{"id":4441,"date":"2026-02-10T09:40:14","date_gmt":"2026-02-10T09:40:14","guid":{"rendered":"https:\/\/salarydistribution.com\/machine-learning\/2026\/02\/10\/accelerate-agentic-application-development-with-a-full-stack-starter-template-for-amazon-bedrock-agentcore\/"},"modified":"2026-02-10T09:40:14","modified_gmt":"2026-02-10T09:40:14","slug":"accelerate-agentic-application-development-with-a-full-stack-starter-template-for-amazon-bedrock-agentcore","status":"publish","type":"post","link":"https:\/\/salarydistribution.com\/machine-learning\/2026\/02\/10\/accelerate-agentic-application-development-with-a-full-stack-starter-template-for-amazon-bedrock-agentcore\/","title":{"rendered":"Accelerate agentic application development with a full-stack starter template for Amazon Bedrock AgentCore"},"content":{"rendered":"<div id=\"\">\n<p>Generative AI and agentic applications are reshaping how businesses operate\u2014from customer support bots to research assistants\u2014and teams need to move from prototype to production quickly. Last year, AWS released <a href=\"https:\/\/aws.amazon.com\/bedrock\/agentcore\/\" target=\"_blank\" rel=\"noopener noreferrer\">Amazon Bedrock AgentCore<\/a>\u2014a development platform for building, deploying, and scaling AI agents in production. AgentCore provides core building blocks like runtime hosting, memory, tool integration, and observability with enterprise-grade security and dynamic scaling.<\/p>\n<p>The <a href=\"https:\/\/github.com\/awslabs\/fullstack-solution-template-for-agentcore\" target=\"_blank\" rel=\"noopener noreferrer\">Fullstack AgentCore Solution Template (FAST)<\/a> shows you how it works together from the start. It\u2019s a ready-to-deploy starter project that connects AgentCore Runtime, Gateway, Memory, and Code Interpreter with a <a href=\"https:\/\/react.dev\/\" target=\"_blank\" rel=\"noopener noreferrer\">React<\/a> frontend and <a href=\"https:\/\/aws.amazon.com\/cognito\/\" target=\"_blank\" rel=\"noopener noreferrer\">Amazon Cognito<\/a> authentication\u2014all defined with <a href=\"https:\/\/aws.amazon.com\/cdk\/\" target=\"_blank\" rel=\"noopener noreferrer\">AWS Cloud Development Kit (AWS CDK)<\/a>. FAST provides a complete reference architecture that shows you how the pieces integrate, with a working chat application that you can learn from and build upon.<\/p>\n<p>In this post, you will learn how to deploy FAST to your <a href=\"https:\/\/aws.amazon.com\/\" target=\"_blank\" rel=\"noopener noreferrer\">Amazon Web Services (AWS)<\/a> account, understand its architecture, and see how to extend it for your requirements. You will learn how to build your own agent while FAST handles authentication, infrastructure as code (IaC), deployment pipelines, and service integration.<\/p>\n<h2>Solution overview<\/h2>\n<p>FAST provides a complete full-stack architecture for deploying agents on Amazon Bedrock AgentCore. The template handles authentication, frontend application hosting, agent runtime, memory, observability, and Model Context Protocol (MCP) tool integration by default.<\/p>\n<p><img decoding=\"async\" loading=\"lazy\" class=\"size-full wp-image-123864 aligncenter\" src=\"https:\/\/d2908q01vomqb2.cloudfront.net\/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59\/2026\/02\/03\/ML-20357-1.png\" alt=\"AWS architecture diagram showing an AI agent application using Amazon Bedrock AgentCore with multi-agent orchestration, including user authentication through Cognito, API Gateway, Lambda compute layer, AgentCore Runtime with code interpreter, memory, gateway, and observability components, DynamoDB storage, and CloudWatch\/X-Ray monitoring.