Before pasting anything in AI: redact names, numbers, emails, financial data.

Every AI reflects training-data biases. Check: gender, culture, economic class.

In academic/professional: state when AI used. Transparency protects + builds trust.

Don't ask AI "write in author X's style". That = using their commercial style sans permission.

For each task automated with AI, ask: "Freed for higher value, or replaced my learning?".

AI = info-gathering tool. Personal decisions (marriage, career, medical, friendship) = human decides.

Identify the living values you want guiding behavior across ten life domains.

Place each thought on a leaf and watch it drift down a stream.

Prefix every thought with "my mind is telling me..." to see you are not it.

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

Define one action today expressing a value, even if opposing thoughts show up.

Open your hand to uncomfortable feelings instead of clenching — and watch them soften.

Hear what you wish would be said of you in 50 years to learn what matters today.

You're the bus driver, your thoughts are noisy passengers — drive despite their voices.

Ask yourself the single question that distinguishes real decisions from distractors.

Goals end; values are perpetual direction — confusing them loses you.

You're the bus driver. Hard thoughts are noisy passengers, but you stay on the road.

Imagine an inner switch — when on, suffering doubles. Can you leave it off?

Open space for hard sensation in your body instead of suppressing or fleeing.

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

Willingness to accept reality as is, not willfulness rejecting it — subtle but powerful.

Morning: pick one value to live today. Evening: rate yourself.

No paralyzing "big plan" — one tangible action aligned with your value within 24 hrs.

At your funeral in 50 years, what do you wish people said? Start it today.

Thoughts aren't facts or orders — guests passing through.

Physical pain doesn't obey resistance — it softens with conscious acceptance.

Values are roots, behaviors are leaves — draw your tree.

Each team member: annual signature on disclosure of relationships affecting decisions.

In crisis: one person leads, all report to them, fast decisions — not "committee".

From 30 values, pick only 5 — very hard but reveals what truly matters.

Identify 5 core values and verify your decisions actually reflect them.

Before ethically murky decision, evaluate on 4 axes: legal/ethical/values/reputation.

Set clear policy: which decisions will never be delegated to AI in your team.

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.

Don't paste contracts, health data, or IP into a public model — may appear in later training.

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.