Frame, then facts, then structure, then language. Each pass can invalidate everything below it, so reviewing in the wrong order means redoing work — and most people start at the bottom.
- This is where failure rates are structurally highest, because facts appearing rarely in training cannot be reliably recalled — the mechanism is on why AI makes things up.
Reviewing AI output in the wrong order wastes most of the effort. Fix the frame before the sentences, because fixing sentences inside a wrong frame is work you will throw away.
Frame → facts → structure → language. Each pass can invalidate everything below it, so going upward means redoing work. Most people start at language because it is the easiest to see.
Pass 1 · Frame
Before reading a single sentence for quality: is this answering the right question?
- Does it address what you asked, or what it inferred you meant?
- Did it accept a premise in your prompt it should have challenged? A loaded question produces a loaded answer — see how AI influences you back.
- Is anything important missing rather than wrong? Absence is the hardest error to see, because nothing on the page points at it.
If the frame is wrong, stop. Do not fix anything else. Rewrite the brief and start fresh — reprompting inside the same conversation anchors on the wrong frame.
Pass 2 · Facts
Every specific. Names, dates, figures, citations, quotes, technical claims, legal references.
This is where failure rates are structurally highest, because facts appearing rarely in training cannot be reliably recalled — the mechanism is on why AI makes things up.
Check the claims that would be expensive to get wrong, not a sample of the easy ones.
Practical shortcut: anything confident and specific that you did not supply is the highest-risk sentence on the page. Start there.
Pass 3 · Structure
Now that the frame holds and the facts stand, does the argument work?
- Does each section earn its place, or is it there because the format suggested it?
- Is the strongest point buried? Models tend to order by convention rather than by weight.
- Are there three examples where one would do? Padding is the default failure of generated structure.
Pass 4 · Language
Last, and quickly. By this point the frame is right, the facts hold and the structure works — language is the cheapest thing to fix and the least consequential to get wrong.
The one thing worth catching: confident phrasing on uncertain claims. Generated prose asserts at a uniform confidence regardless of how well-supported the underlying point is, so hedging has to be added deliberately.
When to stop
- Cap the passes. Three is usually the point of diminishing return — see loops that degrade.
- Judge against the brief, not the previous version. Comparing to the last attempt guarantees convergence on the last attempt.
- If pass 1 fails twice, the task is wrong for this. Two failed frames is information about the task, not about the prompt.