\" width=\"665\" height=\"500\"><\/p>\n<p>The architecture is centered on <a href=\"https:\/\/docs.aws.amazon.com\/bedrock-agentcore\/latest\/devguide\/agents-tools-runtime.html\" target=\"_blank\" rel=\"noopener noreferrer\">Amazon Bedrock AgentCore Runtime<\/a>, which hosts your agent. In FAST, users authenticate through Amazon Cognito, which secures four integration points:<\/p>\n<ol>\n<li>User sign-in to the frontend web application on <a href=\"https:\/\/aws.amazon.com\/cloudfront\/\" target=\"_blank\" rel=\"noopener noreferrer\">Amazon CloudFront<\/a><\/li>\n<li>Token-based authentication for the frontend to access AgentCore Runtime<\/li>\n<li>Token-based authentication for agents to access AgentCore Gateway<\/li>\n<li>Token-based authentication for API requests to <a href=\"https:\/\/aws.amazon.com\/api-gateway\/\" target=\"_blank\" rel=\"noopener noreferrer\">Amazon API Gateway<\/a><\/li>\n<\/ol>\n<p>The frontend is a React application that uses <a href=\"https:\/\/tailwindcss.com\/\" target=\"_blank\" rel=\"noopener noreferrer\">Tailwind CSS<\/a> and <a href=\"https:\/\/ui.shadcn.com\/\" target=\"_blank\" rel=\"noopener noreferrer\">shadcn<\/a> components, hosted on <a href=\"https:\/\/aws.amazon.com\/amplify\/hosting\/\" target=\"_blank\" rel=\"noopener noreferrer\">AWS Amplify Hosting<\/a>. It communicates with AgentCore Runtime using streamable HTTP for real-time response streaming.<\/p>\n<p>The feedback mechanism is provided to demonstrate how to make synchronous and authenticated HTTP calls through API Gateway and store application data in Dynamo DB. AgentCore Runtime connects to several AgentCore capabilities:<\/p>\n<p>The template includes patterns for <a href=\"https:\/\/strandsagents.com\/latest\/\" target=\"_blank\" rel=\"noopener noreferrer\">Strands Agents<\/a> and <a href=\"https:\/\/www.langchain.com\/langgraph\" target=\"_blank\" rel=\"noopener noreferrer\">LangGraph<\/a>. FAST and AgentCore are agent framework-agnostic so you can use the agent SDK of your choice. The infrastructure is defined in AWS CDK for repeatable deployments.<\/p>\n<p>The architecture is modular by design. The frontend integrates with the backend powered by AgentCore, which you can use as an example for integrating with your own frontend application. That can be your own React application or a frontend using a completely different frontend framework.<\/p>\n<h3>Designed for AI-assisted development<\/h3>\n<p>FAST includes extensive documentation by design. The repository includes:<\/p>\n<ul>\n<li><strong>Steering documents<\/strong> \u2013 Rules and conventions that coding assistants follow automatically<\/li>\n<li><strong>Feature guides<\/strong> \u2013 Detailed documentation on gateway, memory, streaming, and other integrations<\/li>\n<li><strong>READMEs<\/strong> throughout the codebase \u2013 Context for each component<\/li>\n<\/ul>\n<p>When you ask a coding assistant to make changes, it can read these documents and follow the documented patterns. This approach works with many AI coding assistants, including <a href=\"https:\/\/kiro.dev\/\" target=\"_blank\" rel=\"noopener noreferrer\">Kiro<\/a>, Cline, Claude Code, Cursor, and others. The documentation and steering docs are system-agnostic.<\/p>\n<p>AI-assisted development is optional. The same documentation that guides coding assistants is equally useful for developers who prefer to write the code themselves.<\/p>\n<h2>Prerequisites<\/h2>\n<p>Before deploying FAST, make sure you have the following installed:<\/p>\n<p>The <a href=\"https:\/\/aws.amazon.com\/iam\" target=\"_blank\" rel=\"noopener noreferrer\">AWS Identity and Access Management (IAM)<\/a> user that you use must have permissions to make the necessary AWS service calls and manage AWS resources mentioned in this post. When providing permissions to the IAM user, follow the principle of least privilege.<\/p>\n<h2>Solution deployment walkthrough<\/h2>\n<p>Start by deploying the solution in your local environment.<\/p>\n<h3>Step 1: Clone the repository<\/h3>\n<p>Start by using the following commands to clone the repository.