AWS Builder Center
Weekend Showcase Challenge: STEM-Connect

Weekend Showcase Challenge: STEM-Connect

An AI-powered educational platform built with Amazon Bedrock and AWS Amplify that personalizes STEM learning for young students

AWS Cloud Captain ☁️
Vision and what it does When we conceptualized our entry for the Phaw AI project fair we wanted to build something much deeper than a standard web application. We started with research. We analyzed the specific barriers that prevent young students, particularly girls, from diving into STEM (Science, Technology, Engineering, and Mathematics). Our findings highlighted a critical issue: while educational resources exist on the internet, they are severely fragmented, overwhelming to navigate, and lack personalized guidance for beginners.
STEM-Connect👩🏻‍💻 is the direct solution to that research problem. It is an intelligent, centralized digital hub designed to aggregate high-quality STEM resources, interactive tutorials, and technical content. But what truly sets it apart is its applied AI integration. STEM-Connect isn't just a static directory; it uses artificial intelligence to actively guide students. By applying generative AI to our research framework, the platform personalizes the learning journey. It acts as an interactive mentor that helps curate and recommend specific resources based on a student's unique interests. It transforms a passive browsing experience into an active, guided pathway, bridging the gap between initial curiosity and actual technical skill development.
How we built it Building STEM-Connect required a careful balance of frontend architecture, data management, and AI implementation. My project partner, Ariana, and I collaborated closely to translate our research into a functional, user-friendly platform.
From a technical standpoint, a major challenge was integrating AI seamlessly into our frontend without making the interface feel overly complex. Coming from a cybersecurity engineering background at the National University of Engineering, my priority was also ensuring that the platform was safe and resilient. When introducing AI into an educational tool for younger audiences, you need strict guardrails. We spent significant time configuring the application to ensure the AI's interactions remained strictly within the bounds of safe, educational STEM content. We wanted the AI to feel like a supportive teacher, not just an unpredictable chatbot.

AWS Services used and a brief architecture overview To bring STEM-Connect from a local prototype to a production-ready application capable of winning a national AI fair, we relied on a robust AWS architecture:
  • AWS Amplify: This was the cornerstone of our deployment. We connected our GitHub repository directly to Amplify to establish a seamless continuous integration and continuous deployment (CI/CD) pipeline. Every time we push a new feature to the repository, Amplify handles the build and global deployment automatically.
  • Amazon Bedrock (AI Engine): To power the "applied AI" aspect of the platform, we utilized AWS's generative AI capabilities. This allowed us to build the intelligent recommendation features without having to train foundation models from scratch, keeping our architecture lean, secure, and highly scalable.
  • Amazon Route 53 & CloudFront: Provided out-of-the-box by Amplify to ensure our application is delivered securely and with low latency to users anywhere in the world.
  • AWS IAM: We implemented strict least-privilege policies to ensure our frontend only had the exact permissions needed to securely query our backend resources.

What I learned across the summer This summer has been incredibly rewarding. I learned that the best applications start with rigorous research—you have to truly understand the human problem before writing a single line of code. As an AWS Community Builder, I also deepened my expertise in merging cutting-edge AI with rapid deployment tools. The experience taught me how to move fast with AWS Amplify without compromising on security or architecture best practices.
Links
Tag a builder who inspired you A huge thank you to my amazing project partner, Ariana, for her tireless work and brilliant ideas on this build! I also want to tag Ana Cunha (@ana)—her insightful tips on using Kiro were incredibly helpful and served as a great resource for me while bringing STEM-Connect to life =).
Any opinions in this article are those of the individual author and may not reflect the opinions of AWS.
Enjoyed reading this content? Let the author know!

Your likes, comments, shares, and saves help creators reach more builders.

Loading recommendations

Loading article