Every two weeks, each member gives one peer specific feedback in a fixed format — no waiting for the annual review.

Disclose vulnerability across 4 escalating levels — full reveal follows proven trust.

Deliver specific SBI feedback to a peer within 48 hours of the event.

Convert mutual critique into a two-way SBI meeting with 5-whys for root cause.

Set a boundary when office gossip starts: "I prefer not to talk about him absent — let's ask him".

Set a loving boundary with your parents around a personal decision (job, marriage, parenting).

Set a joint boundary with your spouse around in-law interference in your home.

Plan holidays 2 weeks ahead: who, where, when, presence boundaries, polite exit.

Distribute home roles clearly: who owns what, without expecting mind-reading.

Open dialogue about a painful family loss via Sue Johnson's emotional questions.

Renegotiate parental expectations (career, marriage, presence) in a calm structured talk.

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

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.

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.

Build a friendship with someone at least 15 years older or younger.

When a text exchange escalates, freeze the thread immediately and switch channels before the next reply.

End a drawn-out text thread with a warm closing line instead of silently fading out.

When talking across generations (a parent, a teen), switch to their preferred channel, not yours.

When someone near you is distressed, lower your own voice and pace first — your calm body lends calm.

After guessing what a close person feels, verify explicitly instead of trusting your hunch alone.

Prepare one line that works for any brief encounter under 20 seconds (elevator, hallway, queue).

Replace "what do you do?" with a question that opens a story, not a dry job title, at networking events.

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

Use one "bridge" question to move dialogue from the surface (weather) to a real shared thread (values, ambition).

When a conversation drops into awkward silence, name it lightly instead of fleeing or pretending it didn't happen.

Don't assume your partner's love language — test it with three situations this week and compare reactions.

Keep 3 ready "repair" phrases to deploy mid-argument before it escalates into emotional flooding.

Every evening, tell your partner one specific appreciation about that day — not a generic recycled phrase.

After both calm down from a conflict, run a structured 4-question dialogue to close it for real, not superficially.

Plan a monthly date with three fixed elements: a new activity, one deep question, no phones.

Open the sensitive money talk with a values question first, not a direct numbers spreadsheet.

Ask each other one simple daily question about the desired level of non-sexual physical touch.

Draw a 5-year timeline together and compare divergence points before they become a sudden collision.

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.