Skip to main content
The single most common way a task configuration goes wrong is duplication: the same limit stated in the specialist prompt, again in special instructions, and again in a quality rule. They drift apart, and only the rule is enforced.
Every constraint lives in exactly one place.

​
The placement table

​
The three-question test

For any new requirement, ask in this order:
1

Must it be enforced?

Then it is a quality rule — deterministic if it can be expressed as a schema constraint or a term list, an AI rule if it genuinely needs judgment.
2

Must it vary by language, brand, or audience?

Then it is a variant field, and possibly a scoped rule alongside it.
3

Is it just context for generation?

Then it is a special instruction — and that is a last resort, not a default.

​
Why special instructions are last

Quality checks never see special instructions. Anything written there is invisible to every check, so it can never be verified.
That makes them right for genuinely unverifiable context — a campaign’s mood, a one-off note about an unusual batch — and wrong for anything you would be unhappy to see violated.

​
Why variants beat prompt text

Variant fields reach the generator and every AI check’s context. Prompt text reaches only the generator. So if a brand’s tone rules live in the specialist prompt, the brand-voice check has no idea what the tone was supposed to be. Put them in the variant and the checker is working from the same brief as the writer.