ONLINEAGENT_OPS 2026.Q3 HOMEARTICLESBLOGRECORDCRAFTSEARCH
HOMERECORDHow To Ask Ai Well
RECORD · REVISED ON A SCHEDULE

HOW TO ASK AI WELL

Not prompt tricks that expire with the next release. Not prompt tricks that expire with the next release. Sourced, dated, and revised when the numbers move.

◈ THE ONE THING

A model fills every gap you leave with the average of everything it has seen. That single fact explains almost all bad output. Generic in, generic out — not because the tool is weak, but because you asked it to guess and it guessed the most common answer. Everything below is a way of leaving fewer gaps.

Seven habits

HABIT 01
Say what you actually want, including the constraint

Most weak requests describe a topic and hope. Strong ones state the goal, the audience, the length, the thing that must not happen, and what "finished" looks like.

WEAKWrite about our new pricing.
STRONGERDraft a 150-word note to existing customers explaining that pricing rises 12% in March. They are small businesses on tight margins. Do not apologise, do not use the word "unfortunately", and give them one concrete reason the increase is happening.
Why it works: every specific you supply is one fewer gap the model fills with an average.
HABIT 02
Give it something it cannot average

Real examples, actual numbers, your genuine position, the constraint that makes your situation unlike everyone else's. This is the whole difference between output that sounds like the internet and output that sounds like you.

Why it works: the model has read a million generic versions. It has never read yours.
HABIT 03
Ask for the reasoning, then check it

Requesting the steps does two things: it usually improves the answer, and it gives you something inspectable. An answer you cannot check is a claim you have to take on faith.

Why it works: you are turning an oracle into a colleague who shows their working.
HABIT 04
Verify anything checkable and consequential

These systems produce fluent, confident text whether or not the claim underneath is true — and the confidence carries no information about accuracy. Names, dates, figures, citations, legal and medical specifics: check them, every time.

Why it works: it is the one habit that prevents the failure mode that actually damages people.
HABIT 05
Iterate on the output, not the prompt

When something is 70% right, most people rewrite the prompt and start over. Faster: say what is wrong with what you got. "Second paragraph is too soft, cut the last sentence, keep the opening."

Why it works: the model can already see the draft. Editing is a smaller task than generating.
HABIT 06
Decide what stays yours

Before you start, know which part of the work is the part you are for. The judgement, the position, the taste, the responsibility for being right. Hand over the labour, keep the decisions — otherwise you become an editor of things you do not understand.

Why it works: it is the difference between using the tool and being used by it. This is also the whole argument of the last luxury.
HABIT 07
Know what not to hand over

Other people's private information, credentials, anything under confidentiality, anything you would not want retained. Assume input may be stored or reviewed unless you have a written guarantee otherwise, and check what your specific tool and plan actually promise.

Why it works: this is the one mistake with consequences you cannot edit afterwards.

Three ideas worth more than any template

Context beats phrasing. The industry called this "prompt engineering" and the name did damage — it implied secret words. The real skill is supplying the specifics only you have. Context is the craft.

Cheap output raises the value of judgement. When producing a draft costs nothing, the scarce thing becomes knowing which draft is good, and why. That is not a consolation — it is where the work moved. See the silver lining.

The tool has no stake in being right. It will produce a confident answer to a question it cannot answer, because that is what it was trained to do. You are the one who carries the consequence, so you are the one who has to care.

WHY THIS PAGE IS SHORT

This site used to have eleven separate rooms of prompting technique. Most of it was true in 2024 and stale by 2026 — tied to quirks of models that no longer exist. Rather than maintain a museum of expired advice, it is condensed to the part that has not changed: supply context, keep judgement, verify claims. If a technique cannot survive a model release, it was never a skill.

◈ WHERE THIS SITE STANDS

Using AI is not cheating and it is not shameful — the writer does it daily and says so on every relevant page. What matters is disclosure and responsibility: say when a machine did the work, and stay accountable for whether it is true. The people who get hurt in this era are not the ones who used the tools; they are the ones who trusted output nobody checked.