How We Keep Stories Safe
Our Safety Promise
We build stories for children aged 3–10. That means we constrain what can be requested and how the AI writes — and we give parents clear controls when something feels off. This page explains what we actually do today, without marketing layers that are not running in production.
We think parents deserve an honest system description, not just a badge.
Why Safety Is Hard for AI-Generated Content
A children's book written by a human author goes through editorial review, publisher guidelines, and age-rating checks. Those gatekeeping steps exist because human language is subtle — something that reads as neutral on the surface can carry an inappropriate implication for a young reader.
AI-generated content faces the same challenge without the same institutional guardrails. StoryKind is tuned for children aged 3–10: age-aware prompts, blocked themes, and parental review tools — not adult social-media moderation alone.
What Runs on Every Story
Pre-generation filter
Before any story is written, we check your child's profile and interests against topics and themes that should not appear in children's stories. The AI is given explicit constraints: it knows it is writing for a child of a specific age, with specific interests, and it is instructed on what is off-limits.
This is not only a blacklist of words — it is a structural constraint on the type of story that can be requested. A child's interest in "fighting games" becomes adventure and problem-solving. A child who lists "sharks" as an interest gets ocean adventures, not horror.
Age-appropriate writing instructions
Every generation call includes system prompts that require kind, age-suitable language and forbid violence, trauma, and other hard-blocked themes. Stories are also aimed at your child's reading level so the language stays accessible.
What we do not claim as always-on today
We have additional automated checks (third-party moderation, a children's-content classifier, and Lexile band verification) in the codebase. Those post-generation layers are not enabled in production until the models and corpora behind them meet our quality bar. We would rather underclaim than imply that every chapter passes four separate automated gates.
If a request fails the pre-generation filter, generation stops and the story is not delivered. Failed or incomplete generations are logged for our team.
Illustrations
Chapter art shares a book style (palette and look) across pages. The hero is described from avatar choices you pick (hair, skin tone, and so on) — not from a photograph of your child. We do not claim pixel-perfect face identity on every page.
Parental Controls
You remain in control of what your child reads. From the parent dashboard you can:
- Report any story — if something concerns you, report it and our team will review it.
- Delete any story from your child's library permanently.
- Update interests at any time to redirect the types of stories generated.
- Review all stories — every story generated for your child is visible in your dashboard, not just the ones they've read.
Staff can also hide or remove stories that fail review.
COPPA Compliance and Data Privacy
StoryKind is designed from the ground up for child safety — not just content safety, but data safety.
We comply with the Children's Online Privacy Protection Act (COPPA) in the United States and are designed to meet GDPR requirements in Europe. We collect only what is necessary to provide the service:
- Your child's first name (never last name)
- Age and reading level
- Interests you select from our list
- Reading history and quiz results
We never collect photographs, school names, precise location data, or contact information about children. We do not share or sell any data about children to third parties for marketing purposes.
A full description of our data practices is in our Privacy Policy.
Questions?
If you have a concern about a story your child received, or a question about how our safety system works, please contact us at [email protected]. We take every content concern seriously and respond within 24 hours.