- Antonio Rodriguez from AWS explains how to move Claude Code applications from local prototypes to production-ready apps on AWS, framing the AWS–Anthropic partnership as a "better together" story backed by multi-billion dollar investment and Project Rainier infrastructure.
- AWS offers three ways to use Claude: directly through Amazon Bedrock, via the new Claude platform on AWS (a gateway with consolidated billing and access control), and through Claude Desktop / Claude Code with consolidated AWS billing.
- The session is a hands-on workshop where attendees get free AWS accounts to experiment with Claude Code on Bedrock, working through modules covering setup, context, Playwright MCP, Git workflows, sub-agents, plugins, skills, and hooks.
AI with Claude on AWS: From code to orchestration
- The AWS–Anthropic relationship is deep: Amazon made a multi-billion dollar investment, is the primary cloud provider for Anthropic, and Anthropic committed over 100 billion in AWS usage, with Project Rainier being one of the largest AI compute infrastructures for training and hosting Claude models, powered by purpose-built Trainium chips (now third generation).
- Amazon Bedrock is a full platform: beyond foundation models, it offers evaluation, prompt optimization, fine-tuning (the only provider that lets you fine-tune Haiku), model distillation, managed knowledge bases for RAG, guardrails (content filters, PII masking, hallucination grounding), and agentic AI tooling.
- Security is a core differentiator: data stays inside your AWS boundary with no public-internet hopping, the latest Bedrock inference engine has zero operator access (no one from Amazon or Anthropic can reach those instances), and no customer data is used for training.
- The "better together" value includes data sovereignty, centralized/consolidated billing, full observability via CloudWatch and CloudTrail, SLAs with guaranteed uptime, built-in auth integration (SSO, OAuth, IAM, Entra ID, Okta), and PrivateLink for fully private communication.
- Bedrock Agent Core lets you host Claude Agent SDK agents securely in the cloud and is compatible with open frameworks like LangChain and Crew AI.
- The three deployment paths give the most options in the industry: Bedrock APIs (including the recently added Opus 4.7 and Messages API), Claude platform on AWS (acts as a gateway forwarding inference to Anthropic with full feature parity including web search, files, and agents), and Claude Desktop / Claude Code billed through AWS Marketplace or the CodeWhisperer 3P connection.
- The hands-on workshop uses the Scaled Draw repository: Module 1 covers basic Claude Code setup on AWS, Module 2 adds context and Playwright MCP for screenshots and Git workflows, and Module 3 covers sub-agents, plugins, custom skills, hooks, and advanced configuration.
Amazon Bedrock — AWS's managed platform for accessing, fine-tuning, and operating foundation models including Anthropic's Claude.
Project Rainier — One of the largest AI compute infrastructures, built by AWS for training and hosting Claude models.
Trainium — AWS's custom, purpose-built chipset designed for Claude models, now in its third generation.
Bedrock Agent Core — A managed infrastructure for hosting agents built with open frameworks or the Claude Agent SDK securely in the cloud.
Guardrails — A Bedrock feature for applying content filters, denying topics, masking PII, and grounding outputs to control hallucinations.
PrivateLink — An AWS feature that keeps all communication private without sending data to the public internet.
Data sovereignty — Full control over the environment and region where Claude is deployed, helping meet regulations like GDPR.
Claude platform on AWS — A recently launched gateway that gives the same Anthropic experience with consolidated AWS billing and access control while forwarding inference requests to Anthropic.
Playwright MCP — A tool used in the workshop to capture screenshots of diagrams and let Claude Code make automated modifications.
