Artificial intelligence has undeniably revolutionized the landscape of software engineering. Generative AI and large language models (LLMs) can now produce vast quantities of code and documentation, while machine learning algorithms excel at monitoring system performance and identifying security vulnerabilities. However, a critical question arises when the task shifts from the digital realm to the physical: can these AI tools offer a similarly transformative impact when it comes to conceiving, designing, and fabricating 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 a mission to answer this very question. The intensive program tasked MIT undergraduates with investigating whether artificial intelligence could significantly compress the traditional design-build-test cycle, ultimately enabling them to build faster and better.
Professor Zolti Spakovszky, the director of the MIT Gas Turbine Laboratory, a key institution behind the initiative, offered a nuanced perspective on the challenge’s outcomes. "The JARVIS challenge showed that AI can substantially accelerate safety-critical hardware engineering, but engineering judgment remains the decisive differentiator," Spakovszky stated. He elaborated on the evolving role of engineers in this new paradigm: "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 highlights a core finding: while AI can augment and accelerate certain phases of engineering, the practicalities of physical production and the indispensable human element of expert judgment are far from obsolete.
The Teams, The Tools, and The Ambitious Task
The JARVIS Challenge presented a demanding objective to its undergraduate participants: within a condensed four-week period, they were to design, fabricate, assemble, and rigorously test a small gas turbine aero engine. The central premise was to leverage AI as their primary engineering partner throughout this intense sprint. The ultimate goal was to construct a "JARVIS-class" single-spool jet engine capable of generating between 50 and 100 pounds of thrust, operating on Jet-A fuel, and successfully completing five separate 60-second test runs. The teams were granted complete autonomy in their design choices, material selection, and fabrication methods, fostering an environment of innovation and independent problem-solving.
A diverse cohort of 31 students, representing nearly every department within MIT’s School of Engineering, organized themselves into seven distinct teams. The composition of these teams varied significantly, ranging from groups comprised entirely of first-year students to those heavily populated by seniors. A notable aspect of the challenge was that many competitors initially possessed limited prior experience in specialized fields such as turbomachinery, compressible flows, or, particularly for the younger students, even fundamental thermodynamics. Indeed, many had never encountered the intricate workings of a gas turbine before committing to the ambitious task of building one from the ground up.
To support their endeavors, the students were provided with access to MIT’s state-of-the-art machine shops and a network of trusted manufacturing vendors. They also had access to a suite of sophisticated commercial software, including industry-standard tools like Concepts NREC for aerodynamic design, SolidWorks for 3D modeling, and ABAQUS for advanced finite element analysis. Furthermore, various specialized test rigs were available for characterizing and assembling individual engine components.
Crucially, the teams also gained access to MIT Parley, a newly launched platform designed to aggregate frontier large language models through a unified interface. This innovative tool provided the JARVIS leadership with direct insight into how the students were utilizing the AI tools. They could monitor the students’ prompts, track the associated costs per prompt, identify the specific LLMs being employed, and gather other critical usage data. The JARVIS leadership facilitated early access to Parley for all participants. Generous financial support from MIT Lincoln Laboratory, the Department of Mechanical Engineering, and corporate sponsors including Safran, Voyager Technologies, Beehive Industries, and Boom Technology ensured that the students had virtually unlimited access to AI resources throughout the competition.
The motivations behind these sponsorships were multifaceted, stemming from both a keen interest in talent 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," Garnier added. "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, played a vital role in ensuring the safety and integrity of the project. During weekly progress reviews, they meticulously evaluated student advancements and critically assessed the integration of AI into their design and development processes. Professor Spakovszky developed a refined methodology for guiding teams toward solutions without directly providing answers or assistance. His approach often involved posing insightful questions during presentations, such as, "Do you know what a rabbet fit is? Take in the comment," prompting students to delve deeper into their understanding and research.
Navigating the AI Landscape: Where It Helps and Where It Hinders
By the conclusion of the first week, one team had withdrawn from the competition. The remaining teams, with varying degrees of success, had formulated initial designs for their gas turbines. The integration of AI proved to be a versatile tool during this initial phase. Teams employed AI to summarize technical textbooks, learn complex design software, identify potential vendors, generate comparative analysis reports for design decisions, and answer specific technical queries. One team even took an innovative approach by creating an AI agent within Parley, tasking it with functioning as their project manager.
