AI is the most powerful learning tool ever built — if you use it to build understanding, not just get answers. Ask for explanations anchored to what you already know, demand active recall, and use the model to catch gaps in your own reasoning.
The Feynman Technique works better with AI than it ever did alone.
02 Weak vs. Strong
EX 01Learning Kubernetes as a Docker user
I'm a backend developer comfortable with Docker: containers, images, volumes, docker-compose for multi-container apps. I've never used Kubernetes.
Teach me Kubernetes using Docker as the foundation. For every new concept:
1. Tell me what Docker concept it replaces or extends
2. Tell me what specific problem it solves that Docker alone couldn't
After explaining:
- One scenario where Kubernetes is clearly right over docker-compose, with the specific technical reason
- One scenario where docker-compose is still sufficient and Kubernetes would be overkill
Then quiz me: 3 questions to test if I actually understood. After I answer, tell me what I got right, what was partially right, and what was wrong with corrections.
→ Why it works
Anchored to Docker knowledge. Each concept explained as an extension of what's known.
EX 02Understanding compound interest with real numbers
I'm 28, have $12,000 in savings, deciding between a HYSA at 4.8% APY vs. a broad index fund (assume 7% avg annual return). Planning to leave it 25 years.
Explain compound interest using MY numbers:
1. What does $12,000 become in 25 years in each scenario?
2. Year-by-year comparison at years 5, 10, 15, 20, 25
3. What changes if I add $200/month to the index fund scenario?
After, give me the one mental model I can use for the rest of my life to quickly estimate whether compound growth is working for or against me (savings AND debt).
Then: ask me to explain compound interest back to you in one paragraph in my own words. Correct any errors.
→ Why it works
Uses the person's actual numbers. Calculates real outcomes. Asks for a lasting mental model, not just a formula.
03 Key Points
01Anchor to existing knowledge: 'explain X like I already understand Y'
02Ask for a quiz after every explanation — forces active recall
03Use Feynman: explain the concept back, ask AI to correct you
04'What's the most common misconception about this?' — prevents bad mental models
05Ask for the simplest version first, add complexity layer by layer
04 Model-Specific Notes
Claude adapts explanation depth to your stated background and will push back on incorrect explanations. Explicitly ask it to 'point out any errors in my reasoning.'
05 For Your Role
Best learning prompt: 'Explain X, then give me 3 quiz questions.' Forces engagement over passive reading.