Good afternoon, everybody. Let's continue with the agenda. Thank you for joining this session. My name is Antonio Rodriguez. I work in Amazon Web Services and I'm also a developer as many of you, and also a cloud whisperer as I like to say — we are really just whispering orders these days, not really writing code. And in this session we're going to be talking about how to take the applications that you are building in Claude Code from prototypes that you might have in your computer to fully production-ready applications that you can have in the cloud, in this case with Amazon Web Services. And I think the story that we are telling today is a story about teamwork, a story about better together. Because I remember I joined the team and I started working with Anthropic more than 3 years ago. I remember we were still launching Claude 2 as the big amazing model that was changing and shifting the ground below us. And since then we have tried to combine the best frontier models that Anthropic has been developing with the best cloud provider that we had in Amazon Web Services.
This session, by the way, is a hands-on session. So what we are going to do is that I'm going to give you a brief introduction into how do we work together — Anthropic and AWS — and how you can use Claude in AWS in many different ways that we have available today. And then we are going to give you some accounts in AWS so that you can, free of charge and with no limitations, test Claude in Bedrock in this case, and also in general in AWS, so that you can see how to use it. You have guided instructions and a workshop, and again we are going to give you an environment so that you can play around with it.
This collaboration started and has been continued as a very long-term relationship. We have proven this year by year. Amazon has done a multi-billion investment in Anthropic because we really believe that we are building the future of AI together. And at the same time, we are the primary cloud provider for Anthropic. And Anthropic has committed more than 100 billion in usage in AWS as well, in the infrastructure that we are offering for powering the models that you are using every day with Claude. An example of this investment is Project Rainier. Project Rainier is actually one of the largest AI compute infrastructures that was built for training and hosting the Claude models that you are using today with Anthropic. We are also using custom and purpose-built chipsets that are specifically made for the Claude models, in the chipsets that we call Trainium. So we have our third generation of Trainium chipsets already built by Amazon. So you can actually get the best speed and also use it in the most cost-effective way when you are spending tokens with Claude.
If we start diving into the technical part of this collaboration, there are three angles that we basically offer you when you use Claude through AWS. The first one is that you have a very comprehensive list of features. In Bedrock, you have a full platform. So you can combine and fine-tune the models as well. We are the only provider that allows you to fine-tune Haiku, for example, in the cloud. And we have full integrations with the rest of the features that we have available in Bedrock and the AWS ecosystem in general. The second and very important point is the security. So we can make sure that you keep control of your data at all times. We avoid this hopping of data going to the public internet. You can keep everything private in your AWS boundary. So we make sure that you always align with the compliance and security best practices that you might have in your companies, or the regulations. If you are working in banking or health care, these kinds of highly regulated industries, it's very important that you actually have these options for controlling everything that you're doing in cloud. And obviously the data privacy part: we work nowadays with the latest generation inference engine that we have in Bedrock. We have zero operator access in the platform, which means that no one from Amazon or from Anthropic can actually get access to those instances. So your data remains fully private. We are not sharing that data with anyone. No one is using that data for training models or anything like that. Last but not least, the scalability. Using those cloud models through Bedrock gives you practically infinite scalability in the sense that you can really decide how you want to do the deployments. You have full flexibility for choosing regions as well. For example, you could decide that you want to deploy Claude only in London region in AWS, or only in the European region if you have to align with GDPR and these kinds of regulations.
Now, if we see the whole ecosystem — who is familiar with Amazon Bedrock, by the way, in this room? Okay, so I was expecting fewer hands to be honest, because this is really a cloud event, but it's great to hear that you are using Bedrock or you know about Bedrock. Bedrock has been growing a lot since the beginning, since the last three or four years when we released the service. And today, apart from the core, which is obviously the foundation models that you have access to — and obviously Anthropic Claude models are a very important part of that — you also have other features that help you in the full journey as a developer. So you have a feature that helps you doing evaluation, that helps you doing prompt optimization, that helps you fine-tuning the models as we mentioned before, or doing model distillation as well if you need it. We also give you some features that help you connecting if you have RAG use cases — you can have knowledge bases that are fully managed so that you can attach to it as well. We have guardrails, which is a way in which you can apply content filters, you can deny topics, you can protect PII data or sensitive data by doing automatic masking, and so on. And you can also control hallucinations from the models by doing proper grounding, automated reasoning checks. And even more important in the last two years, tools for building with agentic AI. And if you are using Claude agents, then awesome. But if you are using the Claude Agent SDK and you are looking for an infrastructure for hosting your agents in a secure way in the cloud, then you can also use Amazon Bedrock Agent Core, which is fully compatible with any open framework that you might be using for agentic AI today, like LangChain, like Crew AI, and obviously Claude Agent SDK as well.
