Artificial intelligence has undeniably revolutionized software engineering, with generative AI and large language models (LLMs) capable of producing vast quantities of code and documentation, while machine-learning algorithms meticulously monitor performance and identify security vulnerabilities. However, a critical question lingers: can these AI tools achieve a similar level of transformation when applied to the intricate task of conceiving, designing, and fabricating complex physical systems, such as a jet engine? This past semester, the JARVIS Challenge, an intensive sprint focused on Jet-engine AI Research and Validation, set out to explore precisely this, tasking MIT undergraduates with determining if AI could significantly compress the design-build-test cycle, enabling them to engineer faster and with greater efficacy.
The outcomes of the JARVIS challenge, according to Professor Zolti Spakovszky, director of the MIT Gas Turbine Laboratory, have demonstrated that AI can indeed substantially accelerate safety-critical hardware engineering. However, he emphasized that "engineering judgment remains the decisive differentiator. 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."
The Challenge: Engineering a Jet Engine in Four Weeks
The JARVIS Challenge presented MIT undergraduates with a formidable task: to design, fabricate, assemble, and test a small gas turbine aero engine within a tight four-week timeframe. The core objective was to build 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 distinct 60-second test runs. Teams were granted complete autonomy over their design choices, material selections, and fabrication methods, fostering an environment of innovation and independent problem-solving.
Thirty-one students, representing a diverse array of disciplines across the School of Engineering, organized themselves into seven distinct teams. These teams exhibited a broad spectrum of experience, ranging from groups composed entirely of first-year students to those heavily comprised of seniors. A significant portion of the participants confessed to having limited prior experience in critical areas such as turbomachinery, compressible flows, or, particularly for the younger students, even fundamental thermodynamics. Many had never even witnessed the internal workings of a gas turbine before committing to the challenge of building one.
Resources and Tools: A Blend of the Traditional and the Cutting-Edge
To equip the students for this ambitious undertaking, MIT provided access to its state-of-the-art machine shops and a network of trusted manufacturing vendors. They also had at their disposal a suite of industry-standard commercial software, including Concepts NREC for aerodynamic design, SolidWorks for 3D modeling, and ABAQUS for finite element analysis. Furthermore, specialized test rigs were available for characterizing and assembling individual engine components.
A pivotal element of the challenge was the integration of cutting-edge AI tools. Teams had access to MIT Parley, a newly launched platform designed to aggregate various frontier large language models through a unified interface. This provided the JARVIS leadership with unprecedented visibility into the students’ AI utilization, tracking their prompts, associated costs, the specific LLMs employed, and other crucial operational data. With early access to Parley secured for all participants and substantial financial backing from MIT Lincoln Laboratory, the Department of Mechanical Engineering, and corporate sponsors including Safran, Voyager Technologies, Beehive Industries, and Boom Technology, students were afforded essentially unlimited access to AI resources.
The involvement of these sponsors was motivated by a dual interest: a keen desire for recruitment opportunities and a genuine curiosity about how AI might 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, describing JARVIS as "a genuine experiment, a learning endeavor. We frankly didn’t know what to expect, from the students or from the AI models." He noted that the students’ initial enthusiasm for exploration evolved into a "cool-headed realization of what AI could or could not help them with, and then almost instantly adapted for that." This adaptability, Garnier remarked, instills confidence 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, comprising professors Zachary Cordero, Zolti Spakovszky, Masha Folk, and Andreea Bobu from the Department of Aeronautics and Astronautics, alongside engineers from Lincoln Laboratory and a dedicated team of teaching assistants, played a crucial role in ensuring safety and guiding the educational objectives. Weekly progress reviews allowed them to critically assess student advancements and their application of AI tools. Professor Spakovszky developed a refined methodology for steering teams toward productive avenues without providing direct answers or solutions. His guidance often took the form of probing questions, such as, "Do you know what a rabbet fit is? Take in the comment."
