The JARVIS Challenge, a rigorous four-week intensive sprint at MIT, explored the transformative potential of artificial intelligence in conceiving, designing, and building complex physical systems, specifically a miniature jet engine. While generative AI and large language models (LLMs) demonstrated a significant capacity to accelerate the design-build-test cycle, the experiment underscored that human engineering judgment remains the critical differentiator, particularly in safety-critical hardware development. The challenge also highlighted manufacturing as the persistent bottleneck, rather than the engineering design or analysis phases.
The JARVIS Challenge: Pushing the Boundaries of AI in Hardware Engineering
The initiative, spearheaded by Professor Zolti Spakovszky, director of the MIT Gas Turbine Laboratory, aimed to answer a fundamental question: can AI tools, already revolutionizing software engineering by generating vast amounts of code and documentation, and by monitoring performance and detecting vulnerabilities, similarly compress the timeline for creating intricate physical machinery? The JARVIS Challenge provided an unprecedented opportunity for MIT undergraduates to directly engage with this question, tasked with building a functional jet engine with AI as their primary engineering partner.
"The JARVIS challenge showed that AI can substantially accelerate safety-critical hardware engineering, but engineering judgment remains the decisive differentiator," stated Professor Spakovszky. "An AI-native engineer is not defined by using AI, but by leading it – knowing when to trust it, when to challenge it, and how to translate AI outputs into working hardware. Manufacturing – not engineering design or analysis – remained the fundamental rate-limiting step."
Teams, Tools, and the Task: A Condensed Engineering Odyssey
Over a demanding four-week period, 31 undergraduate students, organized into seven teams representing a broad spectrum of engineering disciplines, were challenged to design, fabricate, assemble, and test a small gas turbine aero engine. The objective was to create a "JARVIS-class" single-spool jet engine capable of producing between 50 and 100 pounds of thrust, running on Jet-A fuel, and successfully completing five 60-second test runs. Teams were granted complete autonomy in their design choices, material selections, and fabrication methods.
Remarkably, many participants, particularly those from earlier years of study, had limited prior experience in specialized fields such as turbomachinery, compressible flows, or even thermodynamics. For some, the competition marked their first encounter with the inner workings of a gas turbine. This diverse background highlighted the challenge’s commitment to democratizing advanced engineering concepts through AI-assisted learning.
To facilitate their ambitious undertaking, students had access to MIT’s state-of-the-art machine shops and a network of external manufacturing vendors. They were also equipped with industry-standard commercial software packages, including Concepts NREC for turbomachinery design, SolidWorks for computer-aided design (CAD), and ABAQUS for finite element analysis. Various specialized test rigs were available for characterizing and assembling individual engine components.
A pivotal element of the challenge was the integration of MIT Parley, a newly launched platform designed to aggregate a range of advanced large language models through a unified interface. This provided the JARVIS leadership with direct oversight into how students were utilizing AI, tracking their prompts, associated costs, the specific LLMs employed, and other crucial data points. With generous financial backing from MIT Lincoln Laboratory, the Department of Mechanical Engineering, and corporate sponsors Safran, Voyager Technologies, Beehive Industries, and Boom Technology, students were granted essentially unlimited access to AI tools.
Industry Perspectives: AI as the Future of Engineering
The corporate sponsors were motivated by a dual interest: the potential for recruiting top talent and a genuine curiosity about how AI could fundamentally reshape engineering workflows. Ryan (Hal) Hefron of Voyager Technologies articulated this sentiment, telling the students, "We see this as the future of engineering. You’re honing skills that are not just nice to have – they’re going to be the future baseline in the engineering workforce."
Vincent Garnier, managing director of Safran Tech, observed the competition with keen interest. "JARVIS was a genuine experiment, a learning endeavor," he remarked. "We frankly didn’t know what to expect, from the students or from the AI models. What struck me coming from the students was: first, the enthusiasm to explore; then, as the project developed, they all came to the cool-headed realization of what AI could or could not help them with, and then almost instantly adapted for that. It makes me confident that this generation of leading engineers will probably not fall prey to easy and shortsighted use of AI, and will do so by keeping ever more in contact with experiments – physical or thought experiments."
The faculty leadership, including Professors Zachary Cordero, Zolti Spakovszky, Masha Folk, and Andreea Bobu from the Department of Aeronautics and Astronautics, alongside engineers from MIT Lincoln Laboratory and a dedicated team of teaching assistants, provided essential guidance and oversight, prioritizing safety throughout the process. Weekly progress reviews offered a platform for critical evaluation of student advancements and their AI integration strategies. Professor Spakovszky developed a nuanced approach to mentoring, posing targeted questions designed to prompt critical thinking without providing direct answers.
AI’s Dual Role: Enabler and Obstacle
By the conclusion of the first week, one team had withdrawn from the competition. The remaining teams had, with varying degrees of success, developed initial designs for their gas turbines. Students leveraged AI extensively for a range of tasks, including summarizing technical literature, learning new design software, identifying potential vendors, generating data for spreadsheets, answering specific technical queries, sourcing academic references, and conducting comparative analyses of design alternatives. One team even created a dedicated AI agent within Parley to function as their project manager.
As teams moved into the second week, the focus shifted to detailed CAD design, procurement of components, and prototyping of combustors. It was at this juncture that the limitations of AI began to surface more prominently. While LLMs like Claude and ChatGPT proved adept at suggesting design alternatives and bridging knowledge gaps, the well-documented issues of AI "hallucinations," sycophancy, and a fundamental lack of understanding of physical principles started to undermine student confidence and impede progress.