Now, if I have to summarize in a single slide everything that I'm saying so far on the "better together" story — why is it better to use Claude in AWS — I would say this is probably the slide. First of all, the data sovereignty that you can get when you are using Claude in AWS: you have full control of the environment that you are setting up and where you are using it. You also have centralized billing from AWS, so you can actually have a single bill. If your companies are already using AWS, you can have a consolidated single bill that has the usage of Claude included with everything else that you might be doing today. You have full observability through our services like CloudWatch or CloudTrail as well, in which you can actually see details of metrics, logs. You can see the traces of everything that has happened. And we also offer SLAs, so we make sure that you have guaranteed availability on the services. So you have an uptime that is secure for your applications and you can go safe to production and make sure that you can scale at cloud scale safely. Another very important point is that we have built-in auth integration. So if you're using single sign-on, or if you're doing OAuth, or if you're using IAM roles in AWS for example, you can directly integrate that with your identity provider. You could be using Microsoft Entra ID, you could be using Okta, you could be using any of those identity providers today. And last point, you can use PrivateLink, which means that all the communication can remain fully private. So you make sure that no data is being sent to the public internet at any point when you are using Claude in Bedrock. As I mentioned about compliance before, these are some of the compliance regulations that we support — for example, FedRAMP, HIPAA, and so on and so forth. There is a full list online if you want to check it out.
Now, the good news is that today you have three ways of using Claude in AWS. And actually, this is the most options that you are going to find in the whole industry right now. The first one is you can use Claude models directly through Amazon Bedrock, as I mentioned before. So basically everything that I was saying so far, in which you have the same high-quality output that you might be getting directly, but in this case fully through the Amazon Bedrock APIs that are offered to you. We have recently added Opus 4.7 and included the Messages API as well, so that you can directly invoke with the Messages API if that's the method that you prefer. Now, we have also recently launched Claude platform on AWS. Claude platform on AWS is actually generally available since a few days ago, and this allows you to have the same exact experience that you might be using today directly with Anthropic, but in this case with consolidated billing through AWS and having the access control fully done on AWS as well. We act as a gateway in this case, and we send all the inference requests to Anthropic so that they can process the request for you. So it's giving you the best of both worlds: you get the security, the billing, the consolidated access control that we are giving in AWS, and at the same time you have all the feature parity with Anthropic, including web search, files, agents, and so on and so forth. Now, the third way in which you can use it is also if you are not using Claude programmatically, but you are rather using Claude Desktop. So you might be using CodeWhisperer, you might be using Claude Code through the Claude Desktop application. You can also use it directly from AWS, and again you can pay in a consolidated bill in AWS. You have two ways of doing that as well. One is through Claude Enterprise in the AWS Marketplace, in which you pretty much subscribe to the number of developers that you have using this application. But you now also have the option of using, let's say, the CodeWhisperer 3P, which is one of the latest additions also that the Anthropic team did for connecting Claude Desktop to third parties. In this case, you can connect Claude Desktop to Bedrock, or you can connect even Claude Desktop to the Claude platform on AWS if you prefer to do so. So you have all sorts of combinations to make your life easier, and pretty much meet you where you are on your needs.
