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.

Convert "me vs you" into "us vs the problem" with one question about a shared need.

A 3-hour session that breaks silos between teams and unites them around a goal larger than their own department.

Before a joint project between different teams, hold a "hidden assumptions" session surfacing mutual stereotypes between departments before they sabotage collaboration.

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.

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.

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

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.