"AI is a helpful tool, great at finding information, helping organize things, and can write well, but it can’t do design," observed Elizabeth Tupaj, a member of the 811 Crew team. "The moment the engineer doesn’t know what is going on and the AI is in charge is the moment the design becomes unreliable, at least with AI at its present capabilities."
Teaching assistant John Zhang commented on the impact of initial impressions: "Seeing this firsthand with the students reminded me how much first impressions matter. If the students couldn’t get answers from the AI early on, they quickly grew frustrated and formed a lasting opinion that precluded them from using it later."
The final weeks presented another significant hurdle that no AI could surmount: navigating the complexities of vendor relationships. Students reported that AI-driven vendor searches often yielded contacts with whom they had no established rapport and who were unwilling or unable to meet their tight deadlines. Conversely, the vendors who ultimately proved reliable were those with whom the teams had cultivated personal connections.
The Moment of Truth: Finalists and the Test Stand
Of the three teams that reached the finals, only "Fast and Fractured" successfully achieved first-attempt ignition of their mini-combustor. This team had extensively utilized AI for trade studies and architectural comparisons, enabling them to arrive at a viable design despite having no prior experience in gas turbine engineering.
"The JARVIS Challenge showed what’s possible when you combine AI-enabled design with motivated students and a culture of rapid experimentation," remarked Masha Folk, the Charles Stark Draper Career Development Professor of Aeronautics and Astronautics. "The moment that stood out most was when the first student-designed combustor was installed on the test stand. It ignited flawlessly, ramped to full power, transitioned to dual-fuel operation, and then sustained stable combustion on 100 percent Jet-A fuel. This was proof that we can dramatically accelerate the cycle of design, build, and test while giving students hands-on experience with a real engineering challenge."
The Vanguard of AI-Native Engineering: Lessons Learned
By the end of May, two of the more senior teams, "Fast and Fractured" and "811 Crew," successfully completed full engine tests. "Fast and Fractured," despite their AI-assisted design prowess, faced significant delays due to vendor issues but ultimately made it to the test stand. Their test run was prematurely halted when the rotor experienced rubbing and seized against the stationary housing.
The "811 Crew," having entered the competition with greater prior exposure to turbomachinery and propulsion concepts, emerged as the victorious team. Their engine successfully started, transitioned to Jet-A fuel, and generated net thrust.
"As we stood there with the air-starter, hearing their engines spool up and watching them spit fire, it felt like my heart was racing out of my chest," recounted PhD student Joe Chiapperi. "There were so many ways it could go wrong! What these students accomplished in such a short time span is nothing short of amazing."
Interestingly, the "811 Crew" had exhibited a degree of resistance to using AI throughout the competition, opting instead to rely on their fundamental engineering knowledge and teamwork. "We had people who were at least somewhat familiar with the design software, mechanical engineers who knew how to build anything, and aerospace engineers who had taken classes on the design of gas turbine engines specifically," explained Tupaj.
Analysis of the teams’ approaches revealed a trend: younger students tended to utilize Parley more frequently and innovatively, while juniors and seniors drew upon their deeper, pre-existing expertise.
The Human Factor: Judgment, Curiosity, and Accountability
Professor Andreea Bobu distilled a key takeaway from the challenge: "JARVIS taught me that getting value from AI takes two things: enough expertise to judge what it tells you and catch it when it’s wrong, and enough curiosity to actually lean on it where it could help. The team that moved fastest in the sprint was experienced and leaned heavily on AI to get there. The team that eventually won was more resistant to AI; they had the expertise, but that skepticism made them slower. The sweet spot seems to be knowing enough to stay in charge of the tool, and being eager enough to pick it up in the first place. To me, that’s the real opportunity ahead: training the next generation of engineers who have the judgment to direct these AI tools and the instinct to reach for them."
The competition’s most significant finding reinforced the enduring value of engineering experience as a multiplier and highlighted the indispensable nature of the human element. Mastery of first principles and fundamental concepts cultivates sound engineering judgment, enabling individuals to navigate complex decisions amidst incomplete information. For safety-critical physical systems, particularly in aerospace, human hands and human accountability remain irreplaceable.
"JARVIS has shown that AI copilots can have a multiplicative effect on engineering productivity, with judgment and first-principles thinking serving as the key differentiators among teams," added teaching assistant Kyle Woody.
Broader Implications for Aerospace and Engineering Education
The implications of AI in the aerospace sector are profound. The capacity for small, AI-augmented teams to compress design-build-test cycles from years to mere weeks could fundamentally alter workforce structures, R&D timelines, and competitive dynamics within the industry. The students who participated in the JARVIS Challenge are among the pioneers grappling with these stakes not as theoretical exercises, but within the tangible reality of a machine shop, with a jet engine on the test stand.
"JARVIS highlighted the power of AI in the design of physical systems," concluded Professor Cordero, associate director of the MIT Gas Turbine Laboratory. "But it also showed that the key to unlocking that power is education, through coursework, internships, and hands-on extracurriculars like MIT Motorsports and Rocket Team. Performance in JARVIS correlated strongly with year in school. My main takeaway is that in the AI era, education is more valuable than ever."
The success of the JARVIS Challenge suggests that the future of complex physical system design lies in a symbiotic relationship between advanced AI tools and highly skilled, critically thinking engineers. The challenge has paved the way for a new generation of "AI-native" engineers, equipped not only with the ability to leverage AI but also with the wisdom to direct it effectively, ensuring that innovation in physical engineering continues to be guided by human ingenuity and rigorous scientific principles.
