Any program
Explain one feature
Use REA to inspect <program>. Explain how <feature> works, step by step, and show the code or runtime evidence behind each step. List anything you could not confirm.
Tools
Starting points for your next investigation. Replace the parts in angle brackets, paste into your agent, and keep the request to one feature. Why these work
Any program
Use REA to inspect <program>. Explain how <feature> works, step by step, and show the code or runtime evidence behind each step. List anything you could not confirm.
Apps and games
Use REA to find the rule that controls <behaviour> in <program>. Write the rule in plain words, then build a minimal standalone version I can run, and give me one input that proves it matches the original.
Desktop and Electron apps
Use REA on <app>. Start at the <button name> button and trace what happens until the result is written, sent or shown. Name every module or function on the path and what each one does.
Web apps
Use REA to observe <site> while I use <feature>. List the requests, scripts and state changes involved, then summarise how the feature works and which parts run on the client versus the server.
Any program
Use REA to compare <version A> and <version B> of <program>. Focus on <feature>. Show what changed in its behaviour and point to the code differences that explain it.
File formats
Use REA on <program> to work out how it reads and writes <file type>. Describe the structure field by field, show where each field is parsed, and write a small reader that prints a sample file.
Defensive review
I am allowed to analyse <program>. Use REA to find where it stores or sends <kind of data>. Show the code paths, say whether the data is encrypted at rest and in transit, and list concrete risks with evidence.
Getting started
Use REA to give me a map of <program>: its main parts, entry points and the three features worth investigating first. Keep it short and point to evidence for each claim.