Let's dive into the actual workshop that we are going to be building together. I just want to make a recap that, first of all, you need two prerequisites for running this workshop. One is you need an AWS account — we've got you covered. We are going to give you a workshop account that has an environment that you can play around with, free of charge, free of any concern. And then the other thing is that you obviously need to have Claude Code installed as an application. In the accounts that we are setting up for you, you are going to find the workshop that is called "Introduction to Claude Code on AWS." This workshop has instructions on how to set up everything. We are pretty much playing around with the Scaled Draw tool, with the repository of Scaled Draw, so that you can see how Claude Code can help you playing around with Scaled Draw and drawing architecture diagrams for you, for example. This is a basic workshop. Who is getting started with Claude Code in this room? Who would say they are a ninja in Claude Code, with all the skills? Who is in the middle? Yeah, I guess most of the room is probably in the middle. So you will find that probably Module 1 is basic for you — it's just using Claude Code on AWS and learning how to set it up and point to Scaled Draw. Module 2 and Module 3 are probably more interesting. We are going to start playing with the context. We are going to start using Playwright MCP, so we can actually take screenshots of the diagram that we are drawing and make automated modifications through Claude Code on it. You are also playing around with the Git workflows on Claude Code. And in Module 3, we are going to play with sub-agents and plugins. And we are also creating custom skills, hooks, and some advanced parameters for configuration.
I just want to mention that we have an even more advanced workshop that is also available for you if you look for this URL. Basically there you have other things that are very interesting for teams who want to move to production in a safe way. Here you can learn how to set up team standards, how to implement and distribute advanced workflows, how to do scalability, cost control, and so on. For example, you could see how to set up dashboards for making sure that you can control all the use that you are doing of Claude Code tokens in your accounts, developer productivity measurements, measuring return of investment of your applications, and so on. And last, you have also options for using the Claude Agent SDK on the Amazon Bedrock Agent Core, so that you can learn how to build agents connected to the Claude infrastructure that we have here in AWS as well.
Coming back to our workshop, you have different ways of doing it. At the very beginning, you will see a screen with some terms and conditions. I just want to remind everybody that those are workshop accounts, individual for you, but make sure that you don't upload confidential information, personal information, or anything like that. You will have to agree to the terms and conditions and click on "join event." And from that point on, you are going to see this experience, where you're going to have an environment fully deployed for you. You will see a URL that will take you to a terminal and a Visual Studio Code UI where you can actually work on all the instructions in the workshop. Let's say that you don't want to follow this path, and you want to do it on your own machine — then you can. You can use Claude directly in a terminal. If you prefer, you can configure it for pointing to Bedrock with instructions that we're giving you in the workshop. Let's say that you want to use CodeWhisperer or the Claude Desktop app — you can do it as well. Here I'm pointing to my Bedrock account. So I have a Claude Desktop pointing to Bedrock, and here I'm doing the Scaled Draw application on the workshop that we have for you over there as well. And there is more information. At the end, we are going to be sharing with you more guidance, for example, for how to use Claude Code and Cowork on Amazon Bedrock. There is a full block from my colleagues who is covering all of this in detail.
The instructions for accessing the accounts are very easy. All you have to do is go to join.thatworkshop.aws, and you have to input that access code that you see on the screen. You have the two solutions architects from AWS who can help you with questions. If you have any questions, just raise your hand. We also have been handing over some pieces of paper that has this information, so you can copy and paste it in your laptops. One last comment with regards to advanced configurations: if you want to use things like configuring the settings that you're using in Claude Code manually, this is the kind of parameters that you will need to set up. You might take a picture now if you want. Here is how to set up the region pointed to Bedrock, choose the default model, and so on. And then on the right-hand side, you also have some parameters for reducing the token usage or doing rate limiting, and how to enable auto reporting for telemetry. You also have some information here about how to configure extensions in the case that you're using Visual Studio. But again, it is all about asking Claude to configure itself, or you can do it manually if you prefer through the extensions. It helps you with some things, for example, disabling the login prompt that is a bit annoying every time that you start, or hiding the onboarding message that you always get in Claude Code.