AI’s Dual Role: Facilitator and Fetter
By the conclusion of the first week, one team had withdrawn from the competition. The remaining six teams had, with varying degrees of success, developed initial designs for their gas turbines. The integration of AI varied across the teams. Some utilized AI to summarize technical literature, learn new design software, identify potential vendors, generate complex Excel spreadsheets for analysis, answer specific technical queries, locate relevant research papers, and perform comparative analyses between different design decisions. One particularly innovative team even developed an AI agent within Parley to function as their project manager.
As the competition progressed into week two, teams were required to transition to detailed CAD designs, initiate parts procurement, and begin prototyping their combustor components. It was at this stage 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 inherent characteristics of generative AI—such as hallucinations, sycophancy, and a lack of genuine physical understanding—started to undermine student confidence and decelerate progress.
Elizabeth Tupaj, a member of the 811 Crew team, shared her perspective: "AI is a helpful tool, great at finding information, helping organize things, and can write well, but it can’t do design. 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 observed that "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 of the challenge introduced another significant obstacle that no AI could surmount: navigating the complexities of vendor relationships. Students reported that "AI searches found vendors we had no rapport with, who had no interest in our tight timeline. The vendors who came through were the ones our team had personal relationships with." This highlighted the enduring importance of human networking and established professional connections in the physical engineering world.
Of the three teams that ultimately reached the finals, only Fast and Fractured achieved first-attempt ignition of their mini-combustor. This team had extensively leveraged AI for trade studies and architectural comparisons, successfully arriving at a viable design despite none of its members possessing prior gas turbine experience.
Masha Folk, the Charles Stark Draper Career Development Professor of Aeronautics and Astronautics, reflected on the achievement: "The JARVIS Challenge showed what’s possible when you combine AI-enabled design with motivated students and a culture of rapid experimentation. 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: Judgment and Instinct
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. Their hot fire test was ultimately cut short when the rotor experienced a rub and seized against the stationary housing. Team 811 Crew, however, who entered the competition with a stronger foundational understanding of turbomachinery and propulsion concepts, emerged as the victorious team. Their engine successfully started, transitioned to Jet-A, and generated net thrust, a testament to their rigorous engineering approach.
PhD student Joe Chiapperi described the palpable tension during the final tests: "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. There were so many ways it could go wrong! What these students accomplished in such a short time span is nothing short of amazing."
Intriguingly, the winning 811 team had initially been resistant to extensive AI utilization throughout the competition, opting instead to rely on their fundamental engineering knowledge and strong teamwork. Tupaj explained, "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."
An interesting trend emerged: younger students tended to engage with Parley more frequently and creatively, while the more experienced juniors and seniors leveraged their deeper domain expertise. Professor Andreea Bobu offered a nuanced perspective on this observation: "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 underscores the critical role of engineering experience as a multiplier, with the human element remaining an indispensable component. Mastery of first principles and fundamental concepts cultivates sound engineering judgment and the crucial ability to navigate complex decision-making processes amidst incomplete information. Furthermore, in the realm of constructing safety-critical physical systems, human oversight, manual dexterity, and ultimate accountability are irreplaceable.
Teaching assistant Kyle Woody summarized this key takeaway: "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."
Broader Implications and the Future of Aerospace Engineering
The implications of AI’s integration into aerospace engineering are profound. The ability of small, agile teams, empowered by well-managed AI copilots, to compress design-build-test cycles from years to mere weeks could trigger substantial shifts in workforce structure, R&D timelines, and competitive dynamics within the industry. The students who participated in the JARVIS Challenge stand at the forefront of this transformation, grappling with these stakes not as abstract concepts, but in the tangible environment of a machine shop, with a functioning jet engine on the test stand.
Professor Cordero, associate director of the MIT Gas Turbine Laboratory, concluded, "JARVIS highlighted the power of AI in the design of physical systems. 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 JARVIS Challenge serves as a compelling pilot study, offering invaluable insights into the evolving landscape of engineering education and practice in an era increasingly defined by artificial intelligence.
