AI engineering learning path
Agent engineering
Design workflows, tool contracts, and durable state for tasks that can recover.
Suggested background: basic Python, HTTP, and JSON. The examples focus on engineering boundaries and can be practiced locally.
From taking action to finishing the task.
From taking action to finishing the task.
Chapters
When an agent helps and when a workflow is enough
Decide using control flow, task uncertainty, and failure cost, then separate model decisions from program rules.
Tool calling and MCP still need execution boundaries
Define input, output, error, and permission contracts and practice with an offline tool dispatcher.
Recoverable agents: state, retries, and idempotency
Use SQLite to practice durable task transitions and distinguish conversation history from external side effects.