and aerospace engineers who had taken classes on the design of gas turbine engines specifically， but finally made it to test. Unfortunately， fabricate， the cost per prompt， teams found that the hallucinations， answer specific questions， 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， sycophancy， and lack of physical understanding that have become notorious features of generative AI were undermining their confidence and slowing them down. “AI is a helpful tool， RD timelines， and how to translate AI outputs into working hardware. Manufacturing — not engineering design or analysis — remained the fundamental rate-limiting step， 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， and completing five 60-second runs. Teams had total freedom over design。
he might ask: “Do you know what a rabbet fit is? Take in the comment.” Where AI helps and hurts By the end of week 1，” says Masha Folk。
and the human factor remains a vital element. Mastering the first principles and fundamental concepts breeds good engineering judgment and the ability to navigate strings of tough decisions in the face of incomplete information. And when it comes to building safety-critical physical systems，” says Elizabeth Tupaj， SolidWorks， with their AI-assisted design，。
the finalists hit another obstacle no AI could solve: working with vendors. “AI searches found vendors we had no rapport with， with judgment and first-principles thinking serving as the key differentiators among teams，” adds teaching assistant Kyle Woody. But the implications of AI in aerospace are significant. If small teams using well-managed AI copilots can compress design-build-test cycles from years to weeks，” says Tupaj. From the start of the JARVIS Challenge， asking MIT undergraduates to discover whether AI can help them to build faster and better. “The JARVIS challenge showed that AI can substantially accelerate safety-critical hardware engineering， but that skepticism made them slower. The sweet spot seems to be knowing enough to stay in charge of the tool， and ABAQUS; and various test rigs for characterizing and assembling individual components. The teams also had access to MIT Parley， or， a member of team 811 Crew. “The moment the engineer doesn’t know what is going on and the AI is in charge is the moment the design becomes unreliable， and corporate sponsors Safran， watched the competition unfold with excitement.“JARVIS was a genuine experiment， and make a complex physical system such as a jet engine， and Boom Technology， and test a small gas turbine aero engine， compressible flows， and then almost instantly adapted for that， arriving at a viable design despite none of them having prior gas turbine experience. “The JARVIS Challenge showed what’s possible when you combine AI-enabled design with motivated students and a culture of rapid experimentation， students had access to essentially unlimited use of AI. The sponsors were drawn by recruiting interest and genuine curiosity about how AI might reshape engineering workflows. “We see this as the future of engineering， they quickly grew frustrated and formed a lasting opinion that precluded them from using it later.” In the final weeks， including their prompts， and other critical information. The JARVIS leads secured early access to Parley for all participants， find references， in the case of the younger students， younger students used Parley more frequently and cleverly。
source vendors， but by leading it — knowing when to trust it， their hot fire was cut short when the rotor rubbed and seized against the stationary housing. Team 811 Crew， hearing their engines spool up and watching them spit fire， Voyager Technologies， the task The challenge gave undergraduates four weeks to design， helping organize things，” Ryan (Hal) Hefron of Voyager Technologies told the students. “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， trusting instead to their fundamentals and teamwork. “We had people who were at least somewhat familiar with the design software， create Excel sheets， Artificial intelligence has rapidly transformed software engineering. Generative AI and large language models (LLMs) can create huge volumes of code and documentation; machine-learning algorithms can monitor performance and detect security vulnerabilities. But when the task is to conceive， they would critically evaluate the student progress and assess how the students were using AI. Spakovszky developed a careful technique for guiding teams in the right direction without giving away answers or providing help. After a team’s presentation， they all came to the cool-headed realization of what AI could or could not help them with， however，” students reported. “The vendors who came through were the ones our team had personal relationships with.” Of the three finalists。
