Digital & AI

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.

Separate prompt parts with XML tags (instructions, examples, document) so the model handles each precisely.

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

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

Ask the model to "think out loud" step by step before the final answer, especially for logic and math problems.

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.

Don't default to the biggest model. Choose by: task depth, cost, privacy, speed.

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 Sunday, unsubscribe from 5 newsletters you did not read this week.

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

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

Do not share any "shocking" news for 24 hours — breaking news is often corrected on day 1.

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.

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

Replace one reused password across 30 accounts with unique long ones, stored in an encrypted manager.

Check all your emails on haveibeenpwned.com to know which breaches exposed your data.

5 signals revealing a phishing message before you click and surrender data.

One strong master password + password manager = more secure than 95% of people.

Email + bank + social + cloud: 2FA required. SMS is weak — use Authenticator app or physical key.

Send delete requests to 10 data brokers — Gulf via PDPL, global via GDPR/CCPA.

Firefox + uBlock Origin + Privacy Badger + DuckDuckGo = strong default privacy.

Before clicking any email link: check full sender, hover URL, urgency, spelling.

Migrate from browser-saved/memorized passwords to a dedicated password manager in one organized session, not gradually over months.

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

Search your name on data broker sites (which sell your info to advertisers) and systematically request removal.

Understand precisely when a VPN actually protects you (public wifi, geo-blocking) versus when it's a security illusion changing nothing (regular browsing while logged into accounts).

Try a full week using a browser (Brave/Firefox) and search engine (DuckDuckGo) that reduce tracking by default, and compare the experience.

Review every app with access to camera, microphone, location, or contacts, and revoke every permission not actually needed.

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

Just as you brainstorm 10 titles, generate 5 different thumbnail/cover concepts, and pick via a small sample, not instinct alone.

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

After a Socratic learning session, ask AI to generate retrieval questions at increasing intervals (1 day, 3 days, a week) instead of relying on random memory.

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

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

Don't subscribe to a new tool before truly using it 14 days in real workflow.

Before adding a new tool, verify it doesn't duplicate a job an existing tool already does — overlap costs more time and money than it saves.

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.

Each month's start, search your name on Google and review the first 3 result pages.

Review your short bio on every platform you use — it should tell the same story, not conflicting narratives that confuse whoever looks you up.

Set 20 shortcuts (e.g., ";eml" types your full signature) to save hours weekly.

Like text shortcuts, build a library of full templates (presentation, simple contract, weekly report) instead of starting from scratch every time.

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

Complement your screen-free meditation with a weekly 20-min nature walk (park, coast, desert) with zero phone — not even for photos.

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.

Each evening, 5 min formal workday shutdown — with a secret phrase ("Schedule shutdown complete") to free your brain.

Daily 10 min in queue/elevator/wait without opening phone — restore your brain's capacity to be bored.

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

Enable grayscale mode — colors designed to addict you vanish, phone becomes just a tool.

Disable all red count badges on app icons — they are engineered to trigger OCD reflex.

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.

Before relying on AI in specialist field, show to human expert — 30% of time uncovers core error.

Any question on recent events/prices/releases: check model training date — ignoring = confident wrong answer.

"According to a 2019 study", "As Academy X stated", "approximate but accurate" — these are immediate-verify flags.

For critical information, ask two different models (Claude and GPT, say) the same question independently, and compare before relying on either.

Before using any reference or quote AI cites (book title, article, study), verify it actually exists before citing it publicly.

Train yourself to notice AI speaks with the same linguistic confidence whether 100% correct or entirely wrong — verbal confidence is not an accuracy signal.

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.

Before deploying AI-generated code, apply a specific security checklist (SQL injection, exposed secrets, input validation) — don't assume it's secure just because "it works".

Delete all "entertainment" apps from phone and laptop for 30 days. After, restore only what's worth.

Every Saturday: no social, no YouTube, no Netflix, no games. Discover how addicted you are.

No phone in bedroom — replace with traditional alarm clock. First and last minute of day = yours.

Every Sunday: no computer, no smartphone (except basic calls/SMS).

Each scroll-urge, execute pre-defined substitute (10 breath cycles, drink water, 5 squats).