<\/p>\n<div class=\"hide-language\">\n<pre><code class=\"lang-code\">git clone https:\/\/github.com\/awslabs\/fullstack-solution-template-for-agentcore.git\ncd fullstack-solution-template-for-agentcore<\/code><\/pre>\n<\/p><\/div>\n<h3>Step 2: Configure your deployment<\/h3>\n<p>Edit <code>infra-cdk\/config.yaml<\/code> to customize your deployment:<\/p>\n<div class=\"hide-language\">\n<pre><code class=\"lang-yaml\">stack_name_base: your-project-name \nadmin_user_email: admin@example.com # Optional: auto-creates user and emails credentials \nbackend: pattern: strands-single-agent # Available: strands-single-agent, langgraph-single-agent \ndeployment_type: docker # Available: docker, zip<\/code><\/pre>\n<\/p><\/div>\n<h3>Step 3: Deploy the backend with CDK<\/h3>\n<p>Use the following commands to deploy the backend.<\/p>\n<div class=\"hide-language\">\n<pre><code class=\"lang-bash\">cd infra-cdk \nnpm install \ncdk bootstrap # Only required once per account\/region \ncdk deploy<\/code><\/pre>\n<\/p><\/div>\n<p>This creates the Cognito User Pool, builds and pushes the agent container to <a href=\"https:\/\/aws.amazon.com\/ecr\" target=\"_blank\" rel=\"noopener noreferrer\">Amazon Elastic Container Registry (Amazon ECR)<\/a>, creates the AgentCore Runtime, and sets up the CloudFront distribution. Deployment takes approximately 5\u201310 minutes.<\/p>\n<h3>Step 4: Deploy the frontend<\/h3>\n<p>Use the following commands to deploy the frontend.<\/p>\n<div class=\"hide-language\">\n<pre><code class=\"lang-code\">cd ..\npython scripts\/deploy-frontend.py<\/code><\/pre>\n<\/p><\/div>\n<p>The script generates the authentication configuration from CDK stack outputs, installs dependencies, builds the React application, and deploys to <a href=\"https:\/\/aws.amazon.com\/amplify\" target=\"_blank\" rel=\"noopener noreferrer\">AWS Amplify<\/a> Hosting. The script outputs the application URL when complete:<\/p>\n<div class=\"hide-language\">\n<pre><code class=\"lang-code\">\u2713 Deployment completed successfully!\n\nConsole: https:\/\/console.aws.amazon.com\/amplify\/apps\nApp URL: https:\/\/main.d123490abcdef.amplifyapp.com<\/code><\/pre>\n<\/p><\/div>\n<h3>Step 5: Create an Amazon Cognito user<\/h3>\n<p>If you provided <code>admin_user_email<\/code> in the configuration, you will receive an email with temporary credentials that you can use to sign in. Move to the next step.<\/p>\n<p>If you didn\u2019t provide an <code>admin_user_email<\/code>, create a user manually:<\/p>\n<ol>\n<li>Open the Amazon Cognito console.<\/li>\n<li>Find your <strong>User Pool<\/strong> (named <code>{stack_name_base}-user-pool<\/code>).<\/li>\n<li>Navigate to <strong>Users<\/strong> and choose <strong>Create user<\/strong>.<\/li>\n<li>Enter an email address and temporary password.<\/li>\n<li>Select <strong>Mark email as verified<\/strong>.<\/li>\n<li>Choose <strong>Create user<\/strong>.<\/li>\n<\/ol>\n<h3>Step 6: Access and test the application<\/h3>\n<p>You\u2019re ready to access and test the application using the following steps:<\/p>\n<ol>\n<li>Open the Amplify Hosting URL (printed in your terminal after deploying the frontend) in your browser.<\/li>\n<li>Sign in with your Amazon Cognito user credentials.<\/li>\n<li>Change your temporary password when prompted.<\/li>\n<\/ol>\n<p><img decoding=\"async\" loading=\"lazy\" class=\"alignnone size-full wp-image-123878\" src=\"https:\/\/d2908q01vomqb2.cloudfront.net\/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59\/2026\/02\/03\/FAST-blog-gif-2.gif\" alt=\"Gif demonstrating logging into the default FAST application with a username and password, then entering a sample query and seeing the response stream back to the screen.