Dissect the thought: evidence? Real ratio? What are others actually doing?

Before writing, describe reader in 5 sentences: age, job, knows, doesn't know, decision he makes.

Who influences whom? — draw network to know "who talks to whom to shift decision".

Before people-affecting decision, identify 3 potential biases and create a shield for each.

Assign the model a specific background and expertise so its answer matches a real expert level.

Learn 4 signals that reveal the model invented info instead of citing documented fact.

Don't repeat instructions every message — set them once in System Prompt, save 70% writing time.

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

Every AI reflects training-data biases. Check: gender, culture, economic class.

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.