PlanetArchitecture
Back to AI Fluency
L1

Prompter

Single-turn prompts, high rework rate

Characteristics

Approach

Single-turn, copy-paste prompts

Turns per task

10-20

Mental model

AI as search engine or autocomplete

Error response

Re-prompt with slight variations

Impact

Requests per feature

15-20 requests for a single feature

Rework rate

High rework rate (60%+)

Context quality

Context window wasted on corrections

What It Looks Like

User: "Write a function to validate emails"
AI: *writes function*
User: "Make it also check for disposable domains"
AI: *rewrites function*
User: "Add tests"
AI: *writes tests*
User: "The tests are failing"
AI: "Let me fix that..."
User: "Now add it to the user service"
AI: *adds to service*
User: "It broke the existing tests"
...continues for 15+ turns

Common Patterns

  • No context provided upfront
  • Each turn is a new thought
  • Frequent "actually, I also need..."
  • Debugging by describing symptoms
  • Never uses skills or structured workflows

How to Level Up

The shift

Stop treating AI like a search engine.

Practice
  • 1.Before your next prompt, write down what you're building
  • 2.Include the technologies you're using
  • 3.Describe what constraints exist
  • 4.Define what success looks like
  • 5.Include all of this in your first message
Skills to learn
None specific — just better prompting
Measure success

Did your turns drop from 15+ to 10?