nTop's Computational Design Summit Delivers Again Yesterday I had the pleasure of attending nTop's 2nd Computational Design Summit (CDS) as an attendee. I was really looking forward to this event because looking back over the last year, the technical progress in computational design that came out of last year's event is impressive. The industry collaboration Bradley Rothenberg and the team at nTop facilitated and committed to in their product integration over the last year is a true sign of dedication to advancing the state of the art. While the 2nd CDS reviewed some of these achievements, the main focus was really setting the stage for the next year of advancement. The event also included a completely different set of companies from last year's, and they exhibited potential solutions for the very problems discussed throughout the day. I particularly enjoyed the panel discussions, especially the panel with Kumar Bhatia, George Irving, Jan Vandenbrande and Steve Bleymaier with Bradley Rothenberg moderating. The mix of decades of experience in advanced system concept development, multi-disciplinary optimization, and aircraft design made for an insightful conversation on how computational design might change aerospace system development in the future. The theme of "Reclaim your engineering ambition" was also very appropriate to the content and to the industry right now and resonated with me personally. My three key take-aways and conclusions from the summit: 1. Physics-informed AI methodologies are built on a foundation of simulation, which distinguishes itself from generative AI. Efficient synthetic generation of datasets underlaid by physics-driven simulation may help address the inaccessibility or nonexistence of training data for developing AI models to be used for evaluating advanced engineering concepts and exploring a design space potential to meet requirements. 2. The development of surrogate models capturing both the input and output space can dramatically increase the amount of system concepts evaluated early in the engineering design cycle, which can help teams avoid locking into a lower performing design too soon. It can also help identify poorly constrained optimization problems and inadequate design space constraints. 3. Implicit modeling is inherently suitable for optimization routines leveraging AI. nTop is not only systemically eliminating the difficulties of working with implicit models in workflows, they are continuing to enable new workflows and approaches in engineering design where implicit modelling eliminates barriers that have been in place for decades with traditional CAD models. Thank you Bradley Rothenberg & the nTop team for another great event, I'm looking forward to the next one already!