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 comprehensive documentation. Concurrently, sophisticated machine-learning algorithms are adept at monitoring system performance and proactively identifying security vulnerabilities. However, a critical question arises when the task shifts from the digital realm to the tangible: can these AI tools offer a similarly transformative impact when applied to the conception, design, and fabrication of complex 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 an ambitious exploration of this very question. The initiative tasked MIT undergraduates with a singular objective: to ascertain whether AI could significantly compress the traditional design-build-test cycle, enabling them to construct a functional gas turbine engine faster and more effectively.
Professor Zolti Spakovszky, the esteemed director of the MIT Gas Turbine Laboratory, encapsulated the core findings of the challenge, stating, "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 assertion underscores a nuanced understanding of AI’s role: not as a replacement for human expertise, but as a powerful co-pilot requiring skilled human direction.
The Teams, The Tools, and The Ambitious Task
The JARVIS Challenge presented a formidable undertaking: within a condensed four-week period, undergraduate teams were required to design, fabricate, assemble, and rigorously test a miniature gas turbine aero engine. The cornerstone of their approach was the integration of AI as their primary engineering partner. The ultimate objective was to construct a "JARVIS-class" single-spool jet engine capable of producing between 50 and 100 pounds of thrust, operating on Jet-A fuel, and successfully completing five distinct 60-second test runs. Teams were granted complete autonomy over their design methodologies, material selections, and fabrication processes, fostering an environment of unbridled innovation.
The participating student body represented a broad spectrum of academic disciplines within MIT’s School of Engineering, with 31 students organizing into seven distinct teams. These teams exhibited a diverse range of academic backgrounds, from cohorts comprised entirely of first-year students to more senior-heavy groups. Notably, many of the competitors commenced the challenge with limited prior experience in specialized fields such as turbomachinery, compressible flows, or, particularly for the younger students, even fundamental thermodynamics. A significant number had never had the opportunity to physically inspect the internal components of a gas turbine prior to their enrollment in the program.
To facilitate their ambitious project, the teams were provided with access to MIT’s state-of-the-art machine shops and a network of specialized manufacturing vendors. They also had at their disposal a suite of commercial engineering software, including industry-standard tools like Concepts NREC for aerodynamic design, SolidWorks for 3D modeling, and ABAQUS for finite element analysis. Furthermore, various test rigs were available for the precise characterization and assembly of individual engine components.
A pivotal element of the challenge was the students’ access to MIT Parley, a newly launched platform designed to aggregate leading-edge large language models through a unified interface. This provided the JARVIS leadership with direct visibility into the students’ AI tool utilization, including the specific prompts they employed, the associated costs per prompt, the particular LLMs being utilized, and other critical operational data. The JARVIS leads secured early access to Parley for all participants, and with substantial financial backing from MIT Lincoln Laboratory, the Department of Mechanical Engineering, and a consortium of corporate sponsors—Safran, Voyager Technologies, Beehive Industries, and Boom Technology—the students were afforded essentially unlimited access to AI resources.
The sponsors’ engagement was driven by a dual motivation: a keen interest in recruiting emerging talent and a genuine curiosity regarding AI’s potential to reshape established 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. He described JARVIS as "a genuine experiment, a learning endeavor. 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, were present to ensure paramount safety throughout the rigorous process. In weekly progress reviews, these mentors critically evaluated the students’ advancements and meticulously assessed their integration and application of AI tools. Professor Spakovszky developed a refined methodology for guiding teams toward optimal solutions without directly providing answers or explicit assistance. 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," thereby encouraging independent critical thinking and research.
AI’s Dual Role: Assistance and Obstacles
By the conclusion of the first week, one team had elected to withdraw from the competition. The remaining teams, with varying degrees of success, had managed to formulate an initial design blueprint for their gas turbines. The application of AI varied considerably across the groups. Teams leveraged AI to condense complex technical literature, acquire proficiency in design software, identify and vet potential vendors, generate detailed financial spreadsheets, obtain answers to specific technical queries, locate relevant research papers, and conduct comparative analyses between different design choices. One particularly innovative team even developed an AI agent within Parley, tasking it with functioning as their project manager, demonstrating a proactive approach to leveraging AI for organizational efficiency.
