Describe, Express, Specify, Consequence — a template to disarm any recurring quarrel.

Seven elements that turn a confused request into a clear respectful message that can be refused without breaking the relationship.

Recognize, Allow, Investigate, Nurture — four steps to heal a hard emotion.

Map your boundaries across five layers (physical, emotional, time, material, digital) on a single page.

Frame your stance as: "When [behavior] I feel [feeling] because I need [value] and I request [ask]".

Write four sentences: Describe the behavior, Express the impact, Specify the change, Consequences.

Repeat the same refusal in the same words calmly, no matter how the other person reshapes the pressure.

In unfair criticism, agree only with the "grain of truth" without entering defense.

Say no in three sentences: thanks, refusal, closing — with no "sorry" or justification.

Memorize one 7-word refusal sentence and rehearse it until it emerges automatically under pressure.

If your idea is publicly credited to another, correct the record with three friendly specific sentences immediately.

Instead of "you always...", say "I feel ... when X happens".

When pressured to retract, repeat request calmly same words — don't explain more.

Say "no, I can't" — complete sentence. No explanation, no apology.

Instead of "be better", request "reply to my message within 24h".

When unjustly criticized, agree partially vs confront: "true I was late".

When criticized, ask: "what specifically in X bothers you?" — forces clarity.

In tough confrontation: Describe-Express-Specify-Consequence — four sentences resolve.

You have the right to change your mind without justification — old promise doesn't bind forever.

Before tough meeting, declare boundary: "I have only 30 minutes".

Draw a table: rows = team members, columns = skills, cells = competence 1-4.

You cannot improve what isn't first documented as a standard — document today's best-known method before searching for a better one.

4 steps: Describe (situation), Express (impact), Specify (change), Consequences (outcomes).

Manager crossed a line or made an error affecting you. DESC: Describe, Express, Specify, Consequence. Each in a sentence.

Practice refusing an unethical request clearly and respectfully — before you must in reality.

Use the format "I agree on X, but I see a risk in Y, and suggest Z" instead of silence or unstructured direct opposition.

Don't wait for "he'll grow out of it" — a practical question list turning your vague worry into a specific teacher conversation.

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?

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

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.