We turn AI and security research, our own technologies and hands-on expertise into professional security services.
We research AI and security technologies, knowledge use, and collaboration between people and AI. We build tools and systems that strengthen the capabilities of professionals and AI, developing expertise that does not rely excessively on any one model or provider. We put that work into practice through security services.
Move down to go from the outside in through our services, to the research and development at the heart, then on to social contribution.
Professional service
Exposure and attack-surface analysis, investigations and monitoring
What can be seen from outside, and which threats are relevant?
We turn what is happening outside into evidence you can decide on.
We investigate externally visible assets, services, accounts and related threats, analysing their history, relationships and changes. Targeted investigations and monitoring help clients assess risk.
Professional service
Testing that starts from a system, or from a harm you're worried about
Can our vulnerabilities really be exploited, and do our key protections actually hold?
We identify vulnerabilities, exploit conditions and real-world impact in systems and services.
Our experts confirm which paths can really be exploited and what they would mean for the business. Custom validation and red-team or response-capability assessments are scoped separately to suit the engagement.
Learn moreBespoke Security ValidationRed Teaming & Resilience Testing
Professional service
Training, exercises and hacking competitions for people; tailored evaluation and improvement of AI agents
Can our people and AI agents make sound judgements and get real security work done?
People learn by doing and competing; AI agents improve through evaluation.
We build people's security capabilities through training, practical exercises and hacking competitions. Evaluation and improvement of AI agents' task performance and safe operation are delivered as tailored engagements.
Research in AI, security, knowledge use, professional development and people–AI collaboration.
What do we research and build?
At the heart of our services are six research domains in three groups.
We research AI and security technologies and build the knowledge systems, tools and collaborative environments that help professionals and AI work more effectively. We aim to improve the quality and efficiency of security work across different environments, without relying on model capability alone.
Our social contribution programme
Is professional security support out of reach without a budget?
Selected organisations short on budget can cover part or all of the service cost through an agreed social contribution.
The organisations we support then help others in turn, through pro bono work, donations and shared knowledge.
Individual services, integrated assessments, annual care and ongoing collaboration. Every service can be contracted on its own or combined with others.
Integrated assessment
Comprehensive Security Health Check
Where do we stand overall?
We search like an attacker and check like a defender.
We combine relevant expertise around the organisation's environment and priorities. Within an agreed scope, we review its overall security posture and identify key risks and improvement priorities.
Annual programme
Cybersecurity Advisory & Care
Is someone keeping an eye on your security, and there to talk to when you need them?
We check in regularly and help you make the calls that matter.
An annual programme combining the Comprehensive Security Health Check, exposure intelligence, training and expert advice in an agreed service scope.
Custom development · Ongoing collaboration
How do we build what a problem needs when existing tools do not fully address it?
We build the tools and environments your team needs, together with you.
We design and develop security tools, AI models and agents, knowledge delivery systems and collaborative environments for needs that existing tools do not fully address.
SSQ
SAFE SQUARE Service Guide
ClassificationPUBLICCollaboration, services, research and development, and the company, set out as one document. Each service comes with the question it answers, and the sitemap shows every chapter at a glance.