As the challenge progressed into the second week, teams were required to pivot towards the development of detailed CAD designs, initiate the procurement of necessary parts, and commence the prototyping of their combustor components. It was at this juncture that the inherent limitations of AI integration began to surface. While LLMs such as Claude and ChatGPT proved adept at suggesting alternative design concepts and bridging knowledge gaps, the persistent issues of "hallucinations" (generating plausible but incorrect information), sycophancy (overly agreeable or uncritical responses), and a fundamental lack of ingrained physical understanding—features increasingly recognized in generative AI—began to erode student confidence and introduce significant delays.
Elizabeth Tupaj, a member of the team known as "811 Crew," 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." This sentiment highlights the crucial need for human oversight and domain expertise when employing AI in critical design processes.
Teaching assistant John Zhang observed a pattern in student interactions with AI: "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 underscores the importance of effective AI onboarding and initial user experience in fostering long-term adoption and trust.
In the critical final weeks, the teams that advanced to the finals encountered a significant obstacle that no AI, in its current iteration, could surmount: the complexities of vendor relations and manufacturing procurement. Students reported, "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 skills, and established industry connections in overcoming real-world logistical challenges.
Of 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 close of May, two of the more senior teams, "Fast and Fractured" and "811 Crew," had successfully completed full engine tests. "Fast and Fractured," despite their AI-assisted design prowess, faced significant delays attributed to vendor-related issues throughout the competition. Nevertheless, they persevered and finally reached the testing phase. Unfortunately, their critical hot fire test was abruptly curtailed due to an unforeseen rotor rub against the stationary housing, leading to seizure.
In contrast, the "811 Crew," who entered the competition with a stronger foundational understanding of turbomachinery and propulsion concepts, emerged as the victorious team. Their engine successfully initiated, transitioned smoothly to Jet-A fuel, and most importantly, generated net thrust, meeting the core objective of the challenge.
PhD student Joe Chiapperi described the palpable tension and excitement 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."
Interestingly, the "811 Crew" had adopted a more cautious approach to AI integration throughout the competition, prioritizing their fundamental engineering knowledge and collaborative teamwork. Tupaj elaborated on their strategy: "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."
Observations from the challenge indicated a correlation between student year and AI utilization. Younger students tended to engage with Parley more frequently and with greater experimental flair, while junior and senior students often leveraged their more extensive academic and practical experience to guide their AI interactions.
Professor Andreea Bobu offered a critical insight into the dynamics of AI adoption: "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 salient finding reinforces the principle that engineering experience acts as a powerful multiplier, and the human element remains an indispensable component of success. A firm grasp of first principles and fundamental concepts cultivates sound engineering judgment, enabling individuals to navigate complex decision-making processes even when confronted with incomplete information. Moreover, when the objective is the development of safety-critical physical systems, human ingenuity, hands-on expertise, and accountability are irreplaceable.
Teaching assistant Kyle Woody summarized this crucial 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 expanding role in the aerospace sector are profound. If small, agile teams, empowered by well-managed AI copilots, can compress design-build-test cycles from years down to mere weeks, the ramifications for workforce structure, research and development timelines, and the overall competitive landscape could be substantial. The students who participated in the JARVIS Challenge stand among the inaugural cohort of engineers to confront these stakes not as a theoretical exercise, but within the practical realities of a machine shop, with a functional jet engine undergoing rigorous testing.
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 underscores the critical need to adapt educational paradigms to equip future engineers with the skills to effectively collaborate with and direct AI technologies, ensuring that human judgment and fundamental understanding remain at the forefront of innovation. The JARVIS Challenge has not only demonstrated AI’s potential but has also illuminated the vital role of human expertise in shaping its future application in complex engineering endeavors.
