A practical course for automation builders

Turn the workflows you already know into agents you can trust.

One prescriptive path from model calls and structured output to tools, MCP, memory, tests, deployment, cost, and cleanup — through a single bounded capstone. Pick a track: deploy it on AWS, or run it entirely locally with OpenRouter and Docker. Same agent, either runtime.

A fixed workflow becoming a bounded agent loop with tools, memory, validation, and human review.

The autonomy ramp

From a fixed rule to an agent you can verify

Each lesson adds exactly one new source of complexity. You start with deterministic code and add model judgment only where fuzzy input earns it.

  1. 1Deterministic workflowExact rules you already trust.
  2. 2Model-assisted stepA model reads fuzzy human input.
  3. 3Structured outputAnswers forced into a typed schema.
  4. 4Tool-using agentThe model calls a bounded read-only tool.
  5. 5Memory and MCPCross-session recall and an external tool.
  6. 6Tested, deployed runtimeEvaluated, deployed, observed — on AWS or your own machine.

Course map

The 11-lesson path

Four ordered stages. Later lessons use only concepts already taught.

Autonomy with boundaries

Freedom where it helps, hard limits where it matters

Build the smallest agent you can verify.

Begin lesson 00 (AWS) →Begin lesson 00 (local) →