Développer avec Claude sur Google Cloud

Hello everyone. Thank you for being uh for being here today. I'm pretty much excited to have uh this session with you. I know we are almost at the end of the event. So thank you for bear with us. So just to start let me to introduce myself. I'm Nardini. I'm a developer advocate at Google Cloud working on building content in partnership with Antropic. And um in order to start this presentation today, I just want to ask a very simple uh a very simple question. So how many of you in the last week use any tool uh to code or build application? Okay, the majority. Um how many of you use the same AI tool to build and deploy application on Google cloud? Yeah, just a few of them. So the the goal here today is just try to make it better. So in these uh in this demo what I'm going to show you is uh how you can use cloud on Google cloud to build and uh deploy application end to end and in order to do that I'm going to wear five different uh hats and uh we will start from um imagine the use case right imagine the scenario you are an enterprise context in an enterprise context you probably have a team like the one that we are visualizing here that um it's engaged to build a new feature or a new product. So starting from the left, you probably have a PM. Uh some of you in this room are PMs and u the PM might have an idea of how to improve a particular product or how to implement a feature. And starting from this idea, he shared this idea with a UIUX design which allows him to design the idea to visualize the idea. And uh after the idea start getting a shape then uh the idea is sent to a software engineer that essentially start developing the core logic uh behind this idea in order to ship and make the application accessible or the feature the future feature accessible to everyone. And uh but before to ship it, in order to be confident on what you are releasing, you probably have to pass a security review. So that's why you have a a role like the security engineer that will allows you to be confident in the release. And finally, once the application gets uh released, um you probably have a data persona like a grow marketer or a data analyst that analyze uh the data that are collect through the app in order to generates insight and produce feedback to the PM um in a way that the product or the feature itself gets uh improved. So these are kind of uh you know all the personas that in a simple way we can imagine are involved in uh the software development life cycle. Now with respect to these personas uh claw code the entropics coding agent augment all of them providing several components that we are going to use uh today. So as I said in the uh for the remaining part of this presentation I'm going to put the hat of all these personas and going to show you how you can use these uh clock components together with a cloud on Google cloud in order to ship build and ship a very simple feedback application that at the end of the presentation we're going to use to rate uh my my performance here. But before to start building uh of course you need to uh set up and the uh cl code that we are going to use and uh I'm so excited and so proud that we work together with entropic to make this process of setting up cloud code in order to use model on Google cloud in a very simple way in a very straightforward way. So you have multiple methods to use cloud models on Google cloud in code code. But the simplest one, the faster one is using the application default credential which uh automatically f finds uh your credential for example the user one and based on the environment that you're going to use and uh as you can see in this representation recently cloud code also introduced this wizard that will simply allows you to uh detect your project and your region where the models are served and um uh check which models are available in your project and uh like let uh you to pin them in order to start building your application. At this point like probably you are familiar with this and you're wondering okay but what's it what is different to use just cloud code with the with the cloud models why using cloud on GCP on Google cloud. So there are many reason why you want to do why you want to do this. So first of all because you pay for what you use. So the the usage of cloud models on Google cloud is per token. So you don't receive a message uh message cap and also if you're building uh enterprise application that needs to go uh to production you can always access to what is called provisioning throughput which essentially will reserve some uh um uh throughput for you in order to build this kind of application. Um the other important reason why you want to consider uh like cloud on Google cloud is as I said the setup is pretty straightforward using the uh the ADC you don't have API to rotate or uh you know uh environment variable to set in some sense so it's a it's a epic journey in uh in with respect to this aspect uh you can access model in your project uh with your own uh um you know policies set and uh also like the data stays in your project while you are interacting with the clock code and model are served in multiple region. So you have global endpoint, you have a regional endpoint depending on you know the availability that you that you need and as a Google cloud talking about availability we have very great uh availability service that standards that will allows you to uh use cloud and on one of the most performing infrastructure that you can find in the in the market. So these are all some of the main reason why you want to consider cloud on on Google cloud especially in an enterprise contest. So now that you have uh like few reasons of why using cloud on Google cloud we are ready to uh build and so as I said I will start wearing the hat of a PM. So imagine that you just joined uh the company or maybe you're already part of the company. You have um you you want to improve a services. You want to implement a new uh features uh with respect to a particular product. What it was happening in the past is that you have the idea you go to a UIUX designer and you ask him to prototype and visualize the idea. Now with the with the cloud and co all you you what you can do is just uh uh drawing a picture like the one that you see uh here while you're drinking a coffee maybe in San Francisco and then let uh Claude doing um implementing the idea for you. So let's see this uh in action. So this is a the code UI like you will probably familiar with that and you are familiar with the cloud MD which is essentially gives some instruction here we just say um that we are a PM we want to uh we want to have a starting from the picture we want to render uh a prototype of uh the app the wireframe that we are going to then use and pass to the UX designer and in few minutes you can see how cloud was capable of rendering it and u just starting from a very simple uh picture or drawing that you you uh did while you were drinking your coffee. So pretty pretty straightforward but imagine uh how much time you save in doing this because compared