WZ Vault › Prompts

Prompts that make an AI agent behave

Getting code out of an agent is the easy part now. These are the prompts for the other part: keeping it on the change you asked for, making it prove its work, and catching what it got wrong before a client does.

Building

The prompt that stops an AI agent touching everything

How do you stop an AI coding agent from refactoring or changing files you did not ask it to?

Dependencies

The prompt that catches a package your AI invented

How do you check whether an AI coding agent invented a package that does not exist?

Verifying

The prompt that makes an AI agent prove its code works

How do you verify that code written by an AI agent actually works?

Debugging

The prompt that stops an AI agent going in circles

What do you do when an AI coding agent keeps trying fixes that do not work?

Security

The prompt to run before any app with a database goes live

How do you check whether your database is exposed before launching an app?

The full packs

The pages above are a handful of the prompts I use. The packs are the whole set, each with the same reasoning underneath, plus the research behind them and a house-rules file you paste into your agent once.

Pack · €9

The Build Prompt Pack

57 prompts for browser builders, plus the six doors that get vibe-coded apps breached.

Pack · €9

The Operator Prompt Pack

60 prompts for working with an AI coding agent, built around the three things it measurably gets wrong.