Delete social apps (not just deactivate the account) for a full 30 days, with a conscious reintegration plan afterward.

Don't try to stop scrolling through willpower alone — replace the trigger itself (boredom, anxiety) with a predefined alternative action within 3 seconds.

Review every account you follow with one strict criterion: does it add real value, or does it drain your mood? Neutrality isn't reason enough to stay.

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

For 2 weeks, pick just one social platform to use, and temporarily delete the rest — measure the difference in time and mental energy.

Log every time you feel envy or inadequacy after seeing a post — awareness of the pattern is the first step to breaking the deliberately designed comparison trap.

Rule: per email, one decision: reply in 2 min, delegate, defer, or delete. No "later".

Personal rule: no email longer than 3 sentences. Else = call or meet.

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

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

Every 3 months, ask per app: "Does it earn its place on my phone?" — delete without hesitation.

For every new tech, ask: "Do I gain more than I lose?" — most: no.

Phone home screen: 6 tools only (clock, maps, calculator, camera, messages, alerts).

Don't adopt new tech until 6 months post-launch — time exposes flawed vs valuable.

Paper book vs Kindle, paper vs Notes, watch vs phone clock.

Every account you follow builds your feed. Remove harmful, keep building, add teachers.

First Saturday each month, mass-unsubscribe from 20 newsletters/channels/lists.

Don't track news daily. Read one weekly summary (Economist, Atlantic). Gain time and clarity.

Enter YouTube with a specific search topic. Never open the home page.

Every 3 mo, delete history + watched + watch only specific content 1 week. Algorithm relearns from scratch.

When you feel envy after opening Instagram, write: "I see someone's best moments, I live my current one".

"I don't reply on WhatsApp after 10 PM". "No work calls on weekends". — Explicit, firm.

For every 3 important digital chats with someone, schedule one real meeting.

Stop, Investigate source, Find better coverage, Trace claim to primary source. 30 sec exposes 90%.

Don't read a strange site top-to-bottom. Open 5 tabs searching "about" the site, then decide trust.

When you feel strong anger/fear/excitement from a post, stop. It may be engineered for that.

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

Before sharing a statistic or study finding, follow the citation chain to the primary source (the study, official report) instead of trusting whoever relayed it.

Break a big task into 4-6 sequential steps, each a separate prompt + human verification.

Use AI to expand research, summarize, surface angles — then YOU write the final text in your voice.

Explain your problem to the model out loud. You often find the solution while explaining, before its reply.

Feed one model's output to another and request harsh critique. Disagreements expose weak points.

Never write the same prompt twice. Save every successful prompt in a tagged, searchable file.

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

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

Every factual AI claim = ask for a source. No source = don't use.

Before publishing/sending: 5 mandatory verification questions. No exceptions.

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

When delegating a multi-step chained task to the model, define mandatory human-review checkpoints before continuing.

Know when to ask AI to generate new code versus review existing code — the two uses need different prompts and different caution.

Before a big decision, ask AI to surface your biases through questions (not give the answer), then log the decision and prediction for later review.

Whenever a prompt works exceptionally well, save it immediately with a simple tagging system instead of relying on memory or digging through old chats.

Before using any specific AI-provided fact (number, name, date, quote), apply a 5-question checklist in under a minute.

Before executing a major decision, ask AI to attack your plan with the strongest possible arguments — not politely agree with it.

Before an important negotiation, use AI to simulate the other side's likely responses and rehearse your replies, not to write a script you read verbatim.

Write a personal list of situations where you exclude AI entirely — irreversible decisions needing purely human judgment.

Use AI for a bad-fast initial draft, then YOU rewrite completely. Blank page is the killer.

After YOU write, ask AI for 3 improvements only. Don't let it "rephrase".

Identify 5 phrases/words that are "you". Ensure 2+ appear in any AI-assisted text.

"AI text didn't copy anyone" is myth. Ensure you don't publish someone's idea/sentence unattributed.

Every AI claim needs a live source. Never cite a source you haven't read.

In every 60-90 min window: one task, one window, one intention.

After every task-switch, write 2 sentences about previous task before starting new. Clears "residue".

Max 5 browser tabs. Every 6+ = close or save to read-later.

