Advancing the Safety
of AI Agents.
We are an independent UK organisation researching AI security, architecture and compute efficiency for frontier AI systems.
What We Research
Our research programme covers six interconnected areas spanning AI safety, security, and compute efficiency. Most programmes are closed; Semantic Efficiency Research has been spun out as Q2X Labs.
Model Package Protocol (MPP)
A licensed protocol for secure, signed, and sandboxed AI tool artifacts, commercialised by Quantum 2x. MPP brings container-like isolation to AI agent tool execution with WASM sandboxing, Ed25519 signing, and fine-grained permission boundaries.
Visit mpp-protocol.ioBehaviour Verification for AI Models
Research into methods for formally and empirically verifying the behavioural properties of AI models, ensuring they act within defined, auditable bounds and do not exhibit unintended emergent behaviours.
AI Agent Review & Monitoring
Systems for the continuous review and real-time monitoring of AI agents in operation, tracking decisions, tool invocations, and data access with full traceability and anomaly detection.
Security Protocols for Agents in Production
Research into security architecture and protocol design for AI agents deployed in live environments, covering isolation, least-privilege execution, inter-agent trust, and supply-chain integrity.
AI Agent Audit Tools
Tools and frameworks for auditing AI agent behaviour post-hoc, enabling compliance teams, researchers, and operators to inspect, replay, and assess agent decisions with cryptographic integrity guarantees.
AI Architecture
Research into a fundamentally different approach to AI model architecture, centred on what we call the Spherical Navigation Engine (SNE), training and reasoning over concepts rather than raw language tokens. Early results show model training using roughly 92% less compute than traditional transformer approaches, with the savings carrying through to inference. This programme has grown into its own initiative, Q2X Labs, now raising to take the work from lab to scale.
Visit Q2X LabsResearch-First Thinking for the AI Era
AI agents are becoming autonomous decision-makers with access to sensitive systems. Understanding and verifying their behaviour before and during deployment is a foundational challenge for the field.
Quantum 2x conducts independent research into the safety, integrity, and auditability of AI agent systems from formal behaviour verification to production security protocols.
Get in Touch