<?xml version="1.0" encoding="UTF-8"?><ns2:project xmlns:ns1="http://gtr.rcuk.ac.uk/gtr/api" xmlns:ns2="http://gtr.rcuk.ac.uk/gtr/api/project" xmlns:ns3="http://gtr.rcuk.ac.uk/gtr/api/fund" xmlns:ns4="http://gtr.rcuk.ac.uk/gtr/api/person" xmlns:ns5="http://gtr.rcuk.ac.uk/gtr/api/project/outcome" xmlns:ns6="http://gtr.rcuk.ac.uk/gtr/api/organisation" ns1:created="2026-06-22T07:57:45Z" ns1:href="http://gtr.ukri.org/gtr/api/projects/FA1F082F-76E9-4DB1-AC6C-5418CA9212B9" ns1:id="FA1F082F-76E9-4DB1-AC6C-5418CA9212B9"><ns1:links><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/persons/72F5EEB4-0CF9-48D5-9D84-2170DEF53D63" ns1:rel="PM_PER"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/CE7116A3-F471-4805-ACF0-40BCF91FDD84" ns1:rel="LEAD_ORG"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/CE7116A3-F471-4805-ACF0-40BCF91FDD84" ns1:rel="PARTICIPANT_ORG"/><ns1:link ns1:end="2026-03-30T23:00:00Z" ns1:href="http://gtr.ukri.org/gtr/api/funds/B9063970-3C9B-4369-BBEC-441B6B9DFFC7" ns1:rel="FUND" ns1:start="2025-11-01T00:00:00Z"/></ns1:links><ns2:identifiers><ns2:identifier ns2:type="RCUK">10171124</ns2:identifier></ns2:identifiers><ns2:title>AI-native operating system for complex engineering</ns2:title><ns2:status>Closed</ns2:status><ns2:grantCategory>Fast Start Response</ns2:grantCategory><ns2:leadFunder>Innovate UK</ns2:leadFunder><ns2:abstractText>Three Sigma is building an AI-native operating system that enables complex hardware industries (initially aerospace) to embed data-driven intelligence throughout their engineering lifecycle. We unify design, test, quality and production data to deliver trusted, verified context to LLMs and establish rules to constrain these models, enabling smart automation that scales with hardware complexity. The _Neuro-Symbolic Assurance Engine_ (NSAE) project makes this technology robust and deployable for UK SMEs.

With Innovate UK support, we will enhance accuracy and auditability of Three Sigma's foundational knowledge layer, while establishing a secure, single-tenant cloud foundation for customer deployment. In the project's final stages, we will conduct a shadow-mode pilot with an aerospace partner to validate ROI (target: =30% reduction in engineering-change Mean-Time-To-Resolution) and generate evidence for early sales.

The result is an explainable, verifiable context layer on top of which AI agents are deployed to empower engineers to work more efficiently and reliably, all the while meeting regulatory requirements for provenance and accountability. Every prompt and reasoning step is telemetry-traced, providing span-level audit trails that support trusted AI adoption in safety-critical environments.

By reducing manual detective work and rework, NSAE aims to free up high-skill engineer hours, accelerate UK aerospace programmes and reduce lifecycle emissions associated with repeat builds. The project delivers an affordable, adoptable, investable AI capability for UK industry, creating a platform that can expand beyond aerospace into other high growth, export-rich verticals including sustainable aviation, Defence, fusion, medical devices and green manufacturing.</ns2:abstractText></ns2:project>