After completing AI-assisted work (report, presentation, plan), ask AI itself to attack the work as a strict external critic before submission.

Phrase every goal as "if X happens, I will do Y" — doubles completion rate.

Before sending an emotional message, read it aloud in three tones and adjust.

Before sending, ask: is the content emotional (voice) or informational (text)?

Sort every file you own into just four: Projects, Areas, Resources, Archive.

Write a prompt that gives the AI model precise context, role, task, and expected format.

Assign the model a specific background and expertise so its answer matches a real expert level.

Before believing a "shocking" image, drag it to Google Lens or TinEye to find its true source and date.

In every long message you reply to, quote the specific line/question to make the thread readable.

Instead of rewriting the prompt, say "this part good. this part fix to X". 4 rounds = perfect output.

Before asking AI, paste relevant docs/refs. It answers from "your knowledge", not its imagination.

Before sharing any emotionally charged image (disaster, shocking event), reverse-search it to learn its true source and history.