Ignis Algos
All case studiesConsumer AI · Safety

Shipping a child-safe LLM at scale

Shipping an LLM to children requires re-thinking the safety stack from scratch.

Client: Series A consumer AI 14 months 4 engineers, 2 safety researchers, 1 designer

The problem

The client came to us with a working LLM demo and a 6-month-old safety review document. Their first attempt at a kids' product failed an internal review: the model could be tricked into discussing violence with age-inappropriate framing, and the parent dashboard was a buried afterthought.

We were hired to redesign the entire stack — model guardrails, conversation storage, parent controls, and the kid-facing UX — and ship a version that could pass both COPPA and GDPR-K audits while still feeling delightful to a 7-year-old.

Approach

  • Built a layered guardrail system: a fast classifier screens every turn before it reaches the LLM, a topic-blocklist layer catches known-bad patterns, and a secondary model reviews the LLM's output before it reaches the child
  • Designed a parent onboarding flow that explains the tradeoffs honestly — what Mia will and won't do, what data is stored, how to delete it
  • Shipped a parent dashboard with conversation history, daily time budgets, and topic boundaries configurable per child
  • Implemented end-to-end encryption for conversation history with parent-held keys

Key technical decisions

Layered safety, not a single gate

A single classifier with 99% accuracy is the wrong architecture for child safety — that 1% becomes 1 in every 100 turns. We run 3 independent layers, each with different failure modes, and any one can block a turn.

Topic boundaries configurable per child

A 7-year-old and a 12-year-old need different guardrails. Parents set per-child policies; the model is told which policies are active at the start of each conversation via a system prompt.

Encryption with parent-held keys

COPPA wants minimal data collection. We store less by encrypting conversation history with a key only the parent's device holds. The servers see ciphertext; even a server breach leaks nothing readable.

Outcome

< 0.4%
Guardrail false-positive rate
passed
COPPA + GDPR-K audit
62%
Daily active rate (7-day)
4.7 / 5
Parent-reported trust score
2 (FT)
Engineers on safety team

Stack

TypeScriptNext.jsPostgreSQLOpenAI APIReact NativeAWS KMS