Instead of directing reports, give them full context to decide confidently themselves. You do this as leader.

You aren't your thoughts or feelings — you're the context they happen in.

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

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

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

Open the meeting with five minutes of silent reading of a written memo instead of slides.

Consciously decide which platform is purely professional, which is personal, and which is deliberately mixed — instead of unintentional mixing that harms both.

Before any conference, set 3 people to meet and 3 questions for each.

Project first meeting: explicit expectations — scope, date, quality, comms, alarms.

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

For your most critical accounts (main email, bank), move from vulnerable SMS codes to a physical hardware security key (YubiKey or similar).

Set "system instructions" once in your account = every chat starts from your context automatically.

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

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

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

Before judging behavior, imagine context from other's view for 30 sec.

Before asking a high-context colleague for something, reshape your direct ask into a polite hint.

Before a joke with a multicultural group, run it through a filter: does it rely on local wordplay?

Each significant decision: a text file with context, options, choice, consequences.

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

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

Discover the constant "I" that has witnessed every changing thought and feeling.

Group similar tasks into one slot.

Open any writing with Who-What-Where-When-Why-How in one paragraph.

In some cultures "yes" means "I heard", not "I agree" — ask explicitly.

10am and 4pm only. Otherwise: closed. No one dies if your reply takes 2 hours.

Build 3 iOS/Android modes: "Writing" (no notif), "Meeting" (phone only), "Rest" (family WhatsApp).

Each week, use one of your strengths in a new way.

Turn a vague wish into an actionable plan in 15 minutes via 4 steps: Wish—Outcome—Obstacle—Plan.

Turn phone to grayscale — reduces appeal 50%+.

Of 10 demands, 2 deserve 80% of your power. Focus there.

Before tough meeting, declare boundary: "I have only 30 minutes".

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

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

Before reading a colleague's silence in a meeting, ask: is it thinking, respect, or deferred refusal?

KPIs measure business-as-usual, OKRs drive change — don't mix.

When a member delivers excellent results but destroys team morale, separate performance from behavior via a clear standard and a direct honest conversation.

Say firm "no" with warm "I understand" — Janet Lansbury's classic formula.

Read aloud to your child 15 min daily — even after he reads independently.

Discuss drugs/alcohol/sex via questions, not lectures. Curiosity opens when invited, not imposed.

Show the model 2-5 examples of the desired output style so it mirrors the pattern with high precision.

Convert a meeting transcript (60+ min) into decisions and action items in 2 minutes.

Turn a 200-page PDF into a Q&A conversation with exact-quote answers.

Between tasks, take 90 sec of "mental close" before starting next — else residue from prior task drains 40% of focus.

In few-shot, deliberate variety (positive/negative/edge case) matters more than count.

Give the model 2-3 complete input-output examples before your ask, instead of explaining the rule verbally.

Review every app with notification permission on your phone, and ask: does this notification serve me, or the company's engagement metrics?

For any specific statistic AI provides ("73% of people..."), first ask for the precise source, then verify it directly before use.

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

Each major decision: context, options, decision, consequences — one page, sequential.

Use a 4-part frame (Fact, Context, Impact, Path forward) to deliver hard news without sugarcoating or panic.

A simple document everyone signs setting when, where, and how much — ending endless daily negotiations.

First line of email: answer/request/decision. Context after. Cuts read time 70%.

Define 5 contexts where you'll NEVER use AI. Write them. Stick to them.

Define where your "good enough" is on a 0-100 ruler, to know when to stop.

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

You are not obliged to hug or kiss anyone you're uncomfortable with — body-respect phrase.

Delegate each task at one of five explicit levels instead of just "do it" or "don't".

Explicitly write a list of 3-5 tasks you never delegate, and delegate everything else without hesitation.

When you realize you won't meet a past promise, announce it early in a specific format — don't wait until the deadline for the stakeholder to discover it themselves.