X in a box every day you do habit — don't break the chain.

Action you repeat 20x daily — turn into meditation in 30 sec.

After any meeting, within 24h: thanks, something enjoyed, concrete next-24h step.

Do not ask "will you be my mentor?". Ask "30 minutes on one specific question" and repeat in a month if it works.

After every answer, ask follow-up — doubles social liking 2x.

Open with "I'm curious about X in your field" — dry chat turns into expertise exchange.

Prep your first mentor meeting with GROW + one single specific question.

Practice asking open GROW questions instead of giving advice in every mentoring meeting.

Design a quarterly give-back ritual for your mentor (written thanks, referral, intro).

Design a 5-mentor board: technical, strategic, life, spiritual, peer.

As mentor: organize a 60-min GROW group session for 4 people.

Use a matrix to match the right mentor with your real need before asking.

Form a peer duo/trio committing to monthly GROW.

Mentor a younger person in new tech/culture, and learn from them in return.

When mentorship phase ends, close it with a gratitude meeting + redefine the relationship.

Identify who is your mentor (teaches) vs sponsor (opens doors) — both crucial.

Design a fixed monthly ritual (call, voice memo, postcard) for a distant friend.

Resolve a friend conflict via a 4-part apology and rebuild trust within 24 hours.

Pick a shallow friend and deepen via 3 of Aron's 36 questions.

Audit your closest 5 via a relationship grid: who adds, who drains, who mirrors your values.

Approach 3 new acquaintances with a specific value before asking for anything.

Organize a monthly meet with neighbors (coffee, breakfast, walk) — builds the "third place" we lost.

Join a new community (mosque, club, org) with the 12-meeting rule before judging fit.

Set explicit community contribution limits: hours/month, task types, exit point.

Ask for donation or support for a community project with "value-first" and a specific story.

Establish a "third place" (not home nor work) for regular meet-ups — café, library, neighborhood club.

Invite one person weekly for a simple 30-min tea — builds community fabric from zero.

Invest 90 passing seconds weekly with a neighbor using one follow-up question that builds cumulative rapport.

Convert your daily meeting to 15 minutes standing, three questions per person, then dismiss.

For one month, measure: how many hours go to "following-up" delegated tasks? Target < 20%.

Define 3 tasks before opening any app — this is what success looks like today.

A 7-milestone Gantt on one page — visible, instantly grokkable.

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

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.

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

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

Ask the model to write a numbered plan first and wait for your approval before executing.

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

Request output as JSON with a defined schema to enable automated processing without manual parsing.

After the model answers, ask it to critique its own answer and improve it before final delivery.

Ask the model to explain a complex idea to a 5-year-old, then raise the level gradually.

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

Do not use AI-sourced info before verifying it in two independent external sources.

The model does not know what happened after its training cutoff. Know each model's cutoff.

RAG (Retrieval-Augmented Generation) fetches real docs for the model before answering. Know the difference.

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

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

Don't pick the first title that comes to mind. Generate 10 with varied angles, then choose the best.

Ask the model to question you instead of answering, surfacing and deepening your understanding.

When an LLM helps you with content you publish or send, disclose it clearly.

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

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

Have the model play expert + student who asks "dumb" questions — extracts tacit knowledge.

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

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

After each output, ask: "What are 3 weaknesses in this answer? How to improve?" — use its intelligence against itself.

Don't repeat instructions every message — set them once in System Prompt, save 70% writing time.

Don't know how to ask? Ask: "What's the best prompt to get X?" — it writes a prompt better than any expert.

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