Introduction to the series
Throughout this article series, we'll develop a simple application to show how to build multi-step applications and orchestrate workflows using AWS Lambda durable functions. For it, we'll explore the AWS Lambda Durable Execution SDK for Java. This simple application provides the functionality to extract the content for the provided user. This content involves searching for YouTube videos of the authors and their upcoming talks. We'll store the result on Amazon S3 Files in JSON format. As this operation may potentially take time, we'll additionally provide access to the author content through the Amazon API Gateway:
- We'll start with the simple application to search for YouTube videos and upcoming talks of the author synchronously. First, we'll use durable steps and then later add waits and callbacks. We won't implement any persistent layer and store the static content in memory.
- We'll then improve our application by adding asynchronous communication where it makes sense. For example, searching for YouTube videos and upcoming talks can be done in parallel.
- We'll then further improve our application by converting the AWS durable function to a pure orchestrator. This means we'll move the business logic for searching for YouTube videos and upcoming talks into separate Lambda functions. With that, our Lambda durable function will invoke those separate Lambda functions in parallel and combine the results
- Finally, we'll further extend our application to use Amazon Bedrock AgentCore Web Search Tool to search for the author content on the web. With that, our Lambda durable function becomes an orchestrator of the agentic AI workflows. As we'll use Java in this series, we'll explore how to run this business logic responsible for the Amazon Bedrock AgentCore Web Search Tool. As this tool is exposed as an MCP tool by the Amazon Bedrock AgentCore Gateway, we need a framework capable of providing AI functionality and supporting MCP. That's why we'll use Spring AI. As 2 operational environments for our agentic AI workflows, we'll explore an AWS Lambda function and Amazon Bedrock AgentCore Runtime.
You can find the code examples in my aws-s3-files-lambda-durable-functions-java-sdk repository. We'll go through all the examples in more detail in the subsequent articles.
Introduction to the services used throughout the series
Throughout this series, we'll use the following AWS services:
AWS Lambda durable functions. With Lambda durable functions, you can build resilient multi-step applications and AI workflows. These can execute for up to one year while maintaining reliable progress despite interruptions. When a durable function runs, this complete lifecycle is called a durable execution, which uses checkpoints to track progress and automatically recover from failures through replay, re-executing from the beginning while skipping completed work. Within each function, you use durable operations as fundamental building blocks. Steps execute business logic with built-in retries and progress tracking. Waits suspend execution without incurring compute charges, making them ideal for long-running processes. These processes include human-in-the-loop workflows or polling external dependencies.
Amazon S3 Files. S3 Files is a shared file system that connects any AWS compute resource directly with your data in Amazon S3. It provides fast, direct access to all of your S3 data as files with full file system semantics and low-latency performance, without your data ever leaving S3. Every file-based application, agent, and team can access and work with your S3 data as a file system using the tools they already depend on. Built using Amazon EFS, S3 Files gives you the performance and simplicity of a file system with the scalability, durability, and cost-effectiveness of S3. You can read, write, and organize data using file and directory operations. At the same time, S3 Files manages the synchronization of changes between your bucket and file system.
We'll also introduce in the later parts of this series the following Amazon Bedrock AgentCore services or features: Gateway, Web Search Tool, and Runtime.
If you like my content, please follow me on GitHub and give my repositories a star!
Please also check out my website for more technical content and upcoming public speaking activities.
Top comments (0)