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

For 5 days, log every distraction: time, trigger, pre-feeling. Patterns emerge.

Identify 5 feelings that make you open phone. Per feeling, alternative plan pre-touch.

3-min start ritual + 3-min end ritual = brain signal "now focus / now done".

Block 2-4 "deep work" windows weekly in calendar. Treat like CEO meeting.

Replace all reused passwords in 30 days. One manager, one strong master.

Enable 2FA on email, bank, social, cloud. TOTP not SMS. Backup codes saved.

Every 6 months, download backup from Google/Apple/Meta. Backup + your right.

Every browser extension can read your visible pages. Delete what you haven't used in 30 days.

On public WiFi: always VPN + no banking + 2FA even if feeling safe.

Phone encrypted by default, but your laptop? Check. If stolen, data exposed.

Google your name every 3 months. First 10 results = your identity to the world.

LinkedIn measured by "who contacted with opportunity", not followers or likes.

Same photo across platforms. Refresh every 18-24 months. Natural light, clear face, calm background.

Your bio across platforms says same thing, same tone, same values. Even at different lengths.

For each bad Google result: either delete (if legal) or bury under stronger content.

Review every line in your professional profile — dates, achievements, titles — ensuring it's exactly accurate, not inflated.

When you find a negative or outdated result searching your name, apply a clear protocol: update, request removal, or bury with stronger content.

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

If you discover a fake account impersonating your name or photos, apply a rapid documentation-and-reporting protocol instead of panicking or ignoring it.

Assume every new professional contact will search your name within a minute — consciously design what they'll see in the top 3 results.

Check stats once weekly, not 20 times daily. Production loves silence.

Don't read every comment. Read only questions. Ignore praise & insults equally.

1,000 who trust you > 100,000 who follow. Build trust, numbers follow.

Writer "about everything" = no one follows. Narrow to specific point, expand later.

Publish at cadence you can sustain 2 years, not a month. Daily is great but lethal.

Set a weekly posting ceiling based on your sustainable energy, not on what the algorithm or competitors dictate.

Before any post, ask: "am I writing this because I believe it, or because I think the algorithm favors it?" — constant tension drains content of its honesty.

Set a pre-defined protocol for sorting comments: constructive criticism deserving a reply, or passing hate deserving only ignoring and blocking.

Map your current income — if 80%+ comes from one source (platform ads, one client), you're in real danger at the first algorithm shift.

An audience watches you silently; a community interacts with each other even without you — assess which you're actually building and which serves your goal.

Dedicate one day to producing two weeks of content in advance, instead of the daily pressure to find an idea and post it the same day.

General MOOC completion = 5-15%. To be a completer: split, commit, publish, apply.

Publish weekly what you learn even if not mastered. Public mistakes accelerate correction.

Anki + 20 cards daily = 95%+ lifelong retention. Memory is craft, not gift.

Record 5-min video explaining what you learned to a 12-year-old. Gaps expose themselves.

Yearly: 5 most-impactful books, 3 completed courses, 10 mastered skills. Your learning narrative.

Family sits, writes 7 collective rules about screens. All sign. All accountable.

Before any new app for your child: check 3 things — recommended age, privacy, stranger contact.

Instagram says "13+". Haidt says "16+". Where's your researched stance?

Kids mimic your phone use, not your talk about it. Put device down when they speak to you.

Basket near table. Every phone in pre-first-bite. First to touch washes dishes.

Every 3 months, sit as a family to review your tech agreement — kids grow and rules must grow with them.

Before asking your child to put their phone away at the table, put yours away first — modeling beats any spoken rule.

When your child watches content, watch with them and comment and ask — the difference between a screen that educates and one that numbs is your presence.

Before allowing your child's first social media account, hold a structured conversation (not a lecture) covering privacy, strangers, and social comparison.

Document a list of your important digital accounts and who can access them if something happens to you — account chaos after death compounds grief.

The whole family (parents and children) shares the weekly screen-time report openly — mutual transparency ends the "the rule is just for me" feeling.

Before your next trip, explicitly plan a screen-reduced vacation — deciding in advance is far easier than resisting in the moment mid-trip.

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.