Collection
Use an AI assistant without outsourcing verification or authority
Give ordinary AI users safe and inspectable data-minimization, prompt-testing, instruction-trust, tool-permission and completion-check habits.
Explore in any order.
What’s included
2 checklists · 4 protocols
6 ideas
Protocol
Strip private material before asking an assistant for help
The most useful example may not need the real names.
Read the idea ChecklistCheck ChatGPT data controls before sharing
Turning off training does not give you permission to share a client secret.
Read the idea ProtocolUse AI to extract questions from a contract, not legal conclusions
A model can help find the question; it cannot promise the answer is legally correct.
Read the idea ProtocolCompare prompt versions on saved test cases
A better answer on one example can hide a new mistake elsewhere.
Read the idea ProtocolRehearse an AI automation with test data
Start with test data and limited permissions.
Read the idea ChecklistCheck what the AI actually changed
A convincing sentence is not the same as a changed system.
Read the idea