TL;DR
- Antonio Rodriguez from AWS explains how to move Claude Code applications from local prototypes to production-ready apps on AWS, framing the AWS–Anthropic partnership as a "better together" story backed by multi-billion dollar investment and Project Rainier infrastructure.
- AWS offers three ways to use Claude: directly through Amazon Bedrock, via the new Claude platform on AWS (a gateway with consolidated billing and access control), and through Claude Desktop / Claude Code with consolidated AWS billing.
- The session is a hands-on workshop where attendees get free AWS accounts to experiment with Claude Code on Bedrock, working through modules covering setup, context, Playwright MCP, Git workflows, sub-agents, plugins, skills, and hooks.
Takeaways
- The AWS–Anthropic relationship is deep: Amazon made a multi-billion dollar investment, is the primary cloud provider for Anthropic, and Anthropic committed over 100 billion in AWS usage, with Project Rainier being one of the largest AI compute infrastructures for training and hosting Claude models, powered by purpose-built Trainium chips (now third generation).
- Amazon Bedrock is a full platform: beyond foundation models, it offers evaluation, prompt optimization, fine-tuning (the only provider that lets you fine-tune Haiku), model distillation, managed knowledge bases for RAG, guardrails (content filters, PII masking, hallucination grounding), and agentic AI tooling.
- Security is a core differentiator: data stays inside your AWS boundary with no public-internet hopping, the latest Bedrock inference engine has zero operator access (no one from Amazon or Anthropic can reach those instances), and no customer data is used for training.
- The "better together" value includes data sovereignty, centralized/consolidated billing, full observability via CloudWatch and CloudTrail, SLAs with guaranteed uptime, built-in auth integration (SSO, OAuth, IAM, Entra ID, Okta), and PrivateLink for fully private communication.
- Bedrock Agent Core lets you host Claude Agent SDK agents securely in the cloud and is compatible with open frameworks like LangChain and Crew AI.
- The three deployment paths give the most options in the industry: Bedrock APIs (including the recently added Opus 4.7 and Messages API), Claude platform on AWS (acts as a gateway forwarding inference to Anthropic with full feature parity including web search, files, and agents), and Claude Desktop / Claude Code billed through AWS Marketplace or the CodeWhisperer 3P connection.
- The hands-on workshop uses the Scaled Draw repository: Module 1 covers basic Claude Code setup on AWS, Module 2 adds context and Playwright MCP for screenshots and Git workflows, and Module 3 covers sub-agents, plugins, custom skills, hooks, and advanced configuration.
Vocabulary
Amazon Bedrock — AWS's managed platform for accessing, fine-tuning, and operating foundation models including Anthropic's Claude.
Project Rainier — One of the largest AI compute infrastructures, built by AWS for training and hosting Claude models.
Trainium — AWS's custom, purpose-built chipset designed for Claude models, now in its third generation.
Bedrock Agent Core — A managed infrastructure for hosting agents built with open frameworks or the Claude Agent SDK securely in the cloud.
Guardrails — A Bedrock feature for applying content filters, denying topics, masking PII, and grounding outputs to control hallucinations.
PrivateLink — An AWS feature that keeps all communication private without sending data to the public internet.
Data sovereignty — Full control over the environment and region where Claude is deployed, helping meet regulations like GDPR.
Claude platform on AWS — A recently launched gateway that gives the same Anthropic experience with consolidated AWS billing and access control while forwarding inference requests to Anthropic.
Playwright MCP — A tool used in the workshop to capture screenshots of diagrams and let Claude Code make automated modifications.
