MCP and your MCP server is the one that spun up the I guess the Chromium instance, right? Is it is your MCP server taking screenshots of what you see in Chromium and shipping them to Nova to Nova Act? The screenshots are locally and then based on that like you can see it's actually getting all the information uh the final page information. So it's not storing your screenshot data and sending that everything that it's running locally and it's clicking those buttons based on what's on the browser sensing. Got it. But is is any of any of the information in Chromium does that any of that need to be sent into any form? Everything running Yes. running locally. I have the distinction. Okay, perfect. Thank you. And let me open up the Where's that looking? So one of the things about making MCP servers is you have to provide a lot of context. So uh for no act like I say you know when writing action for no action be descriptive of what to do you know click the hamburger menu icon go to order history don't find my order. So the more you know uh concise and prescriptive what you want to do it's better you know search for hotels in Houston sort by average customer like so the better specific it is uh that's how the MCP uh client is able to make those great requests and find the information so type coffee maker search block enter so so the more prescriptive you are of nova act the better results you're going to be and I encoded that all into this uh MCP server so the clients can leverage that so I think that's Probably one of the hardest things about making the MCP servers that's making sure you provide a next context of when to use the tool, how to use the tool, the inputs and outputs. But once you solve all that, it's very easy to plug and play to different MCP clients like we've done here. question. Yeah. Right. So when Nova act is doing something, it's passing back the log of everything it's doing. So you know what what steps it did. So the starting page, the act the results, the action result ID. So it's keeping a log of everything it did. Uh power. So it's able to get that JSON to understand what the ID what the result is. So you can see what it's doing so it can move on to the next step. Yep. Make this bigger. A question. Sorry, a quick question. Yeah. Is this able to do uh like uh automated UI testing because of this? Well, with Nova, you know, you can define like what you want it to do. So, you're going to have to define, you know, go to this button, click this, does this work? So, you can define that workflow. So I mentioned before like back in the day like if I'm writing selenium code I have to go click this H1 tag do this like now you can just write in natural language you know click this button click that button so yes it can handle that use case uh specifically of like opening the browser checking these things and but you have to like you know this nova act search for coffee maker you know you have you specifically have to write what buttons to press. Thank you. See, guess if we have time, I can show some multi- aent collaboration with strands. That could be something cool. Uh, I think I have a repo for that. So, should be uh go to the AWS labs page. Where's that work? and then claude. Cool. Okay, I'm just going to copy this code and put it into our environment. So in this example, I'm actually going to show how strand says multi- aent collaboration. So one uh way I'm actually going to create a PowerPoint presentation based on uh you know a cloud migration request. I want to like move my u infrastructure on premise to the cloud. give me a presentation of how I would do that. And so for this, I created three different agents. I created a cost analysis agent. So I have a system prompt there, a solutions architect agent to map out what you're going to be doing. And then each of these uh tools is an actual agent. So this uh costbus has the docs MCP server, the cost analysis MCP server. It has its own prompt. The presentation agent has its own system prompt. It has a tool from there's a a PowerPoint MCP server that I'm using and then there's an architecture agent that also has you know its own specific tools system prompt etc. So uh different agents for different uh things in the workflow and then I have this orchestrator agent what I've called the migration orchestration agent. It has a prompt. I tell it what tools it has access to. And then the cool thing with strands is I make this orchestrator agent and then the tools or this other agents in that. So it knows when to call this agent for this particular tool when to do that and I say you know I want to migrate my work my uh workload. So write the right tools to find that. So I made a fictional company called shop easy e-commerce. They have onremise Java MySQL database. I want to zero down from migration like all this all these little constraints in there and I wanted to make a migration plan and a PowerPoint presentation that I can present to my executives of how this would work and I just assigned and I'm the orchestrator agent will find out what to do. I don't specifically say do this one first, do that first. We'll let the the agent figure that out. So let me run that strands and it should be multi- aent right so cloud partition agent as tools all right again so all the MCP server is running locally it downloads it's using the UX it start with the architecture design first generates a diagram going to use W. So take some time. It might fail but it would just update update itself. Making another judgment. All right. Think it couldn't generate the diagram there, but it's saying all right. That's going to this is what the diagram should have. This is what we're going to doing. Now it's going to do a cost analysis cost analysis on based of the things we did there. So it's it's a this workflow takes maybe a couple minutes to run. But you can see it's calling all these agents uh different things. It's understanding what to do, what actions to take first. It's finding pricing for EKS because it has the uh cost analysis tool and knows where to find that information. So it has the up-to-date pricing all the time finding for Aurora for its database. So it's able to understand all that information and get real time up-to-date information just because we have that uh pricing MCP server from the AWS labs example pricing is it oh cost analysis. Yeah, cost analysis, MCP server documentation, all the stuff you need for finding the right price on AWS. It has all that information and the agent was able to just use that once it's going to generate a report. So, it's still running. Again, this does take a while because I'm asked a very complex question, a lot of things going. Uh, so it does take a couple minutes to run through all that. It gets it monthly spend predictions, monthly savings, etc. So, it's able to understand all the information and get all up-to-date information based on the plan we've provided. And the last thing now wants to create an executive presentation. So, download the PowerPoint MCP server and now it's going to make a PowerPoint presentation based on that. So, adding the title slide. So, you know, add a placeholder. So generating powerpoints is a very popular use case and there's an MCP server that can go ahead and just do that add bullet points etc. So give it a couple another minute or