Replace vague "good job" with specific praise describing: what he did, impact, why it matters.

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

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

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

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

When pulse passes 100, call a 20-min time-out — physiology needs time.

After a fight, don't wait — a small repair gesture within 24h saves the bond.

Deep in conflict, ask: "What is the shared need we are both trying to meet?"

Name the act, acknowledge impact, commit to change, ask for repair — an apology that mends.

Count vendors per category — consolidating 2 similar drops price 15-25%.

Don't pick vendor "by gut" — score on 6 dimensions with weights, pick by points.

Good RFP defines what you need precisely + selection criteria — not "send anything".

Before signing: 12 red flags that may cost thousands later.

90 days into contract: review with vendor — don't wait for renewal to find issues.

Before renewing expensive vendor: compute real switch cost — may be less than you think.

Before signing: exit options? notice? penalties? data handoff?

When stakeholder A wants X, B wants opposite: don't pick — surface underlying interests.

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

Teams with high psychological safety perform 4x better. This exercise measures and raises it in your team.

A small "innocent" comment wounds an employee. Your job as leader: interrupt immediately, respectfully, without trial.

Review your team's last 20 decisions (promotion, project, leave). Who gained? Who lost? Pattern reveals bias.

Your small leader words exclude or include. 10 simple swaps shift your team's culture in 60 days.

When joining a new manager (or they join you), give them YOUR user manual. How you work best? What annoys? What you need?

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

You decided to leave. The last 30 days define your reputation for 10 years. This frame protects bridges.

When sensing conflict of interest, declare it before discussion begins.

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

Instead of "great job," describe exactly what he did — "I love how you split the problem into two steps."

When you wrong your child, fully apologize: what you did, its impact, the change.

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.