Skip to main content
A task configuration defines one repeatable AI content job. It answers five questions and deliberately leaves out a sixth. That last row is the important one. Because the input is bound at session time, one configuration serves many feeds. Content sources

​
Anatomy

Underneath the editor, a configuration is a JSON document:
output is a fixed value — { "$type": "JSON" } and nothing else. It does not define the output’s shape. The shape contract lives in a JSON Schema quality rule, where it can actually be enforced.

​
Special instructions

Free-text context for generation only — campaign notes, edge cases, one-off guidance.
Quality checks never see special instructions. Anything that must be validated belongs in a rule or a variant, not here.

​
Versions

A configuration is versioned, and exactly one version is published at a time.
1

Draft

Saving creates or updates a draft. Drafts affect nothing that is running.
2

Test

Run a preview session against the draft version and inspect the results — particularly the rejected items, whose feedback names the failing rule.
3

Publish

Publishing makes the version live and names the version it displaces, so rollback is a single action.
Never let publishing be the first time a version runs. Preview first.

​
Every constraint in exactly one place

The most common way a configuration goes wrong is duplication — the same limit stated in the specialist prompt, again in special instructions, and again in a rule. They drift, and only the rule is enforced. Where each requirement belongs gives the placement rule for every kind of requirement.