Ask the model to decompose the problem and show its reasoning before answering, raising accuracy on complex tasks.

Before sleep, write 3 good things and reason for each.

Error defined as system problem not person — unlocks honest info without fear.

Ask the model to "think out loud" step by step before the final answer, especially for logic and math problems.

Run your current thought through the list of ten to pinpoint exactly which mental trap caught you.

For every existing operational process, ask: if we designed it today from scratch, would it look like this?

Before any sensitive decision, ask: if published with full detail on tomorrow's front page, would I defend it with pride or look for an exit?

Add "think step-by-step inside <thinking> tags before answering" — boosts complex-problem accuracy 30-40%.

Every AI claim: search 3 independent sources. If absent from any, treat as hallucinated.

Stop, Investigate source, Find better coverage, Trace claim to primary source. 30 sec exposes 90%.

Don't read a strange site top-to-bottom. Open 5 tabs searching "about" the site, then decide trust.

When you feel strong anger/fear/excitement from a post, stop. It may be engineered for that.

Imagine your decision failed a year from now and write the reasons today — preventing 70% of catastrophes.

For every important decision, log: situation, options, expectation, reason — review after 6 months.

Invent at least three plausible reasons for a behavior that upset you, before you judge.

Name your speaker's feeling and confirm it is reasonable, before you propose any solution.

Close a conversation with appreciation + reason + bridge to next, in three sentences.

Call a friend with no reason once a month and suggest a meet within the next 12 hours.

Imagine the project failed entirely a year from now; list 7 plausible reasons before starting.

Review every account you follow with one strict criterion: does it add real value, or does it drain your mood? Neutrality isn't reason enough to stay.

For every new addition request mid-project, apply one rule: it enters in exchange for something leaving, or waits for the next release.

30 min with a top performer, 5 questions on "why you stay and why you might leave" before they actually consider leaving.

After a major success, hold a structured "after-action review" asking: what exactly did we do right, and how do we deliberately repeat it — not just "what did we get wrong".

Explicitly state your expected response times (not instant) in your signature or status, protecting your time and ending "why hasn't he replied" anxiety.