I Migrated My AI Agents from Azure to AWS — Here's the Minimal Setup You Actually Need

After migrating my agent-based document processing system from Azure to AWS, one thing became obvious: Most cloud setups are wildly over-engineered for development. You don’t need half the services people default to just to build and test a distributed system. Here’s the minimal AWS architecture you actually need to develop and run an agent-based pipeline end-to-end — plus what each piece maps to if you’re coming from Azure. If you want a slightly punchier, more viral version: After moving my agent-based document pipeline from Azure to AWS, I realized something: We massively overbuild cloud setups in dev. You don’t need Kubernetes. You don’t need a dozen managed services. You don’t need a $100+ monthly baseline just to iterate. What you do need is a small set of core primitives. Here’s the minimal AWS stack that lets you fully develop and test a distributed, agent-based system — and how it maps from Azure. The System Before we even touch the cloud layer, here’s what’s actually running.