Transcript
Good afternoon, everybody. Let's continue with the agenda. Thank you for joining this session. My name is Antonio Rodriguez. I work in Amazon Web Services and I'm also a developer as many of you, and also a cloud whisperer as I like to say — we are really just whispering orders these days, not really writing code. And in this session we're going to be talking about how to take the applications that you are building in Claude Code from prototypes that you might have in your computer to fully production-ready applications that you can have in the cloud, in this case with Amazon Web Services. And I think the story that we are telling today is a story about teamwork, a story about better together. Because I remember I joined the team and I started working with Anthropic more than 3 years ago. I remember we were still launching Claude 2 as the big amazing model that was changing and shifting the ground below us. And since then we have tried to combine the best frontier models that Anthropic has been developing with the best cloud provider that we had in Amazon Web Services.
This session, by the way, is a hands-on session. So what we are going to do is that I'm going to give you a brief introduction into how do we work together — Anthropic and AWS — and how you can use Claude in AWS in many different ways that we have available today. And then we are going to give you some accounts in AWS so that you can, free of charge and with no limitations, test Claude in Bedrock in this case, and also in general in AWS, so that you can see how to use it. You have guided instructions and a workshop, and again we are going to give you an environment so that you can play around with it.
This collaboration started and has been continued as a very long-term relationship. We have proven this year by year. Amazon has done a multi-billion investment in Anthropic because we really believe that we are building the future of AI together. And at the same time, we are the primary cloud provider for Anthropic. And Anthropic has committed more than 100 billion in usage in AWS as well, in the infrastructure that we are offering for powering the models that you are using every day with Claude. An example of this investment is Project Rainier. Project Rainier is actually one of the largest AI compute infrastructures that was built for training and hosting the Claude models that you are using today with Anthropic. We are also using custom and purpose-built chipsets that are specifically made for the Claude models, in the chipsets that we call Trainium. So we have our third generation of Trainium chipsets already built by Amazon. So you can actually get the best speed and also use it in the most cost-effective way when you are spending tokens with Claude.
If we start diving into the technical part of this collaboration, there are three angles that we basically offer you when you use Claude through AWS. The first one is that you have a very comprehensive list of features. In Bedrock, you have a full platform. So you can combine and fine-tune the models as well. We are the only provider that allows you to fine-tune Haiku, for example, in the cloud. And we have full integrations with the rest of the features that we have available in Bedrock and the AWS ecosystem in general. The second and very important point is the security. So we can make sure that you keep control of your data at all times. We avoid this hopping of data going to the public internet. You can keep everything private in your AWS boundary. So we make sure that you always align with the compliance and security best practices that you might have in your companies, or the regulations. If you are working in banking or health care, these kinds of highly regulated industries, it's very important that you actually have these options for controlling everything that you're doing in cloud. And obviously the data privacy part: we work nowadays with the latest generation inference engine that we have in Bedrock. We have zero operator access in the platform, which means that no one from Amazon or from Anthropic can actually get access to those instances. So your data remains fully private. We are not sharing that data with anyone. No one is using that data for training models or anything like that. Last but not least, the scalability. Using those cloud models through Bedrock gives you practically infinite scalability in the sense that you can really decide how you want to do the deployments. You have full flexibility for choosing regions as well. For example, you could decide that you want to deploy Claude only in London region in AWS, or only in the European region if you have to align with GDPR and these kinds of regulations.
Now, if we see the whole ecosystem — who is familiar with Amazon Bedrock, by the way, in this room? Okay, so I was expecting fewer hands to be honest, because this is really a cloud event, but it's great to hear that you are using Bedrock or you know about Bedrock. Bedrock has been growing a lot since the beginning, since the last three or four years when we released the service. And today, apart from the core, which is obviously the foundation models that you have access to — and obviously Anthropic Claude models are a very important part of that — you also have other features that help you in the full journey as a developer. So you have a feature that helps you doing evaluation, that helps you doing prompt optimization, that helps you fine-tuning the models as we mentioned before, or doing model distillation as well if you need it. We also give you some features that help you connecting if you have RAG use cases — you can have knowledge bases that are fully managed so that you can attach to it as well. We have guardrails, which is a way in which you can apply content filters, you can deny topics, you can protect PII data or sensitive data by doing automatic masking, and so on. And you can also control hallucinations from the models by doing proper grounding, automated reasoning checks. And even more important in the last two years, tools for building with agentic AI. And if you are using Claude agents, then awesome. But if you are using the Claude Agent SDK and you are looking for an infrastructure for hosting your agents in a secure way in the cloud, then you can also use Amazon Bedrock Agent Core, which is fully compatible with any open framework that you might be using for agentic AI today, like LangChain, like Crew AI, and obviously Claude Agent SDK as well.
