Emma is not an LLM. It is a bi-directional, deterministic barrier that intercepts, validates, and transforms every turn between the student and the AI assistant.
Emma is strictly positioned horizontally between the client application and the inference model infrastructure (LiteLLM, AWS Bedrock, OpenAI). As a Policy Enforcement Layer, it enforces security guarantees that system prompts cannot guarantee 100% of the time.
firewall_pre module. Personal Identifiable Information (PII) is redacted and prompt injection attempts (jailbreaks) are neutralized.
firewall_post module. If a direct solution is detected (answer leak), the response is blocked and rewritten to a child-friendly, age-appropriate hint.
Test Emma on your own product — sandbox is free of charge.
Request sandbox accessGratuit — 5 000 interactions/mois. Réponse sous 24 h ouvrées avec votre clé API et un exemple d'intégration.