White Circle, the Paris-based AI control platform, has raised $11 million in seed funding from a group of prominent investors drawn from the highest levels of the AI industry. Backers include Romain Huet of OpenAI; Dirk Kingma, formerly of OpenAI and now at Anthropic; Guillaume Lample of Mistral; Thomas Wolf of Hugging Face; Olivier Pomel of Datadog; François Chollet of Keras; Mehdi Ghissassi, formerly of DeepMind; Paige Bailey of DeepMind; and David Cramer of Sentry. The funding will be used to accelerate product development, expand the team across the US, UK, and Europe, and grow White Circle’s global customer base.
White Circle was founded by engineer Denis Shilov, who went viral in 2024 after bypassing the safety filters of every major AI model with a single prompt, unlocking the ability to extract dangerous or illegal information from systems, including ChatGPT and Claude, that were explicitly built to refuse such requests. The post drew more than 1.4 million views and led to Shilov being invited to join Anthropic’s bug bounty program. He subsequently built White Circle to address growing demand from AI providers for a purpose-built monitoring and control layer. The platform has now processed more than one billion API requests and is trusted by clients including Lovable and two of the world’s largest digital banks.
White Circle’s proprietary models monitor AI inputs and outputs in real time, detecting harmful content, catching hallucinations, preventing prompt injection attacks, flagging model drift, and identifying abusive or malicious users based on each company’s custom policies. The platform can detect a fintech model leaking sensitive customer data, block an AI agent from executing malicious instructions, flag and ban abusive users, and identify rising user frustration when a model begins to fail. Everything runs through a single API, supports more than 150 languages, and operates across both technical and non-technical teams. The platform is SOC 2 Type I and Type II certified and HIPAA compliant.
White Circle’s research arm has also shaped how the industry understands model risk, publishing CircleGuardBench in May 2025 to test real-world AI moderation performance, and more recently the KillBench study, in which more than one million experiments across 15 AI models from OpenAI, Google, Anthropic, and xAI revealed hidden biases tied to nationality, religion, body type, and other attributes. The research also found that structured output, the standard integration method for production AI, repeatedly caused refusal rates to collapse and biases to amplify.
KEY QUOTES:
“AI is moving faster than our ability to guide it. We already trust it with decisions that touch millions of people – from hiring to healthcare, finance and security – and with the rise of vibe coding, anyone can ship an AI product without knowing what that model is actually doing once it’s live. Until now there’s not been a platform purpose-built to monitor AI’s behaviour, catch it when it goes wrong, or shape how it acts. With White Circle, we’re finally giving companies everything they need to hold their AI accountable and optimise their models in a single place, without sacrificing security, compliance or risk.”
Denis Shilov, Founder and CEO, White Circle
“Denis and the White Circle team have an unusual combination of deep technical credibility and a clear commercial instinct. The KillBench research alone shows what’s possible when you approach AI safety empirically rather than ideologically and the team is building the infrastructure the industry genuinely needs.”
Ophelia Cai, Partner, Tiny VC