\" width=\"1200\" height=\"759\"><\/p>\n<p>The FAST example application is a straightforward multi-turn chat interface. The UI remains minimal by design; it\u2019s built to be replaced with your own frontend or integrated into an existing application. The baseline agent includes two tools to demonstrate the architecture:<\/p>\n<ul>\n<li><strong>Text analysis tool<\/strong> \u2013 An <a href=\"https:\/\/aws.amazon.com\/pm\/lambda\" target=\"_blank\" rel=\"noopener noreferrer\">AWS Lambda<\/a>-based tool behind AgentCore Gateway that counts words and analyzes letter frequency. This demonstrates the Gateway integration pattern.<\/li>\n<li><strong>Code Interpreter<\/strong> \u2013 Direct integration with AgentCore Code Interpreter for more secure Python execution in an isolated sandbox.<\/li>\n<\/ul>\n<p>Try these sample queries to verify the tools are working:<\/p>\n<ul>\n<li>\u201cAnalyze the text: The quick brown fox jumps over the lazy dog\u201d \u2013 The agent should return word count and letter frequency analysis<\/li>\n<li>\u201cCalculate the first 20 Fibonacci numbers\u201d \u2013 Watch the agent write and execute Python code in real time<\/li>\n<\/ul>\n<p>Along with the UI, the provided tools are also meant to be replaced. They exist to demonstrate two different architectures for adding tools (behind AgentCore Gateway as in the text analysis tool, and directly to the agent as in the code interpreter tool) and give you a working starting point. Additionally, the feedback collection mechanism exists to demonstrate how to make synchronous and authenticated HTTP calls through an API Gateway and can seamlessly be removed or repurposed.<\/p>\n<h2>Customize the application to your needs<\/h2>\n<p>What if you need a document analysis agent instead of a chatbot? Or you want to integrate with your company\u2019s existing identity provider? FAST handles exactly this; the baseline application is a starting point, not a constraint.<\/p>\n<p>The following is a recording of a live stream on the <a href=\"https:\/\/www.youtube.com\/@AWSEventsChannel\">AWS Events YouTube channel<\/a> in which FAST is used to build an agentic personal assistant application in real time.<\/p>\n<h3>Changing the agent pattern<\/h3>\n<p>The template includes two agent patterns in the <code>patterns\/<\/code> directory:<\/p>\n<ul>\n<li><strong>strands-single-agent<\/strong> \u2013 A basic conversational agent using the Strands framework with MCP tool integration<\/li>\n<li><strong>langgraph-single-agent<\/strong> \u2013 A basic conversational agent using the LangGraph with MCP tool integration<\/li>\n<\/ul>\n<p>To switch patterns, update <code>backend.pattern<\/code> in <code>infra-cdk\/config.yaml<\/code> and redeploy with <code>cdk deploy<\/code>.<\/p>\n<p>To create your own pattern, add a new directory under <code>patterns\/<\/code> with your agent implementation, a <code>requirements.txt<\/code> file, and a <code>Dockerfile<\/code>. Update the configuration to point to your new pattern.<\/p>\n<h3>Adding new tools using Gateway<\/h3>\n<p>AgentCore Gateway routes tool calls to an AWS Lambda function. To add a new tool:<\/p>\n<ol>\n<li>Create a Lambda function that implements your tool logic.<\/li>\n<li>Define the tool schema (name, description, and input parameters) in the CDK stack.<\/li>\n<li>Add the Lambda function as an AgentCore Gateway target.<\/li>\n<li>Redeploy with <code>cdk deploy<\/code>.<\/li>\n<\/ol>\n<p>The agent automatically discovers tools from Gateway through MCP. See <code>docs\/GATEWAY.md<\/code> for implementation details and examples.<\/p>\n<h3>Using Code Interpreter<\/h3>\n<p>Code Interpreter is already integrated in the baseline agent. It provides more secure Python execution in isolated sandbox environments with session persistence. Users can ask the agent to run calculations, generate data, or execute arbitrary Python code.<\/p>\n<h3>Modifying the frontend<\/h3>\n<p>The frontend is a standard React application in the <code>frontend\/<\/code> directory. AI coding assistants like <a href=\"https:\/\/kiro.dev\/\" target=\"_blank\" rel=\"noopener noreferrer\">Kiro<\/a> are skilled at modifying React frontends. Describe the changes you want and let the assistant implement them.