Vindex for family apps

Made for families.
Screened like it.

Story generators, homework helpers, sticker makers, avatar builders: when children are among your users, every prompt needs the strictest reading, and you need to be able to say why a request was refused. Vindex checks each one against your policy before anything renders.

Decisions · family-app policy
Live
AllowedYES64 ms
Dragon reading a bedtime story · nothing fired
ReviewHMM88 ms
Famous footballer on a birthday card · real person · held for review
BlockedNO76 ms
Suggestive outfit request · adult 0.41 · blocked at the family line

Starts from the family-app preset.

The strictest preset Vindex ships. Adult content is blocked above level one, at lower thresholds than any other preset. Real people and copyrighted characters are held for review instead of waved through, and youth-coded adult content is blocked outright rather than sent to a person.

  • ✓ Every line is yours to move, except the minors line
  • ✓ Every decision explains which checks fired and why
  • ✓ Dry-run any policy change on live traffic before you enforce it
Policy · family-app
preset
Adult content
Allowed up to level 1 of 5, blocked above
Minors, any sexual context
Cannot be changed · borderline: blocked
BLOCK
Youth-coded adults
Stated adult, presented young
BLOCK
Real people
Named or described · borderline: tagged
REVIEW
Copyrighted characters
Characters, brands, artist style · borderline: tagged
REVIEW

The risk: the one screenshot a parent sends.

Family apps are judged on their worst output, not their average. One inappropriate image in front of a child is a one-star review, an app store complaint and possibly a news story. The family-app preset reads prompts at lower thresholds than any other preset, blocks youth-coded content instead of asking a person to judge it, and every block says which check fired and against which line, so you can answer a parent plainly.

Ready when you are

See your own prompts scored, live, in twenty minutes.

Bring a hundred prompts you've argued about internally. Start the trial and run them yourself to see where your policy line actually sits.