The Wizard
When all you have is a prompt, everything looks like a spell.
The Wizard treats the LLM as an oracle. They ask big, open-ended questions and trust the output because it sounds authoritative. The model's fluency becomes a substitute for understanding, and the team slowly loses the ability to explain its own architecture.
- Symptom
- Architectural decisions justified with 'the model said,' design docs that read like prompt outputs, and a creeping inability to explain why the system is shaped the way it is.
- Why it matters
- When fluency replaces understanding, debugging becomes guesswork and onboarding becomes impossible. The team owns code it can no longer reason about.
- What the chapter gives you
- The questions that puncture false fluency, how to keep the model in an advisory role, and the review prompts that force real reasoning back into the design.
Anti-Patterns
- Archmage of Analysis Paralysis
- Illusionist of Complexity
- Visionary of Grandiose Plans
Artifacts
- Bag of arXiv Ontologies
- Scepter of Infinite Acceleration
- Scroll of Borrowed Fluency
Spells
- Conjure Phantom Architecture
- Polymorph Solution into Microservices
- Summon Expanding Comparison Matrix
- Time Stop (Pending Next Release)
- Wall of Prerequisite Research
From Volume 1 of The AI Developer's Field Guide
Read the full chapter in The AI Developer's Field Guide.
Get the book
Or choose your store:
Recognize this one in your codebase?
The book has the full chapter, the symptoms, and the interventions.