Vision Learning

As students ourselves, we deeply understand the value of education. Now, as we transition into the professional world, we recognize that professional development is no longer optional—it’s a necessity. However, we’ve noticed that the resources available are often too vague or generic, lacking the personal touch needed for meaningful growth. This inspired us to create Vision Learning, a personalized learning tool that empowers every individual to achieve their potential.

Vision Learning focuses on preparing users for interviews and enhancing professional development. It evaluates critical aspects like confidence, knowledge, and eye contact, providing personalized feedback to identify strengths and areas for improvement. Users can practice solving problems in real-time and then interact with an AI to refine their communication skills, creating a comprehensive and tailored development experience.

We used HTML, CSS, and JavaScript to create an intuitive front-end interface, while Python and Flask power the backend. AWS services like Polly and Rekognition were integrated to add personalization, enabling features like voice synthesis and facial recognition to make the experience more engaging and insightful.

Connecting the front end to the back end was a significant challenge, as not all services interacted seamlessly. We encountered issues with ports being in use and multiple services competing for resources, which caused delays and complications during development. Debugging and streamlining these interactions required substantial effort and collaboration.

We’re proud of delivering a truly personalized learning experience that includes human-like interactions and step-by-step guidance. The smooth and efficient resource allocation we achieved after resolving technical hurdles ensures a flawless user experience. Additionally, the thoughtful UI/UX design adds a positive, approachable touch that enhances the overall functionality of the platform.

This project taught us the importance of integrating diverse technologies to create a cohesive system. We learned how to troubleshoot complex technical issues, like resource conflicts, and gained valuable experience in leveraging AWS services to enhance personalization. Most importantly, we learned how impactful technology can be when it’s designed with empathy and user needs at the forefront.

We plan to further enhance Vision Learning by integrating AWS Transcribe, allowing the AI to offer even more natural and personal interactions through advanced speech capabilities. Additionally, we aim to expand our interview preparation tools to cater to people from diverse majors and professional backgrounds, making Vision Learning an inclusive and indispensable resource for all.