AI Dungeon Game

Overview

You will build an AI powered dungeon adventure game during this tutorial. This tutorial does not assume any existing knowledge of the @aws/nx-plugin or related technologies. The techniques you’ll learn in this tutorial are fundamental to building any @aws/nx-plugin based application, and fully understanding it will give you a deep understanding of the @aws/nx-plugin and a basic understanding of how to use NX.

Note

This tutorial is designed for people who prefer to learn by doing and want to quickly try making something tangible. If you prefer learning each concept step by step, refer to the individual component Guides

Users who complete this tutorial can expect to walk away with the knowledge to:

• use the @aws/nx-plugin to create new applications
• use NX to manage/build their codebase
• build APIs using both tRPC and FastAPI
• use Tanstack router to create new pages
• use Tanstack query to call backend APIs
• make modifications to generated code to be fit for purpose
• create and deploy CDK infrastructure

What are you building?

In this tutorial, you’ll build an AI powered dungeon adventure game with @aws/nx-plugin.

You can see what it will look like when you’re finished here:

Components of the application

The AI powered dungeon adventure game will be built using the following component architecture:

• tRPC API which uses ElectroDB/DynamoDB for managing the game state
• Python/FastAPI Lambda function with streaming responses for story generation (powered by Amazon Bedrock)
• React/Vite frontend website utilising:
  • Amazon Cognito/Identity Pools for secure API calls
  • Tanstack router which supports type-safe file based routing
  • Generated SDKs for calling the Game and Story APIs (leveraging Tanstack query)
• CDK infrastructure to deploy the application

Prerequisites

The following global dependencies are needed before proceeding:

Required

• Git
• Node >= 22 (We recommend using something like NVM to manage your node versions)
  • verify by running node --version
• PNPM >= 10 (you can also use Yarn >= 4, Bun >= 1, or NPM >= 10 if you prefer)
  • verify by running pnpm --version, yarn --version, bun --version or npm --version
• UV >= 0.5.29
  1. install Python 3.12 by running: uv python install 3.12.0
  2. verify with uv python list --only-installed
• AWS Credentials configured to your target AWS account (where your application will be deployed)

Recommended

• Docker is required for some generators.
• Terraform >= 1.12 is required if you choose to use this for infrastructure as code instead of CDK
  • verify by running terraform --version
• If you are using VSCode, we recommend installing the Nx Console VSCode Plugin.

Tip

If you use an AI Assistant such as Amazon Q Developer, Cursor, Claude Code or Cline, you may also wish to install the Nx Plugin for AWS MCP server.

• Ensure your AWS account has enabled access to the Anthropic Claude 3.5 Sonnet v2 model within Bedrock for your target region via the steps outlined in this guide.