<\/p>\n<p>After making changes, redeploy with <code>python scripts\/deploy-frontend.py<\/code><\/p>\n<p>Because FAST is using AWS Amplify Hosting, you have the option of integrating with a supported version control system to take advantage of the built-in continuous integration and delivery (CI\/CD) capabilities of Amplify Hosting, which can replace the provided <code>deploy-frontend.py<\/code> script.<\/p>\n<h2>Beyond chat: Other use cases<\/h2>\n<p>The baseline application centers around a chat interface, but FAST supports many agentic use cases. For example, a document analysis agent might add a file upload component to the frontend, a Lambda tool that extracts text from PDFs, and agent logic that summarizes findings. Or a workflow automation agent might monitor Slack channels and automatically create Jira tickets from support requests. The same architecture applies, you\u2019re only swapping the pieces. These customizations work within the default architecture of FAST. But what if you need to replace a core component entirely?<\/p>\n<h3>Flexibility: swap out major components<\/h3>\n<p>The architecture is intentionally modular, so you can replace major components as your requirements evolve. Here are some examples:<\/p>\n<ul>\n<li><strong>Identity provider<\/strong> \u2013 Replace Amazon Cognito with Okta, Microsoft Entra ID, Auth0, or your existing OAuth 2.0-compatible identity system<\/li>\n<li><strong>Frontend framework<\/strong> \u2013 Swap the React frontend for Vue, Angular, or integrate the agent backend into an existing application<\/li>\n<li><strong>Hosting<\/strong> \u2013 Move from AWS Amplify Hosting to Vercel, Netlify, a self-managed CloudFront distribution, or your preferred hosting solution<\/li>\n<li><strong>Agent framework<\/strong> \u2013 Use Strands Agents, LangGraph, CrewAI, or an agent SDK even in other languages like TypeScript or Java<\/li>\n<\/ul>\n<p>These are some of the flexibility points FAST offers. The modular CDK infrastructure and decoupled architecture make it straightforward to adapt the template to your specific needs.<\/p>\n<h2>Clean up<\/h2>\n<p>Use the following commands to remove the resources created by FAST:<\/p>\n<pre><code class=\"lang-bash\">cd infra-cdk \ncdk destroy --force<\/code><\/pre>\n<p>This deletes the AWS resources including <a href=\"https:\/\/aws.amazon.com\/s3\/\" target=\"_blank\" rel=\"noopener noreferrer\">Amazon Simple Storage Service (Amazon S3)<\/a> buckets and <a href=\"https:\/\/aws.amazon.com\/ecr\" target=\"_blank\" rel=\"noopener noreferrer\">Amazon Elastic Container Registry (Amazon ECR)<\/a> images. If you leave resources running, you might incur charges for some running resources. Note that Amazon Bedrock AgentCore is pay per use.<\/p>\n<h2>Conclusion<\/h2>\n<p>FAST helps reduce the time to build and deploy an agent application to under 30 minutes. You can get more secure authentication, a working frontend, and integrated AgentCore capabilities\u2014Memory, Gateway, Code Interpreter, and Observability\u2014without writing infrastructure code from scratch. The baseline chat application and sample tools are starting points, not constraints. Swap in your own agent logic, connect your tools, modify the frontend, or replace major components like the identity provider or hosting solution. The modular architecture adapts to your requirements.<\/p>\n<p>To get started, star and clone <a href=\"https:\/\/github.com\/awslabs\/fullstack-solution-template-for-agentcore\" target=\"_blank\" rel=\"noopener noreferrer\">the repository<\/a>, deploy FAST to your AWS account, and have a working agent application running in under 30 minutes. From there, customize and ship something real.