Now, if I have to summarize in a single slide everything that I'm saying so far on the "better together" story — why is it better to use Claude in AWS — I would say this is probably the slide. First of all, the data sovereignty that you can get when you are using Claude in AWS: you have full control of the environment that you are setting up and where you are using it. You also have centralized billing from AWS, so you can actually have a single bill. If your companies are already using AWS, you can have a consolidated single bill that has the usage of Claude included with everything else that you might be doing today. You have full observability through our services like CloudWatch or CloudTrail as well, in which you can actually see details of metrics, logs. You can see the traces of everything that has happened. And we also offer SLAs, so we make sure that you have guaranteed availability on the services. So you have an uptime that is secure for your applications and you can go safe to production and make sure that you can scale at cloud scale safely. Another very important point is that we have built-in auth integration. So if you're using single sign-on, or if you're doing OAuth, or if you're using IAM roles in AWS for example, you can directly integrate that with your identity provider. You could be using Microsoft Entra ID, you could be using Okta, you could be using any of those identity providers today. And last point, you can use PrivateLink, which means that all the communication can remain fully private. So you make sure that no data is being sent to the public internet at any point when you are using Claude in Bedrock. As I mentioned about compliance before, these are some of the compliance regulations that we support — for example, FedRAMP, HIPAA, and so on and so forth. There is a full list online if you want to check it out.
Now, the good news is that today you have three ways of using Claude in AWS. And actually, this is the most options that you are going to find in the whole industry right now. The first one is you can use Claude models directly through Amazon Bedrock, as I mentioned before. So basically everything that I was saying so far, in which you have the same high-quality output that you might be getting directly, but in this case fully through the Amazon Bedrock APIs that are offered to you. We have recently added Opus 4.7 and included the Messages API as well, so that you can directly invoke with the Messages API if that's the method that you prefer. Now, we have also recently launched Claude platform on AWS. Claude platform on AWS is actually generally available since a few days ago, and this allows you to have the same exact experience that you might be using today directly with Anthropic, but in this case with consolidated billing through AWS and having the access control fully done on AWS as well. We act as a gateway in this case, and we send all the inference requests to Anthropic so that they can process the request for you. So it's giving you the best of both worlds: you get the security, the billing, the consolidated access control that we are giving in AWS, and at the same time you have all the feature parity with Anthropic, including web search, files, agents, and so on and so forth. Now, the third way in which you can use it is also if you are not using Claude programmatically, but you are rather using Claude Desktop. So you might be using CodeWhisperer, you might be using Claude Code through the Claude Desktop application. You can also use it directly from AWS, and again you can pay in a consolidated bill in AWS. You have two ways of doing that as well. One is through Claude Enterprise in the AWS Marketplace, in which you pretty much subscribe to the number of developers that you have using this application. But you now also have the option of using, let's say, the CodeWhisperer 3P, which is one of the latest additions also that the Anthropic team did for connecting Claude Desktop to third parties. In this case, you can connect Claude Desktop to Bedrock, or you can connect even Claude Desktop to the Claude platform on AWS if you prefer to do so. So you have all sorts of combinations to make your life easier, and pretty much meet you where you are on your needs.