to what you were doing in the past with the back and forth uh to in order to get this first prototype of your idea. Okay. So at this point the PM gives uh like creates a prototypes and pass these prototypes to the UIUX uh developer and at this point he needs to implement a more solid uh interface in order to use it in uh in production. So in in this particular use case what we want to create it's at least three like uh pages from the landing to the thanking um message like message page and a dashboard that will allow me to show you in the real time what can be the feedback that I will receive from the room. So in this case there are many ways you can uh you can implement this but in this case I want to use an additional capabilities of code which is uh the plan mode. So with the plan mode what we do we put claude in a mode where it thinks uh before to um like it thinks and propose what he's going to do before to implement uh any code and this is very important because it gives me like a degree of freedom of deciding to change something bas according to my preference or according to some standard that probably I will get access through an MCP server using uh Figma for example. So now that we have uh in mind what we're going to build, let's see this in action as well. So we started from uh the wireframe from the PM similar prompt. I enabled the plan uh the plan mode. And so as you can see compared to before um in this case I'm simulating the receiving some instruction from Figma using a design doc. But as you can see compared to before he creates a plan of what it's going to do with respect to all the components that are defined in the slide. We look at them we are happy we accept and co code will implement all of them and at the end what we get is uh this uh optimized version. So as you can see we start from here and we get this very very straightforward but you can see how we are shifting from a prototype to something that can be used uh in this session in a very simple way. Okay. So this is the part that probably every view every of you in this room like you do every day, right? Uh let's uh let's wear the third hat which is the one of the software engineer and uh the software engineer you receive this front end like all the components that I was sharing you before and uh maybe it doesn't know anything as probably uh some of you in this room it doesn't know how to deploy this application on Google cloud right so how you can how you can do that, how you can you know uh hand to have this a clear picture of what are the components on Google cloud that you need to use in order to deploy a very simple application like the one that uh I show you today. Luckily, it's not a problem because as a Google cloud, we invest a lot of time to integrate with this large uh by coding ecosystem that now is um growing around u models and uh we have we in the last few months we released two um important components. So the first one is uh the developer knowledge API with this with uh the associated MCP server and the second one is the Google call skills. So with the knowledge uh with the developer knowledge API you get access to the a fresh documentation from Google cloud that can be directly consuming cloud code uh through the MCP server and it will help cloud code to figure it out what is the best uh architecture what is the best implementation uh to deploy a certain application on Google cloud this is very important because again what what we are saying here is that you don't need to know uh like how to deploy deploy an application on Google cloud you can just leverage cloud code and this MCP server that we expose now on on Google cloud side to build application like this one. So in this case uh probably what we want we are going to do is that we are going to deploy the feedback API on a serverless function like a cloud run. We will connect with a web um oriented DB like a fire store to cor to to collect the row responses that we we will give through the feedback app. And then because we want to have that data analytics part, we will uh build the uh implementation in a way that we can store those row response in an analytical data warehouse like BigQuery. And we in bequery we will postprocess and we consume this information in a dashboard uh in a in a in a dashboard like the one that you can find in uh in Lucer. But again it you you can build this using a um a co code in combination with the MCP server without kn without you having a prior knowledge of how to do that. this like the MCP server and the uh developer knowledge API that I just mentioned it got paired with also the skill part and the skill part is if with the MCP server you will be able to design the architecture with the skills you will be able to cover the single blocks of this architecture. For example, we release a a s a simple skills that um enable cloud to deploy uh on cloud run to deploy an API on cloud run or uh to connect like uh cloud run with fire store. So it's more about uh the implementation itself rather than you know giving the overall picture. So once you get cloud code enabled with the the MCP server uh with of the documentation and the skills that I just mentioned you can just directly implement uh the architecture that I was showing you before and you can do this in parallel. So another components that you can use in co code is a sub aents and as you can see here we are going to spin up three different sub aents one for the API one for the ingestion pipeline and the other one for the dashboard and you can parallelize the implementation of each of these components just like you run a team uh a team sprint uh in the in your normal like usual development uh life cycle. So let's see this in action as well. So here we are again. Uh first of all I just want to show you that we have enabled the MCP server of the documentation and we have the skills some of the skills that we pre-built one one time more I provide a very simple prompt. The first step is designing the cloud native back end. So it will uh start like it will provide me um uh draft of the architecture. In this case, I could use again the plan mode, but for simplicity, I didn't. And then you use the skill, one of the skill that I provide in order to implement the API. Let's say that we are happy with the API spec. Then we have the architecture, we have the API spec. The next step is running multiple uh agents in parallel in order to implement the three uh the three components of the app that I was showing you. So it's uh it's pretty quick as you know this code uh like you also manage the testing part one after you finish the implementation and at the end you will get your u your app which is now uh ready to uh deploy on Google cloud. Okay. So at this point uh we have uh we have the code of the app uh that is ready to be deployed but because we are deploying on cloud and we want to open this up to a larger audience we want to deploy it in a conf confidently like uh so this is uh this is when you want to consider to run a security review. Now depending on uh your company uh you can uh you can have