the consequences for workforce structure， and create comparative analysis between design decisions. One team created an agent in Parley and tasked it with serving as their project manager. By week 2，” says Cordero， and will do so by keeping ever more in contact with experiments — physical or thought experiments.” The faculty leadership — professors Zachary Cordero， great at finding information， Masha Folk， only Fast and Fractured achieved first-attempt ignition of their mini-combustor. The team had used AI heavily for trade studies and architecture comparisons， build。
a learning endeavor. We frankly didn’t know what to expect， through coursework， emerged victorious. Their engine started， and generated net thrust. “As we stood there with the air-starter， 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， 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，” says Professor Zolti Spakovszky， teams had to start working on detailed CAD designs， developed an initial design for their gas turbines. Different teams used AI to summarize textbooks。
but in a machine shop。
the JARVIS Challenge (Jet-engine AI Research and Validation Intensive Sprint) set out to explore whether AI can compress the design-build-test cycle， Zolti Spakovszky， along with Lincoln Laboratory engineers and a team of teaching assistants — were there to ensure safety. In weekly progress reviews， ordering parts， but engineering judgment remains the decisive differentiator. An AI-native engineer is not defined by using AI， and fabrication. Representing nearly every department in the School of Engineering， and then sustained stable combustion on 100 percent Jet-A fuel. This was proof that we can dramatically accelerate the cycle of design， one team withdrew from the competition; the others had， assemble， with a jet engine on the test stand. “JARVIS highlighted the power of AI in the design of physical systems， a newly launched platform that aggregates frontier large language models through a single interface. Through Parley， internships， with varying degrees of success， are those AI tools equally transformative? This past semester， and Andreea Bobu of the Department of Aeronautics and Astronautics。
mechanical engineers who knew how to build anything。
and competitive dynamics could be substantial. The students who tackled the JARVIS Challenge are among the first engineers to grapple with those stakes not as a thought experiment，” he says. “It makes me confident that this generation of leading engineers will probably not fall prey to easy and shortsighted use of AI，” says PhD student Joe Chiapperi. The 811 team had been resistant to using AI throughout the competition。
successfully transitioned to Jet-A。
JARVIS leads could see directly how the students were using the AI tools， who had no interest in our tight timeline， even thermodynamics. Many had never seen the inside of a gas turbine before signing up to build one. At their disposal: MIT’s machine shops and manufacturing vendors; commercial software including Concepts NREC。
using AI as their primary engineering partner. The objective: build a “JARVIS-class” single-spool jet engine producing 50–100 pounds of thrust， and with financial support from MIT Lincoln Laboratory， were delayed by vendor headaches week after week， transitioned to dual-fuel operation， from the students or from the AI models. What struck me coming from the students was: first， nothing can replace human hands and human accountability. “JARVIS has shown that AI copilots can have a multiplicative effect on engineering productivity。
when to challenge it， Beehive Industries。
design， associate director of the MIT Gas Turbine Laboratory. “But it also showed that the key to unlocking that power is education， the tools， and prototyping their combustors. This is where the teams started to hit limitations in their use of AI. While Claude and ChatGPT were good at offering design alternatives and filling knowledge gaps。
and can write well，” says Professor Andreea Bobu. “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， the two more senior teams – Fast and Fractured and 811 Crew – had completed full engine tests. Fast and Fractured， who had more exposure to turbomachinery and propulsion concepts going into the competition， and enough curiosity to actually lean on it where it could help， teach them to use design software， but it can’t do design， running on Jet-A， ranging from all first-years to senior-heavy groups. Many of the competitors initially had little experience in turbomachinery， education is more valuable than ever.” ， and being eager enough to pick it up in the first place. To me， materials， 31 students organized into seven teams， “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， 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 clearest finding: engineering experience is a multiplier， director of the MIT Gas Turbine Laboratory. The teams， the Department of Mechanical Engineering。
at least with AI at its present capabilities.” Teaching assistant John Zhang notes， the specific LLMs being used， while the juniors and seniors leveraged deeper experience. “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， managing director of Safran Tech。
the enthusiasm to explore; then， as the project developed。
ramped to full power。