Explainable Results
Understand exactly why text was flagged and which indicators affected score and action.
Protect your users and platform with transparent moderation scoring. No opaque AI. No vendor lock-in. Built for developer teams today, with enterprise-ready architecture from day one.
Weighted terms, phrase matching, directed abuse detection, threat indicators, and anti-evasion normalization.
CPU-friendly signal enrichment for nuance and context without heavy external dependencies.
Each call returns severity score, policy action, category flags, explanations, and matched indicators.
Understand exactly why text was flagged and which indicators affected score and action.
Adjust thresholds, allowlists, and custom terms by tenant or product.
Start free, scale with usage, or move to subscription with included usage and overage.
Deploy on UK/EU infrastructure with straightforward operational control.
Single endpoint and clear schema for fast adoption in chats, forums, and community features.
Predictable responses designed for policy workflows and moderation tooling.
Low-latency moderation endpoint, API key auth, quota enforcement, and deterministic explainable scoring outputs.
Usage records and plan controls live in our database; billing providers handle charging but not business logic ownership.
Self-serve plan management with explicit overage controls and clear monthly/annual billing behavior.
Aegis Core API is positioned for developer growth first while maintaining a clear path to enterprise controls, SLA process, and audit-oriented operations.
Company registration: Scotland (SC754701)