The integration of artificial intelligence into software engineering has been nothing short of revolutionary. Generative AI and large language models (LLMs) now possess the capability to produce vast quantities of code and documentation, while machine learning algorithms can meticulously monitor system performance and proactively detect security vulnerabilities. However, a pressing question arises: can these AI tools deliver a comparable transformative impact when tasked with the conception, design, and fabrication of intricate physical systems, such as a jet engine? This past semester, the JARVIS Challenge—an acronym for Jet-engine AI Research and Validation Intensive Sprint—embarked on a mission to investigate precisely this, tasking MIT undergraduates with exploring whether AI could significantly compress the traditional design-build-test cycle, ultimately enabling them to build faster and better.
Pioneering AI in the Realm of Physical Engineering
Professor Zolti Spakovszky, director of the MIT Gas Turbine Laboratory, summarized the challenge’s core findings: "The JARVIS challenge showed that AI can substantially accelerate safety-critical hardware engineering, but 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." This statement encapsulates the delicate balance observed throughout the competition: AI as a powerful assistant, but human expertise as the indispensable navigator.
The Teams, The Tools, and The Ambitious Task
The JARVIS Challenge presented a formidable objective for undergraduate students: within a compressed four-week timeframe, they were to design, fabricate, assemble, and test a small gas turbine aero engine. Their primary engineering partner throughout this endeavor was to be artificial intelligence. The ultimate goal was to construct 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 operational runs. The teams were granted complete autonomy over their design choices, material selections, and fabrication processes, fostering an environment of innovation and independent problem-solving.
Thirty-one students, representing a diverse spectrum of departments across MIT’s School of Engineering, formed seven distinct teams. These teams exhibited a broad range of academic experience, from all-first-year groups to those heavily populated by senior undergraduates. Notably, many of the competitors entered the challenge with limited prior experience in specialized fields such as turbomachinery, compressible flows, or, particularly for the younger students, even fundamental thermodynamics. For many, the competition marked their first encounter with the inner workings of a gas turbine engine.
To support their ambitious undertaking, the teams were provided access to MIT’s state-of-the-art machine shops and a network of manufacturing vendors. They could leverage commercial software packages, including industry-standard tools like Concepts NREC for turbomachinery design, SolidWorks for 3D modeling, and ABAQUS for finite element analysis. Additionally, various test rigs were available for the characterization and assembly of individual engine components.
A pivotal element of the challenge was the integration of MIT Parley, a newly launched platform designed to aggregate a suite of frontier large language models through a unified interface. This innovative tool allowed the JARVIS leadership to gain direct insights into how students were interacting with the AI, tracking their prompts, the associated costs per prompt, the specific LLMs being utilized, and other critical operational data. The JARVIS leadership secured early access to Parley for all participants. Furthermore, with substantial financial backing from MIT Lincoln Laboratory, the Department of Mechanical Engineering, and key corporate sponsors—Safran, Voyager Technologies, Beehive Industries, and Boom Technology—students enjoyed virtually unlimited access to AI resources, removing financial constraints as a barrier to exploration.
The sponsors’ motivations for supporting the JARVIS Challenge were twofold: a keen interest in recruitment and a genuine curiosity about the potential of AI to reshape engineering workflows. Ryan (Hal) Hefron of Voyager Technologies articulated this sentiment to the students, stating, "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, 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, provided crucial oversight to ensure safety and guide the students. In regular weekly progress reviews, they critically evaluated the student teams’ advancements and their utilization of AI tools. Professor Spakovszky employed a deliberate strategy of guiding teams toward solutions without directly providing answers. Following a team’s presentation, he might pose a probing question, such as, "Do you know what a rabbet fit is? Take in the comment." This Socratic method encouraged deeper student engagement and independent problem-solving.
The Dual Nature of AI’s Impact: Assistance and Obstacles
By the conclusion of the first week, one team had withdrawn from the competition, while the remaining teams had, with varying degrees of success, formulated initial designs for their gas turbines. The students leveraged AI in diverse ways: summarizing technical textbooks, learning to operate design software, sourcing specialized vendors, generating complex Excel spreadsheets for analysis, answering specific technical queries, finding relevant academic references, and conducting comparative analyses between different design decisions. One particularly innovative team even developed an AI agent within Parley, assigning it the role of their project manager.
As the competition progressed into the second week, the focus shifted to detailed CAD designs, procurement of parts, and prototyping of critical components like combustors. It was at this juncture that the limitations of AI in practical engineering applications began to surface. While LLMs such as Claude and ChatGPT proved adept at proposing design alternatives and bridging knowledge gaps, the inherent tendencies of generative AI—including hallucinations, sycophancy, and a general lack of intuitive physical understanding—started to erode student confidence and decelerate progress.
Elizabeth Tupaj, a member of the "811 Crew" team, shared her team’s experience: "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." This sentiment underscores the critical need for human oversight and validation when relying on AI for complex engineering tasks.
Teaching assistant John Zhang observed a recurring pattern: "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." This highlights the importance of early success and effective AI integration to foster sustained adoption.
The final weeks of the competition presented a formidable obstacle that no AI could directly overcome: the complexities of working with manufacturing vendors. 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 experience underscored the enduring value of human networking, negotiation, and established professional relationships in the practical execution of engineering projects.
Among the three finalist teams, only "Fast and Fractured" achieved first-attempt ignition of their mini-combustor. This team had extensively utilized AI for trade studies and architectural comparisons, ultimately 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."
At the Vanguard of AI-Native Engineering
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 persistent delays due to vendor issues but ultimately reached the testing phase. Their engine’s operation was unfortunately cut short when the rotor experienced rubbing and seized against the stationary housing. In contrast, the "811 Crew," benefiting from greater prior exposure to turbomachinery and propulsion concepts, emerged as the victorious team. Their engine successfully initiated, transitioned to Jet-A fuel, and generated net thrust, demonstrating a comprehensive understanding of the design and operational requirements.
PhD student Joe Chiapperi vividly described the culmination: "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 "811 Crew" team had exhibited a degree of resistance to using AI throughout the competition, opting instead to rely heavily on their foundational knowledge and collaborative teamwork. Tupaj elaborated, "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." This suggests that established expertise can sometimes be a more direct path to success than an uncritical reliance on emerging technologies.
Analysis of the teams’ AI usage revealed a nuanced trend: younger students tended to employ Parley more frequently and with greater ingenuity, while juniors and seniors leveraged their deeper existing experience. Professor Andreea Bobu offered a key insight: "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 takeaway was the confirmation that engineering experience acts as a powerful multiplier, and the human element remains an indispensable component of successful innovation. A robust understanding of first principles and fundamental concepts cultivates sound engineering judgment and the ability to navigate complex decision-making processes, especially when faced with incomplete information. Crucially, when it comes to the development of safety-critical physical systems, human ingenuity, skill, and 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.
The implications of AI in the aerospace sector are profound. If small, agile teams, armed with well-managed AI copilots, can dramatically compress design-build-test cycles from years down to mere weeks, the consequences for workforce structuring, research and development timelines, and competitive dynamics within the industry could be substantial. The students who participated in the JARVIS Challenge stand as some of the earliest engineers to confront these stakes not as an abstract theoretical exercise, but in the tangible environment of a machine shop, with a functioning jet engine on a 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." This emphasizes that the future of AI-driven engineering hinges on a foundational commitment to educating and empowering human engineers.
