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?

Starting

The prompt that stops a builder making the wrong app

How do you describe an app to an AI builder so it builds what you actually wanted?

Debugging

The prompt for an error you do not understand

What do you do when an AI builder shows an error message you cannot read?

Safety

The prompt that finds keys your visitors can read

How do you check whether your API keys are visible to visitors in an AI-built app?

Screens

The prompt for the screens nobody designs

Why does an AI-built app look broken when there is no data yet?

After launch

The prompt that tells you when your app fails

How do you find out that your app is broken before a customer tells you?

Design

The prompt that stops a site looking generated

How do you make an AI-generated website not look AI-generated?

Planning

The prompt that gets a plan before any code

How do you make an AI coding agent plan the work before it starts writing code?

Selling

The prompt for deciding what to charge

How do you decide what to charge for software you built yourself?

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?

Setup

The prompt that sets a project up for an agent

How do you set up a project so an AI coding agent works well in it?

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?

Money

The prompt for adding payments safely

How do you add payments to an app without handling card details yourself?

Safety

The prompt that stops an agent obeying text it finds

How do you stop an AI agent following instructions hidden in files or web pages it reads?

Understanding

The prompt that makes an agent read before it writes

How do you get an AI coding agent to understand a codebase before it changes anything?

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?

Changing

The prompt to ask before you change anything

How do you change something in an AI-built app without breaking the rest?

Data

The prompt that tells you what your app is collecting

How do you find out what personal data an AI-built app is actually storing?

Handover

The prompt that makes an agent document what it built

How do you get an AI agent to write documentation for the code it just produced?

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.

The Short Version

Every conclusion from all eight playbooks, condensed. Free, and it names which prompt to reach for.

PDF to your inbox, then three short emails on where to start. Reply “stop” to end them.