the platform
A GPU-accelerated defect modelling engine for any semiconductor material
Machine-learning potentials paired with first-principles DFT, feeding a structured, growing defect database. The material changes as an input. The engine doesn't.
1
2
3
4
5
Structure validation
Establish and validate the pristine crystal structure for your material system.
Defect enumeration & ML screening
Vacancies, antisites, interstitials and complexes, triaged with GPU-accelerated machine-learning potentials (MACE) on Isambard-AI.
Charged-defect DFT
Hybrid-functional validation with finite-size correction, potential alignment and chemical-potential accounting.
Formation energies & CTLs
Charge-transition levels and thermodynamic stability across the relevant chemical-potential range.
Database entry & report
Results are added to our structured defect database and delivered as evidence for your team.
built on the engine
Applications for your team
The engine and database are the core product. These are two ways teams put that evidence to work.
core platform
Defect Modelling & Diagnostics Engine
First-principles and ML-accelerated defect characterisation for your material: formation energies, charge-transition levels, doping-compensation analysis, and radiation or reliability defect behaviour — added to a structured, queryable database.
application
Technology Credibility Audit
Verifies whether a material's claimed or measured performance holds up against its predicted defect physics — evidence-based, not desk research.
application
Investor Technical Due Diligence
The same defect-physics verification applied to investment decisions — an independent, harder-to-fake signal on a target company's material or process claims.
don't see your material?
The method transfers
These five prove the pipeline works across very different structures. Your material is the next input, not a new project.
Ga2O3
SiC
SiO2
AlN
— or tell us yours