In our accompanying paper, “Digital twins for a 21st-century transformation of the Electric Propulsion sector: Vision 2030”, we introduced the concept of digital twin (DT) and emphasized its strategic significance for addressing the cost-efficiency, reliability, and upscaling challenges facing the Electric Propulsion (EP) industry. Here, we delve into the technical efforts ongoing at Imperial Plasma Propulsion Laboratory (IPPL) and informed by our Vision 2030 to realize the world-first fully fledged DT for EP. We report our results and progress plans on three building blocks of DTs, namely, (i) a cost-effective kinetic particle-in-cell (PIC) model to generate extensive high-fidelity databases for machine learning (ML), (ii) ML-enabled, fast reduced-order models (ROMs) for performance predictions, and (iii) a DT architecture supporting the integration of numerical models, and providing the information flowpaths and interfaces for DT’s data exchange with real-world and its dynamic updating. Taking the Hall thruster technology as a proving ground, the building blocks’ development and demonstration fills the gap in terms of the missing foundational capabilities for EP DT.