Skip to content

Control user and model behavior in real time

Get StartedRequest a Demo

Test

Discover failure modes before your users do

Control

Enforce behavior across inputs, outputs, and tools

Analyze

Understand how your users and AI behave over time

Improve

Tune prompts and models from live signals

“White Circle protects millions of AI interactions every day while helping us move faster.”

Igor Andriushchenko, CISOLovable
Read case study
Backed by leaders across the AI ecosystem

Romain Huet/Head of DevExp

Justin Bleuel/PM of ChatGPT

James Dyett/ex-Head of Sales

Durk Kingma/ex-Cofounder of OpenAI

Zach Gleicher/Research PM

Thomas Wolf/Cofounder & CSO

Guillaume Lample/Cofounder & CSO

Paige Bailey/Head of DevExp

Petra Grutzik/PM of Gemini

Mehdi Ghissassi/ex-Head of Product

Karl Tuyls/ex-Research Director

Olivier Pomel/Cofounder & CEO

David Cramer/Cofounder & CPO

Francois Chollet/Cofounder

White Circle works for your entire AI lifecycle

Alert sent to #security — rm -rf / flagged for review

Session terminated — rm -rf / never reached the shell

Your agent is trying to run  rm -rf /
Do you want to continue?

Define policies

Describe how AI and users should behave across safety, security, compliance, and reliability.

Constrain behavior

Automatically block, rewrite, or escalate risky behavior in real time.

Audit decisions

See what happened, why it happened, and which policies were triggered.

See the bigger picture

Explore how everything fits together and collaborate with your team

Adapt to every region

Apply different policies based on a user's location or jurisdiction.

Contact Sales

Blocked
 
Restricted
 
Allowed
 

  • Prompt injectionHidden instructions ignored

  • Leaking sensitive dataSecrets, personal data

  • Unauthorised paymentsHeld for approval

  • Attacking other systemsNo scans, no exploits

  • Destructive actionsHeld for approval

  • Child safetySexual content involving minors

  • Fabricated citationsChecked against sources

  • Acting beyond the taskOnly what was asked

Control every AI interaction

Monitor behavior, apply safeguards, and improve AI systems in real time.

input
unsafe inputs blocking
jailbreak prevention
PII detection
model call
model call

Built for production AI

Real-time protection, analytics, and optimization
for teams shipping AI at scale.

Go to Trust Center ↗
SOC 2 Type ISOC 2 Type IIHIPAAISO 27001:2022

99.99%

Our API uptime

5mins

Time to integrate our API

150+

Supported languages
Unlimited custom policies

One control layer, every industry

Research

The systems, methods, and experiments that shape how we build and safeguard AI products.

Breaking Frontier Image Models Without Frontier AI

Breaking GPT-Image-2.5, DALL·E 3, and Nano Banana 2 with an open-source attacker and an off-the-shelf judge.

Read

Halo: Frontier-Lab Training for Everyone

Open-source distributed training for Hugging Face models, without leaving the ecosystem.

Read
Red-teaming · October 2026Read

RISE: Red-teaming via Iterative Strategy Evolution

A calibrated, strategy-level approach to red-teaming production text-to-image models.
Research · April 2026Read

KillBench: discovering hidden biases of LLMs

Evaluating decision-making biases across frontier AI models.
Research · May 2025Read

CircleGuardBench: Evaluating AI Moderation Models

Measuring the real-world performance of AI guardrails.
Fine-tuning · September 2026Read

GLM-4.7-Flash-Coder

We fine-tuned GLM-4.7-Flash from 33.15% to 41.65% on SWE-rebench-V2, at 14% lower inference cost.
Preprint · OptimizationComing soon

Hat-Muon: Communication-efficient distributed training methods

Making large-scale training more bandwidth-efficient.
InfrastructureComing soon

Custom kernels for Blackwell B300

New building blocks for model training on modern GPUs.
TrainingComing soon

Offline GRPO at scale

Making reinforcement learning more practical for production models.

Want to deploy AI agents safely?

Control AI behavior in real time with White Circle

Get StartedRequest a Demo