Run Free With Containers: Parallel AI Experiments Using Dagger + Amazon Q Developer CLI

What happens when you give an AI developer CLI its own sandboxed container? Pure magic, and rainbow sparkles. In this demo, we explore the new container use capability in Dagger, enabling isolated, parallelized environments for agent-driven development right on your local machine. With zero config collisions and no messy local file writes, each environment becomes a safe playground for experimentation. We pair this with the Amazon Q Developer CLI, showing how it integrates with Dagger’s containerized workflows via MCP to create, customize, and test multiple versions of a Flask app simultaneously. From headbanging metal themes to Sherlock Holmes aesthetics, each AI-generated app runs in its own environment with a single command. You’ll see how to: - Set up Q Dev CLI to connect to Dagger’s container use via MCP - Configure trusted container environments for safe agent execution - Use cu commands to inspect, watch, and merge changes from parallel environments - Run multiple AI agents at the same time—without stepping on each other’s toes Try it today: https://github.com/dagger/container-use https://docs.aws.amazon.com/amazonq/latest/qdeveloper-ug/command-line-chat.html