← All courses

Advanced Claude Code: Designing Loops and Automation

Move beyond one prompt at a time. Learn the four ways Claude Code can keep working without you: turn-based control, goal-driven loops, scheduled automation, and multi-agent workflows — with quizzes to check your understanding.

Log in to start →

Course preview

What you will learn

Explore the full curriculum before you enrol. Lessons unlock after purchase or free enrolment.

01

Loop Thinking

Why 'one prompt at a time' stops scaling, and what a loop actually is

Topics covered

  • The four ways a Claude Code loop can start and stop
  • How to hand off verification instead of checking everything yourself
  • How to set a measurable finish line instead of babysitting every turn
3 lessons5 questions~20 min
02

Manual Control

Turn-based work, self-verification, and /goal

Topics covered

  • Trigger — your prompt.
  • Judge — Claude decides the task is done, or asks you for more context.
  • Best for — short, one-off tasks outside any recurring process.
4 lessons5 questions~25 min
03

Scheduled Automation

/loop, /schedule, and always-on routines

Topics covered

  • Trigger — a fixed time interval.
  • Judge — you cancel it, or the underlying work reports itself finished.
  • Best for — recurring checks or work that depends on something changing externally.
3 lessons5 questions~20 min
04

Dynamic Workflows

Coordinating many agents through a script instead of one at a time

Topics covered

  • Understand what a workflow is and how it differs from ordinary subagents
  • Recognize when a task has genuinely outgrown a simpler approach
3 lessons5 questions~20 min
05

Parallelism & Quality

Choosing the right parallel approach and keeping cost under control

Topics covered

  • Tell apart the main ways of working on multiple things at once
  • Choose based on who's coordinating, and whether the tasks touch the same files
3 lessons5 questions~20 min