In the military, medical simulation and training would benefit from Computer Vision (CV) and Artificial Intelligence (AI) technologies when evaluating individual and team tasks within live Tactical Combat Casualty Care (TCCC) on the battlefield. Realistic hands-on experience is critical for medical training. Virtual solutions offer practice performing steps in the right order, but they do not build critical muscle memory skills needed to perform under stress. Training on manikins enables muscle memory, but simple low fidelity manikins lack the required fidelity; whereas, high-fidelity manikins are fragile, disruptive, and costly. As a result, there are limitations based on a spectrum of required tasks at designated medical simulation training centers. As the Army moves towards the Synthetic Training Environment (STE), live medical training must blend both the physical and virtual worlds. Examining the problem set, we determined that cost, time, and resources available were known constraints within an acquisition life cycle management strategy. Currently, live force-on-force training events use the MILES system to depict wounds and treatment. Whether a large force on force exercise or a medically specific training event, typically the only feedback a 68W Combat Medic receives when treating a patient is from an instructor’s PASS/FAIL observations. In response, the Army has teamed with DARPA and industry partners to address these challenges using CV and AI. Integrating learning ecosystems within multiple training modalities using shared competency models must also support more accurate assessment of skills and capabilities for TCCC training within the STE. Leverging technologies such as CV and AI plus understanding data interoperability within a modular open system architecture is essential for training and readiness. This holistic approach to a data centric learning ecosystem will transform the way we learn, the way we fight, and the way we win.