Train yourself to notice AI speaks with the same linguistic confidence whether 100% correct or entirely wrong — verbal confidence is not an accuracy signal.

Say no in three sentences: thanks, refusal, closing — with no "sorry" or justification.

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

Say "no, I can't" — complete sentence. No explanation, no apology.

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

Score each initiative Impact x Confidence x Ease (1-10 each), execute by score order.

On day one, hand the new hire a list of 15 decisions they make alone without consulting you.

Score each idea on Impact, Confidence, Ease — pick the highest sum.

2 min in a power pose before meeting/pitch = cortisol -25% + testosterone +20%.

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

State explicitly what you do not want in the output (words, styles, assumptions) to cut later editing.

Learn 4 signals that reveal the model invented info instead of citing documented fact.

Use an LLM to draft an email in 30 seconds, then edit by hand for personal tone.

"Max 80 words, don't use 'innovative', start with imperative" beats "make it short and clear".

Before accepting any AI answer, ask: source? dates correct? names real?

Before using any specific AI-provided fact (number, name, date, quote), apply a 5-question checklist in under a minute.

Before an important negotiation, use AI to simulate the other side's likely responses and rehearse your replies, not to write a script you read verbatim.