Fix · Problems with AI tools

The AI tool keeps stopping to ask permission

What you may see

Every step waits for me to press allow

Most likely cause

The tool is built to ask before actions that change files or run commands; this protects you but slows long tasks.

Check first (about two minutes)

Which actions are asked about: reading, editing, or running commands?

The fix prompt

What you type here never leaves your browser. The search runs on this page, and nothing is sent to a server or to an AI.

The exact error or what you see

What you did before it happened

Kept only in this browser, on this device. Keys and passwords are removed before anything is saved.

Prompt language

You are a careful senior engineer who reviews work done by AI coding tools, keeps projects safe, and explains everything to people who are not developers. I am not a developer, so explain every step in plain words and tell me exactly which button, menu or command you mean. If you are not sure about something, say so; do not guess.

THE PROBLEM
The AI tool keeps stopping to ask permission

THE EXACT ERROR OR WHAT I SEE
[paste the exact error here]

WHAT I DID BEFORE IT HAPPENED
[write in a few words what you did before it happened]

MOST LIKELY CAUSE
The tool is built to ask before actions that change files or run commands; this protects you but slows long tasks.

DO THESE STEPS, IN THIS ORDER
1. Help me set a safe allow-list: allow reading files and running the build and tests; keep asking for deleting, installing, network and git push.
2. Work on a branch and commit before long tasks, so any mistake is easy to undo.
Stop and tell me if what you see does not match a step. Do not skip ahead.

CHECK THAT IT WORKED
- Long tasks run with few interruptions, and risky actions still need my approval.
Tell me exactly what I should see on the screen when it works.

DO NOT CHANGE
- Do not allow everything.
- Anything I did not ask about: the design, the text, other pages, other settings or the data.
- Do not delete files, data or branches, do not reset or force-push, and do not rewrite history, unless you first show me exactly what would be lost and I say yes.
- Do not paste, print or ask me to paste a password or secret key into this chat. If one is needed, tell me which settings page of the right service to store it in.

WHEN YOU FINISH
Explain in simple words what you changed (file by file or setting by setting), why you changed it, and how I can undo it.

Paste it into Claude, ChatGPT, Gemini or Cursor, then follow what it says.

After you tried it, did it work?

Steps

Help me set a safe allow-list: allow reading files and running the build and tests; keep asking for deleting, installing, network and git push.
Work on a branch and commit before long tasks, so any mistake is easy to undo.

Do not do this

Do not work on the live project folder with full permission.
Do not allow everything.

Fix it The AI ran (or wants to run) a dangerous command

Try another entry