different security requirements. So for example, you may want to check if your uh application is solid with respect to the most uh common uh OASP issue uh or because you are deploying this application on cloud and one one thing that you need to consider is probably you will use what is called a service account and you want to limit um the the service account when it calls a particular API like the one related to reading and writing DB with respect to certain role. So you are you you're sure that you are limiting what it can happen when uh when the application run some operation on the on the cloud itself. So again these are just a couple of examples of um uh what you want to consider in a uh phase like this one. And of course this representation is a strong simplification of what can happen in the in the real life. Um it's just one of the possible scenario uh that you can have and you can see why is also a simplification because we are letting the security engineer not only to approve if the app is uh secure enough to be deployed but it will also deploy the app in this case but again this is just a demo so we have this degree of freedom. With that being said let's run the final demo and let's uh get the app uh running. So in this case as you can see I use a pre-built security review that you can find in co code very simple um very simple prompt also in this case and what is happening is coco run the first test essentially he double check that uh everything is aligned he found like a possible issue and he automatically fix it so in a way that the app now is secure and once it is secure it deployed the back the back end API and it deploy the API itself. So what we get at the end of this it's an endpoint with our app. The app is live. So I will uh quickly unlock my laptop and I will ask the backstage to share on my laptop. So the uh the app as you can see is up and running on GCP. Uh for people that doesn't know GCP this is cloud run is a serverless uh ser uh service that you can use in order to deploy app and uh the app at the end looks like this one. So if you remember I show you the original uh I show you the feedback uh frame at the beginning. So what we can do now live I can just give me a score. What do you think the session is going so far? Give me >> five. >> Five. Oh okay. Thank you man. I really appreciate that. Okay. Cool session. Let's be uh let's be simple. I submit and then uh in real time it updates the number of response the score and u you know the visualization. And also just for fun I build a feedback analyzer. So once I click this it will uh run it will call uh clock code uh cloud on Google cloud and uh based on the feedback and the comments that you send it will generate this uh this summary. So pretty pretty straightforward. I will ask to go back on the presentation. Thank you. Okay. So at this point we have the app. We collect uh we collect uh good feedback. Thank you again man. Uh but the development life cycle is still there. Uh we have the last step to cover which is essentially people they are start uh using our app. If you saw one of the KPI that I had on the dashboard was the time the response time. So how long is uh was taking you to just in uh uh like providing a feedback. So these are the kind of information that you can use in order uh to like through this data uh you can collect this data analyze them and generate uh insights in a way that they can be used in order to improve uh the uh application. Now running u if you're new on Google cloud there are several services that you can use in order to analyze this data that comes from the app. So a couple of them one as I said at the beginning is an analytical data warehouse which is BigQuery and uh for the reporting part you have a tool like Lucer but again as we said before you don't need to know how to use BigQuery in order to analyze those data as well as how to build a dashboard in Lucer because we also provide MCP server for doing this. Now for the sake of time I'm not going to demo how to use an MCP server to query bequery or building a a dashboard but uh I want to quickly share with you um where you can find uh this information in order to do that after this session because we are going to release the code. So I will ask uh to shift back on my laptop. Thank you. So uh okay loading time. So with respect to all the MCP server that are available on Google cloud we uh recently announced the uh agent platform. So in the agent platform you have uh a services that uh is represented by the agent registry and in the agent registry you have the list of all the MCP server that we natively support on Google cloud. So for example, we have the developer knowledge service that I just show you and we also have the BigQuery the BigQuery MCP server that you can use in order to uh query the data that we just collected from the app. Um it's very like this register is relevant because it tells you how to set uh how to set the MCP server on your side as well as it gives you some observability feature and the description of all the tools that you will find uh for the MCP server. So you know how clock code will be able to use uh this uh this uh this server to query your data. With respect to the um looker part also like we released the MCP toolbox of DB this is a open-source um like a model context protocol server which include an integration with looker and uh it's very well um we have a very very very well documented quick start on how to set up with the clock code and start using it in order to consume that data from bequery and build your dashboard. So I leave you this as an exercise like we we are going to release the code so you can go home and integrate these two parts is pretty straightforward but the dashboard that you you can create they are pretty they're pretty powerful and you will see how nice they can be. Okay, back to the presentation. I think I'm just in time. So time to uh time to wrap up. What I try to explain you today is essentially two things. So first of all I was trying to and I hope I did I did good enough. I was trying to show you how like all the components of a clock code including skills, MCP server, sub aents, they can really like speed up the process of software uh development as well as how you can use cloud code with uh cloud models on GCP in a very seamless way. Like if you saw we run several session across like multiple uh personas and like it was uh the experience was just uh straightforward. It was just uh incredible. So this is uh what you can get if you combine uh you know clock code with cloud models on uh on GCP. As I said um the re the code um is going to be available right after the session. We have a great quick start and we have a a very well maintained documentation both on Google cloud side and entropic side. So I highly recommend to just go there and check out and then I hope I cover everything but if you still have questions or you want to provide additional feedback just feel free to reach out uh these are my social media uh point. So with that being said thank you so much and it was a pleasure being here today.