02 / The Workshop
The Workshop
So there's this thing called chain of thought reasoning. Sounds technical, but it's really not. All it means is: if you tell the AI to think through something step by step before it answers, the output gets noticeably better. More structured, more complete, less hand-wavy.
That's it. You add "think through this step by step" to whatever you're asking, and you get a different quality of answer back. Not a little different. I ran the same prompt both ways below using "compound interest" as the topic. See for yourself.
Example 1 — Standard Prompt
I'm at a beginner level.
Teach me the core idea, show me a real example, and tell me what most people get wrong.
Example 2 — With "Step by Step"
I'm at a beginner level.
Think through this step by step, then teach me the core idea,
show me a real example, and tell me what most people get wrong.
Real example: You invest $1,000 at 5% annual interest, compounded yearly.
Year 1: $1,000 × 1.05 = $1,050
Year 2: $1,050 × 1.05 = $1,102.50
Year 10: $1,628.89
Year 30: $4,321.94
You put in $1,000. You got back $4,321. $3,321 of that was interest earning interest. The growth isn't linear. It's a curve that accelerates.
What most people get wrong: They focus on the rate and ignore the time. The difference between starting at 25 vs. 35 is bigger than the difference between a 5% and 8% return. They also forget that compound interest works against them on debt. Credit card balances grow the same way, just in the wrong direction.
The more you use these tools, the more you start to notice what makes a good output vs. a lazy one. This is one of those small things that makes a big difference.