Search & explore

• Level L03
• T01
• 19 min read

Choose between chat, a saved prompt, an automation, a small app and an agent for a job colleagues depend on. Pick the lowest rung that meets a named requirement, then give it a known-answer test, a README, a pinned version, a maintainer and a deputy, and prove a colleague can run it.

Matching textT01-L03 · Foundations & judgement · Level 3 Builder · 16-minute read, plus 3 hours of doing Build the Smallest Thing Your Colleagues Can Run Without You The app that worked for four weeks A

• Level L02
• T01
• 15 min read

Once colleagues act on your AI-assisted work, a wrong number or a dropped condition travels. Sort output by where it goes, run a five-step check on anything that leaves the team, and attach a short check note so a colleague can trace every claim without asking you.

Matching textT01-L02 · Foundations & judgement · Level 2 Power user · 13-minute read, plus 30 minutes of doing Check AI Output Before Your Team Relies on It The summary three people used A postdoc asks

• Level L01
• T01
• 12 min read

Learn the four-quadrant method: Structure it, Understand it, Choose tools, Build it. Take one real task from your week to a first working result, and learn what AI assistants can and can't do along the way.

Matching textT01-L01 · Foundations & judgement · Level 1 User · 11-minute read, plus 30 minutes of doing From Idea to Working Result: The Four-Quadrant Method Two colleagues, same tool On Monday a colleague…

• youtube

Start with simpler workflow fundamentals before agents. n8n learning roadmap; includes commercial promotion; not the complete tool-selection ladder.

Matching textT01-L03: See why learning fixed workflow fundamentals comes before building agents. This n8n roadmap supports the book's start-simple principle, not its complete selection ladder or maintenance…

• youtube

Choose what to delegate based on the problem and available capabilities. Conceptual companion, not the curriculum's four-quadrant method.

Matching textT01-L01: Think through the problem, the available capabilities and what to delegate to AI. This complements the book's four-quadrant method; it teaches a different framework.

• youtube

Critically assess AI output rather than accepting fluent answers. Does not teach the exact five-step source-line checking routine.

Matching textT01-L02: Learn to assess an AI answer and recognise when its behaviour needs correction. Use the book's five-step routine for tracing claims back to their sources.

One-page diagram to use with T01-L03, "Build the Smallest Thing Your Colleagues Can Run Without You".