Project Info
Inspiration
The inspiration for my project came from my Mechanical Engineering major and its focus on designing parts. As a beginner who has not yet taken all the design and material science classes, it is hard to know whether a project I am designing will be functional or withstand basic usage. This website was built with new engineers in mind who are looking to start their first few sketches and projects.
What it does
MechPilot contains four important tabs that each cover a different part of the process: Project (Prompt), Material, 3D Printing, and Design Review. Under the New Project tab, an engineer can prompt the AI with their project idea and receive guided feedback. The AI asks follow up questions to better understand where the user wants to go, then produces a full plan to help them get started. This includes Design Constraints, Suggested Dimensions, CAD modeling steps, Print Cost Estimates, Failure Risk analysis, and more. The Print Cost Estimate section features an interactive slider that informs the user of cost and printing time based on Shape Factor and Infill settings. Under the Material Recommendation tab, the user inputs their prompt and intended usage so the AI can recommend the best materials for each part, along with a detailed breakdown of the pros and cons of each material and where it is best applied in the project. The 3D Printing Advisor tab provides recommendations on Layer Height, Wall Count, Infill, and more. Finally, the Design Review tab allows users to upload images and sketches of their project so the AI can provide tailored feedback on improvements and potential concerns.
How we built it
I built this on the Sai platform, which constructed my website using Claude Code.
Challenges we ran into
As a hackathon beginner, this was my first time working with Sai. Even though Sai handles most of the background work autonomously, learning how to set it up on my computer was my first challenge. I reached out to the Sai team, who helped me get it running. Shortly after, another issue came up that I was not expecting. Running the program locally on my Mac required an API key, which I had no knowledge of at the time and completely stalled my progress. I went back to the Sai team once more, and they helped me resolve it.
Accomplishments we're proud of
I am proud to have arrived at a fully functioning final product. As a first time hackathon competitor, it means a lot to be submitting a working vision that can potentially help students get started on designing parts.
What we learned
I learned how to work with Sai to build projects. This experience also reinforced how important it is to seek help from mentors and peers when you need it.
What's next
I would like to continue developing MechPilot so that it can work alongside the engineer in real time, providing live feedback and instructions throughout the design process.
This project did not link a GitHub repository.
Analysis
No indexed repository for this project, so there are no commit stats to show.
Technology
No technologies were claimed or detected for this project.
AI coding agents
No repository was indexed, so agent usage could not be checked.
Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.
Codebase size
No repository was indexed, so there is no codebase to measure.
This project did not link a GitHub repository, so there is nothing to diagram.
This project did not link a GitHub repository, so its feature claims have not been checked against code.
Export this project's context (description, README, evidence, key source files) to chat with an AI agent elsewhere.