Skip to main content
WC

White Circle

White Circle is a Paris-based company building a unified AI control layer covering safety testing, real-time security enforcement, evaluations, and performance optimisation for production AI systems.

White Circle, founded in 2024 and based in Paris, builds a unified AI control layer that combines safety testing, real-time security enforcement, evaluations, and performance optimization for AI systems running in production. Its platform processes over one billion API requests annually and supports more than 150 languages. The product line includes automated red teaming to surface AI failures, custom low-latency guardrails, behavioural analytics with clustering and custom metrics, and AI optimisation through dynamic prompts and intelligent model routing. Custom policies are unlimited.

The company operates at the intersection of AI safety and AI security, with technical work spanning automated red teaming, LLM guardrails, behavioural analytics, prompt optimisation, model routing, AI evaluation, and multi-language NLP. It holds SOC 2 Type II certification and is HIPAA compliant. White Circle raised $11 million in seed funding and is backed by founders of OpenAI, Anthropic, HuggingFace, Mistral, DeepMind, Datadog, and Sentry.

The company was founded by Denis Shilov, who in 2024 drew wide attention for demonstrating a single prompt that bypassed the safety filters of every major AI model. The firm's stated mission is to secure and control AI systems entrusted with decisions affecting millions of people.

Open jobs

No open jobs right now.

We use cookies

We use cookies to understand how this board is used and to improve it. Analytics run only if you accept. Cookie Policy