I caught myself hoping for magic. That’s when I knew I’d fallen into the trap.
Here’s what happened: I was running playbook generation with two LLMs connected. Iterate, wait, iterate, wait. Felt productive.
Then I actually read the output.
"I don’t think it’s really good... just presenting the data."
The iteration felt like progress. The output wasn’t.
The Pattern
idea
→ iterate with AI
→ stop reading
→ run more cycles
→ hope for magic
→ finally read output
→ meh
You become a spectator hoping the slot machine pays out. AI generates, you wait, nobody thinks.
Why This Happens
I thought the fix was "read after every cycle." But that treats the symptom, not the cause.
The real problem? I couldn’t articulate what was wrong with it. I didn’t hav…
I caught myself hoping for magic. That’s when I knew I’d fallen into the trap.
Here’s what happened: I was running playbook generation with two LLMs connected. Iterate, wait, iterate, wait. Felt productive.
Then I actually read the output.
"I don’t think it’s really good... just presenting the data."
The iteration felt like progress. The output wasn’t.
The Pattern
idea
→ iterate with AI
→ stop reading
→ run more cycles
→ hope for magic
→ finally read output
→ meh
You become a spectator hoping the slot machine pays out. AI generates, you wait, nobody thinks.
Why This Happens
I thought the fix was "read after every cycle." But that treats the symptom, not the cause.
The real problem? I couldn’t articulate what was wrong with it. I didn’t have acceptance criteria. I was iterating because I didn’t know what I wanted.
The iteration trap is really a clarity trap.
- No acceptance criteria - Without knowing what "good" looks like, you can’t evaluate
- Iteration feels like progress - Dopamine hit of activity without cognitive load of evaluation
- Evaluation is harder than generation - Requires a mental model of what you want
- Variable reward schedule - Unpredictable output creates slot machine dynamics
Structural Fixes That Actually Work
1. Define done before you start
Write 2-3 specific criteria for what "good" looks like. Not vibes - concrete checkboxes.
2. Constrain cycles upfront
"I will do 3 iterations max." This forces you to evaluate seriously because you’re spending a finite budget.
3. Externalize the evaluation
After each output, write: "This is/isn’t acceptable because ___." If you can’t fill in the blank, you don’t have criteria. Stop iterating and go define them.
4. Default to single-shot
Treat iteration as expensive. If you need 5+ cycles, the problem is upstream (unclear requirements, wrong tool, insufficient context).
The Test
What would make the next output obviously acceptable or obviously unacceptable?
If you can’t answer that, you’re not ready to iterate. You’re ready to think.
The takeaway: Iteration without criteria is just busy work. The moment you hope for magic, stop. Define what "done" looks like before you start.