Let's dive into the actual workshop that we are going to be building together. I just want to make a recap that, first of all, you need two prerequisites for running this workshop. One is you need an AWS account — we've got you covered. We are going to give you a workshop account that has an environment that you can play around with, free of charge, free of any concern. And then the other thing is that you obviously need to have Claude Code installed as an application. In the accounts that we are setting up for you, you are going to find the workshop that is called "Introduction to Claude Code on AWS." This workshop has instructions on how to set up everything. We are pretty much playing around with the Scaled Draw tool, with the repository of Scaled Draw, so that you can see how Claude Code can help you playing around with Scaled Draw and drawing architecture diagrams for you, for example. This is a basic workshop. Who is getting started with Claude Code in this room? Who would say they are a ninja in Claude Code, with all the skills? Who is in the middle? Yeah, I guess most of the room is probably in the middle. So you will find that probably Module 1 is basic for you — it's just using Claude Code on AWS and learning how to set it up and point to Scaled Draw. Module 2 and Module 3 are probably more interesting. We are going to start playing with the context. We are going to start using Playwright MCP, so we can actually take screenshots of the diagram that we are drawing and make automated modifications through Claude Code on it. You are also playing around with the Git workflows on Claude Code. And in Module 3, we are going to play with sub-agents and plugins. And we are also creating custom skills, hooks, and some advanced parameters for configuration.
I just want to mention that we have an even more advanced workshop that is also available for you if you look for this URL. Basically there you have other things that are very interesting for teams who want to move to production in a safe way. Here you can learn how to set up team standards, how to implement and distribute advanced workflows, how to do scalability, cost control, and so on. For example, you could see how to set up dashboards for making sure that you can control all the use that you are doing of Claude Code tokens in your accounts, developer productivity measurements, measuring return of investment of your applications, and so on. And last, you have also options for using the Claude Agent SDK on the Amazon Bedrock Agent Core, so that you can learn how to build agents connected to the Claude infrastructure that we have here in AWS as well.
Coming back to our workshop, you have different ways of doing it. At the very beginning, you will see a screen with some terms and conditions. I just want to remind everybody that those are workshop accounts, individual for you, but make sure that you don't upload confidential information, personal information, or anything like that. You will have to agree to the terms and conditions and click on "join event." And from that point on, you are going to see this experience, where you're going to have an environment fully deployed for you. You will see a URL that will take you to a terminal and a Visual Studio Code UI where you can actually work on all the instructions in the workshop. Let's say that you don't want to follow this path, and you want to do it on your own machine — then you can. You can use Claude directly in a terminal. If you prefer, you can configure it for pointing to Bedrock with instructions that we're giving you in the workshop. Let's say that you want to use CodeWhisperer or the Claude Desktop app — you can do it as well. Here I'm pointing to my Bedrock account. So I have a Claude Desktop pointing to Bedrock, and here I'm doing the Scaled Draw application on the workshop that we have for you over there as well. And there is more information. At the end, we are going to be sharing with you more guidance, for example, for how to use Claude Code and Cowork on Amazon Bedrock. There is a full block from my colleagues who is covering all of this in detail.
The instructions for accessing the accounts are very easy. All you have to do is go to join.thatworkshop.aws, and you have to input that access code that you see on the screen. You have the two solutions architects from AWS who can help you with questions. If you have any questions, just raise your hand. We also have been handing over some pieces of paper that has this information, so you can copy and paste it in your laptops. One last comment with regards to advanced configurations: if you want to use things like configuring the settings that you're using in Claude Code manually, this is the kind of parameters that you will need to set up. You might take a picture now if you want. Here is how to set up the region pointed to Bedrock, choose the default model, and so on. And then on the right-hand side, you also have some parameters for reducing the token usage or doing rate limiting, and how to enable auto reporting for telemetry. You also have some information here about how to configure extensions in the case that you're using Visual Studio. But again, it is all about asking Claude to configure itself, or you can do it manually if you prefer through the extensions. It helps you with some things, for example, disabling the login prompt that is a bit annoying every time that you start, or hiding the onboarding message that you always get in Claude Code.