White Circle raises $11M to help companies secure and monitor AI model behavior
Artificial intelligence guardrail and monitoring startup Pumpkin Intelligence Inc. , which operates as White Circle, announced today it raised $11 million in seed funding from a who’s who of AI leadership after its founder showed it was possible to break most models with a single prompt. Some of the biggest names in the industry joined the round, including OpenAI Group PBC Head of Developer Experience Romain Huet; Dirk […] The post White Circle raises $11M to help companies secure and monitor AI model behavior appeared first on SiliconANGLE.
Key Takeaways
- SiliconANGLE UPDATED 11:45 EDT / MAY 12 2026 AI White Circle raises $11M to help companies secure and monitor AI model behavior by Kyt Dotson SHARE Artificial intelligence guardrail and monitoring startup Pumpkin Intelligence Inc.
- Today, his company provides a single application programming interface that allows companies to monitor both inputs and outputs to protect them against inbound attacks and monitor outputs.
White Circle employs its own specialized AI models that track inputs and outputs in real time.
- "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.
" According to White Circle, the API can detect a fintech model leaking sensitive data and stop it before it gets out.
- As part of its mission to close the accountability gap, White Circle recently published its KillBench study in which it ran more than a million experiments across 15 AI models.
These included those from OpenAI, Google, Anthropic and xAI to uncover hidden biases.
- These are obvious issues that caught the attention of the media at the time because they were flashy and loud.
Stats & Key Facts
- #, which operates as White Circle, announced today it raised $11 million in seed funding from a who’s who of AI leadership after its founder showed it was possible to break most models with a single prompt.
- #Some of the biggest names in the industry joined the round, including OpenAI Group PBC Head of Developer Experience Romain Huet; Dirk […] The post White Circle raises $11M to help companies secure and monitor AI model behavior appeared first on SiliconANGLE.
- #SiliconANGLE UPDATED 11:45 EDT / MAY 12 2026 AI White Circle raises $11M to help companies secure and monitor AI model behavior by Kyt Dotson SHARE Artificial intelligence guardrail and monitoring startup Pumpkin Intelligence Inc.
- #, which operates as White Circle , announced today it raised $11 million in seed funding from a who's who of AI leadership after its founder showed it was possible to break most models with a single prompt.
SiliconANGLE UPDATED 11:45 EDT / MAY 12 2026 AI White Circle raises $11M to help companies secure and monitor AI model behavior by Kyt Dotson SHARE Artificial intelligence guardrail and monitoring startup Pumpkin Intelligence Inc. , which operates as White Circle , announced today it raised $11 million in seed funding from a who's who of AI leadership after its founder showed it was possible to break most models with a single prompt. Some of the biggest names in the industry joined the round, including OpenAI Group PBC Head of Developer Experience Romain Huet; Dirk Kingma, co-founder of OpenAI, currently working at Anthropic PBC; Mehdi Ghissassi, formerly of Google LLC's DeepMind; and DataDog co-founder and Chief Executive Olivier Pomel.
The company's founder and CEO Denis Shilov went viral in 2024 after he showed that he could jailbreak numerous proprietary AI models on the market with a single prompt. His display showed that he could bypass safety measures on models and unlock instructions for making drugs and weapons, access dangerous or illegal information and extract sensitive information such as ChatGPT's system prompt. Major AI companies such as Anthropic, OpenAI and Hugging Face quickly caught wind of his research, and he built White Circle to capitalize on the need for superior guardrails that protect AI models from prompt injection and jailbreaks.
Today, his company provides a single application programming interface that allows companies to monitor both inputs and outputs to protect them against inbound attacks and monitor outputs. White Circle employs its own specialized AI models that track inputs and outputs in real time. Based on a company's own custom policies, they can detect harmful content, hallucinations, prevent attacks, flag model drift and identify the activity of malicious users.
For more details please read the original article at SiliconANGLE AI.
Continue Learning
Comments
Sign in to join the conversation