Map / Runtime & Guardrails / White Circle
White Circle
whitecircle.ai ↗ · LinkedIn ↗ · Open on the map
Runtime & GuardrailsAI Red Teaming
Capabilities
Real-time AI control platform sitting between users and models: fully custom natural-language policies enforced across messages, tool calls, and agent actions in under 100ms.
Sensors / integration
Continuous inline inspection of AI inputs and outputs across 150 languages, monitoring for hallucinations, prompt injection, sensitive-data leakage, abusive users, and model behavioral drift.
Protections
Blocks harmful content, prompt-injection attacks, and data leaks before they reach the model or the user; enforces custom natural-language policies across the full agent action surface, with detection models that improve accuracy over time.
Differentiator
Founded by Denis Shilov after a viral single-prompt jailbreak of every major proprietary model; backed by individual AI-safety insiders from OpenAI, Anthropic, DeepMind, Mistral, and Hugging Face rather than institutional VCs, and positioned as the first platform purpose-built to monitor and shape live AI behavior rather than just pre-deployment evaluation; publishes the open CircleGuardBench and KillBench research benchmarks.
Team & funding
- Founders
- Denis Shilov
- Total raised
- $11M
- Investors
- Romain Huet, Durk Kingma, Guillaume Lample, Thomas Wolf, Mehdi Ghissassi, Olivier Pomel, Angels from OpenAI, Anthropic, DeepMind, Mistral & Hugging Face
Other Runtime & Guardrails companies
AariaSec · ActaClad · ActiveFence · Acuvity · AGAT Software · AgentFox · AI Aramid · AI Prompt Shield · Aiceberg · Aim Security · AIR · Aira Security · See all →
Last updated · Get the “Listed on” badge