In fights, "you always..." is a no-return point. Swap with "today I noticed...".

Short cycles of 25 minutes work and 5 minutes rest that restore focus in a single session.

Reserve a 90-minute deep work block offline and produce quality work that equals an entire ordinary day.

One 90-min deep block produces what a whole day can't.

Each presentation = one takeaway only. Not 3, not 5. One.

Instead of New Year resolutions, pick one "theme" (year of health, year of depth...).

Edit draft Hemingway-style: short sentences, simple words, no flashy adverbs.

Every writing = one CTA. Two = zero.

Reserve a full weekday for deep work and protect it like an unmissable doctor's appointment.

Before starting each morning, write three tasks that, alone, would make the day a success.

Each active project: continue or kill? No "waiting" middle ground.

No more than 3 active goals at a time — with a visible "waiting" queue for the rest.

One number summarizing your product's value to customer — every decision serves it.

Vanity metric always grows and unaffected by decisions — harmful because feels like success.

Each team member: one number owning their core responsibility this quarter.

Every quarter: review dashboard — drop unused, add needed, refresh targets.

Per recurring meeting: "does it produce decision/action?" — if no, kill it.

Find the intersection of what your team loves, what it can be best-in-world at, and what drives the highest return.

Pick two words that summarize the year's priority, replacing many goals with one shared focus.

Pick 1-3 goals max that create real difference, ignore the rest for 6 months.

Instead of a "start-doing" list, build a "stop-doing" list: what activities to cease to free energy for the most important?

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.

Delete any app unopened in 30 days — lose apps before they cost you focus.

Every Friday, empty the desktop: each file goes to its folder, archive, or trash.

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.

Daily 10 min with zero screens (no phone, computer, smart watch) to restore attention.

Block 90 daily min for deep work with no phone, email, or colleagues — with a fixed startup ritual.

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

At any moment, one tab, one window, one task — multitasking is a neural myth.

Every time a switch-temptation hits during work, jot it on a side sheet to address after the block.

Each morning, write a schedule naming what you'll do each 15-min slot — fewer decisions, 2x output.

Flip the rule: notifications off by default, on only during a chosen hour for chosen people.

Each 90-min focus block, enable airplane mode — no signal, no notification, no temptation.

Instead of checking 80 times daily, set 3 fixed times — outside them, don't look.

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?

Every AI claim: search 3 independent sources. If absent from any, treat as hallucinated.