<\/p>\n<p>For expert assistance, the <a href=\"https:\/\/aws.amazon.com\/ai\/generative-ai\/innovation-center\/\" target=\"_blank\" rel=\"noopener noreferrer\">AWS Generative AI Innovation Center<\/a>, <a href=\"https:\/\/aws.amazon.com\/professional-services\/\" target=\"_blank\" rel=\"noopener noreferrer\">AWS Professional Services<\/a>, and our <a href=\"https:\/\/partners.amazonaws.com\/\" target=\"_blank\" rel=\"noopener noreferrer\">AWS Partners<\/a> are here to help.<\/p>\n<hr>\n<h2>About the authors<\/h2>\n<footer>\n<div class=\"blog-author-box\">\n<div class=\"blog-author-image\">\n          <img decoding=\"async\" loading=\"lazy\" class=\"alignnone wp-image-123865 size-full\" src=\"https:\/\/d2908q01vomqb2.cloudfront.net\/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59\/2026\/02\/03\/ML-20357-2.png\" alt=\"\" width=\"300\" height=\"338\">\n         <\/div>\n<h3 class=\"lb-h4\">David Kaleko<\/h3>\n<p><a href=\"https:\/\/www.linkedin.com\/in\/david-kaleko\/\" target=\"_blank\" rel=\"noopener noreferrer\">David Kaleko<\/a> is a Senior Applied Scientist at the AWS Generative AI Innovation Center, where he leads applied research efforts into cutting-edge generative AI implementation strategies for AWS customers. He holds a PhD in particle physics from Columbia University.<\/p>\n<\/p><\/div>\n<div class=\"blog-author-box\">\n<div class=\"blog-author-image\">\n          <img decoding=\"async\" loading=\"lazy\" class=\"alignnone wp-image-123866 size-full\" src=\"https:\/\/d2908q01vomqb2.cloudfront.net\/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59\/2026\/02\/03\/ML-20357-3.png\" alt=\"\" width=\"270\" height=\"270\">\n         <\/div>\n<h3 class=\"lb-h4\">Isaac Privitera<\/h3>\n<p><a href=\"https:\/\/www.linkedin.com\/in\/isaac-privitera-b8183a78\/\" target=\"_blank\" rel=\"noopener noreferrer\">Isaac Privitera<\/a> is a Principal Data Scientist with the AWS Generative AI Innovation Center, where he develops bespoke agentic AI-based solutions to address customers\u2019 business problems. His primary focus lies in building responsible AI systems, using techniques such as RAG, multi-agent systems, and model fine-tuning. When not immersed in the world of AI, Isaac can be found on the golf course, enjoying a football game, or hiking trails with his loyal canine companion, Barry.<\/p>\n<\/p><\/div>\n<div class=\"blog-author-box\">\n<div class=\"blog-author-image\">\n          <img decoding=\"async\" loading=\"lazy\" class=\"alignnone wp-image-123867 size-full\" src=\"https:\/\/d2908q01vomqb2.cloudfront.net\/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59\/2026\/02\/03\/ML-20357-4.png\" alt=\"\" width=\"438\" height=\"479\">\n         <\/div>\n<h3 class=\"lb-h4\">Ryan Razkenari<\/h3>\n<p><a href=\"https:\/\/www.linkedin.com\/in\/mrazkenari\/\" target=\"_blank\" rel=\"noopener noreferrer\">Ryan Razkenari<\/a> is a Deep Learning Architect at the AWS Generative AI Innovation Center, where he designs and builds AI solutions for enterprise customers. He specializes in applying generative AI to solve complex business challenges, with a focus on translating cutting-edge research into production-ready systems.<\/p>\n<\/p><\/div>\n<div class=\"blog-author-box\">\n<div class=\"blog-author-image\">\n          <img decoding=\"async\" loading=\"lazy\" class=\"alignnone wp-image-123868 size-full\" src=\"https:\/\/d2908q01vomqb2.cloudfront.net\/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59\/2026\/02\/03\/ML-20357-5.png\" alt=\"\" width=\"418\" height=\"516\">\n         <\/div>\n<h3 class=\"lb-h4\">Monica Raj<\/h3>\n<p><a href=\"https:\/\/www.linkedin.com\/in\/monica-27\/\" target=\"_blank\" rel=\"noopener noreferrer\">Monica Raj<\/a> is a Deep Learning Architect at the AWS Generative AI Innovation Center, where she partners with organizations across industries to architect and deploy production-ready AI solutions. She specializes in agentic AI systems, natural language processing, contact center automation, and intelligent document processing with a focus on building scalable, enterprise-grade infrastructure for customers.