Cerbere-AG – The layer that ensures security, observability and control, which sits between the AI agent and the real world

Описание и применение

Cerbere-AG обеспечивает безопасность, наблюдаемость и контроль над автономными ИИ‑агентами, используя три слоя: Regex, ML и LLM‑Judge, уменьшая успешность атак и предоставляя аудит‑трейл.

Задача

AI agents act autonomously and can perform unintended or malicious actions, requiring guardrails that balance autonomy with control.

Результат

Cerbere-AG reduces attack success to below 30% with Regex, achieves 100% recall with ML, and resolves ambiguous cases with an LLM Judge, while providing an audit trail for compliance.

Рабочий процесс

• 1. Agent issues a tool call.
• 2. Regex layer filters obvious malicious patterns.
• 3. ML layer classifies remaining calls, raising recall to 100% in tests but flagging uncertain cases.
• 4. LLM Judge evaluates ambiguous cases, considers context, and decides to allow, block, or flag for human approval.
• 5. Collector records spans and traces into an audit trail independent of the agent.

Доказательства

Regex alone lets more than 30% of attacks through.

Источник

ML pushes recall up to 100% in some of our tests, but raises false positives.

Источник

The LLM Judge resolves the ambiguous cases ML can’t classify.

Источник