As the challenge progressed into week two, the focus shifted towards developing detailed CAD designs, ordering critical parts, and prototyping combustion chambers. It was at this juncture that the limitations of AI in practical engineering applications began to surface more prominently. While LLMs like Claude and ChatGPT proved adept at suggesting alternative design concepts and filling knowledge gaps, the inherent challenges of generative AI, such as factual inaccuracies (hallucinations), a tendency to agree with users (sycophancy), and a lack of fundamental physical intuition, started to undermine the students’ confidence and slow their 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," she stated. "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 domain expertise 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 effective onboarding and initial AI interactions in shaping long-term adoption and trust.
In the final weeks of the competition, the finalists encountered another significant obstacle that no AI could readily overcome: navigating the intricacies of vendor relationships. 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 observation powerfully illustrates that established human networks and personal connections remain invaluable in the often-unpredictable world of manufacturing and procurement.
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 having prior experience in gas turbine engineering.
Masha Folk, the Charles Stark Draper Career Development Professor of Aeronautics and Astronautics, reflected on the project’s success: "The JARVIS Challenge showed what’s possible when you combine AI-enabled design with motivated students and a culture of rapid experimentation," she said. "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." This particular success story encapsulates the potential of AI to democratize access to complex engineering challenges and accelerate learning curves.
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 significant delays due to persistent vendor issues. Nevertheless, they eventually reached the testing phase. Unfortunately, their hot fire test was cut short due to a rotor rub and subsequent seizure against the stationary housing. The "811 Crew," however, who entered the competition with a stronger foundation in turbomachinery and propulsion concepts, emerged as the victorious team. Their engine successfully started, transitioned to Jet-A fuel, and demonstrably generated net thrust, fulfilling the core objectives of the challenge.
PhD student Joe Chiapperi, who witnessed the engine tests, described the palpable tension: "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."
Ironically, the winning team, "811 Crew," had initially displayed a degree of resistance towards using AI throughout the competition, preferring to rely on their fundamental 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. This suggests that while AI can be a powerful accelerator, a strong grounding in fundamental engineering principles and collaborative problem-solving can still lead to successful outcomes.
An interesting observation emerged regarding the students’ engagement with AI tools. Younger students, perhaps less encumbered by prior assumptions, tended to utilize Parley more frequently and inventively. Conversely, the junior and senior students often leveraged their deeper existing expertise, integrating AI more selectively.
Professor Andreea Bobu offered a valuable synthesis of these observations: "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," she stated. "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." This highlights the crucial balance between leveraging AI’s capabilities and maintaining human control and critical thinking.
The competition’s most salient finding underscores the enduring importance of engineering experience as a multiplier and the indispensable nature of the human factor. A firm grasp of first principles and fundamental concepts cultivates robust engineering judgment, empowering individuals to navigate complex decision-making processes even when faced with incomplete information. In the context of building safety-critical physical systems, human ingenuity, craftsmanship, 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. This reinforces the notion that AI acts as an amplifier, enhancing the capabilities of skilled engineers.
Broader Implications for Aerospace and Engineering Education
The implications of AI’s integration into aerospace engineering are profound. If small, agile teams, empowered by well-managed AI copilots, can dramatically compress design-build-test cycles from years to mere weeks, the ripple effects on workforce structure, research and development timelines, and competitive dynamics within the industry could be substantial. The students who participated in the JARVIS Challenge are among the earliest engineers to confront these stakes not as a theoretical exercise, but within the tangible environment of a machine shop, with a functional jet engine undergoing rigorous testing.
"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." This perspective emphasizes that while AI tools are rapidly evolving, the foundational knowledge and educational frameworks that equip engineers to use them effectively are paramount. The JARVIS Challenge serves as a compelling case study, demonstrating that the future of complex physical system design lies in the symbiotic relationship between advanced artificial intelligence and highly skilled, critically thinking human engineers.