<\/p>\n<\/p><\/div>\n<div class=\"blog-author-box\">\n<div class=\"blog-author-image\">\n          <img decoding=\"async\" loading=\"lazy\" class=\"alignnone wp-image-123869 size-full\" src=\"https:\/\/d2908q01vomqb2.cloudfront.net\/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59\/2026\/02\/03\/ML-20357-6.png\" alt=\"\" width=\"374\" height=\"498\">\n         <\/div>\n<h3 class=\"lb-h4\">Davide Merlin<\/h3>\n<p><a href=\"https:\/\/www.linkedin.com\/in\/davide-merlin\/\" target=\"_blank\" rel=\"noopener noreferrer\">Davide Merlin<\/a> is a Machine Learning Engineer at the AWS Generative AI Innovation Center based in Jersey City. He specializes in backend development of AI cloud-native applications, with a focus on API architecture. In his free time, he enjoys playing video games, trying out new restaurants, and watching new shows.<\/p>\n<\/p><\/div>\n<div class=\"blog-author-box\">\n<div class=\"blog-author-image\">\n          <img decoding=\"async\" loading=\"lazy\" class=\"alignnone wp-image-123870 size-full\" src=\"https:\/\/d2908q01vomqb2.cloudfront.net\/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59\/2026\/02\/03\/ML-20357-7.png\" alt=\"\" width=\"542\" height=\"552\">\n         <\/div>\n<h3 class=\"lb-h4\">Brian Zambrano<\/h3>\n<p><a href=\"https:\/\/www.linkedin.com\/in\/brianzambrano\/\" target=\"_blank\" rel=\"noopener noreferrer\">Brian Zambrano<\/a> is a Senior Deep Learning Architect at AWS. He comes from an over 25-year career building software as an engineer and architect. He currently works in the AWS Generative AI Innovation Center where he helps bring customer\u2019s generative AI solutions to life, using his background in cloud architecture, serverless, and event-driven systems. Brian is the author of <em>Serverless Design Patterns and Best Practices<\/em> published in 2018. In his more than 7 years at AWS, Brian has held multiple roles including software engineer, Enterprise Solutions Architect, and Specialist Solutions Architect.<\/p>\n<\/p><\/div>\n<div class=\"blog-author-box\">\n<div class=\"blog-author-image\">\n          <img decoding=\"async\" loading=\"lazy\" class=\"alignnone wp-image-123871 size-full\" src=\"https:\/\/d2908q01vomqb2.cloudfront.net\/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59\/2026\/02\/03\/ML-20357-8.png\" alt=\"\" width=\"515\" height=\"515\">\n         <\/div>\n<h3 class=\"lb-h4\">Anurag Bhagat<\/h3>\n<p><a href=\"https:\/\/www.linkedin.com\/in\/anuragbhagat\/\" target=\"_blank\" rel=\"noopener noreferrer\">Anurag Bhagat<\/a> is Senior Strategist at the AWS Generative AI Innovation Center, where he leads applied AI efforts to help improve business operations for AWS enterprise customers. He comes with 15 years of experience applying AI across industries and functions and is a computer science graduate.<\/p>\n<\/p><\/div>\n<\/footer>\n<p>       <!-- '\"` -->\n      <\/div>\n","protected":false},"excerpt":{"rendered":"<p>https:\/\/aws.amazon.com\/blogs\/machine-learning\/accelerate-agentic-application-development-with-a-full-stack-starter-template-for-amazon-bedrock-agentcore\/<\/p>\n","protected":false},"author":0,"featured_media":4442,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[3],"tags":[],"_links":{"self":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts\/4441"}],"collection":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/comments?post=4441"}],"version-history":[{"count":0,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts\/4441\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/media\/4442"}],"wp:attachment":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/media?parent=4441"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/categories?post=4441"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/tags?post=4441"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}