weScope

Inspiration

As undergraduate students ourselves, we've witnessed firsthand the struggle of finding research opportunities that align with our career goals.

• Students don't know which labs match their skills and interests
• Research opportunities are scattered across department websites, email lists, and word-of-mouth
• The application process feels like shooting in the dark
• Many qualified students miss out simply because they don't know where to look

What it does

Our app utilizes the user’s resume, gpa, and areas of interests and uses AI to help generate a variety of research opportunities and professors for them to connect with. It also aligns students with what next steps they should take and why each specific position is tailor to them specifically.

How we built it

We started with user-centered design, mapping out the complete student journey: First we collected user input to understand where the problem lies. Then we moved onto the following:

1. Onboarding Flow - Collecting key data points:

   • Academic year (Freshman → Post-grad)
   • Past research experience
   • Field of study and specific interests
   • Post-graduation goals (Industry, Research, Grad school, etc.)
   • Resume/transcript upload

2. Wireframing in Figma - Created prototypes including:

   • Multi-step onboarding screens
   • Loading states showing AI processing
   • Results dashboard with match scores (used V0)
   • Individual position detail pages

3. Brand Identity - Developed the WESCOPE brand:

   • Molecular network logo (representing connections in research)
   • Purple color palette (#6B46C1, #E8DEFF) evoking academic/scientific themes
   • Clean, modern UI inspired by consumer apps students already use

AI Architecture: The Matching Engine

We would use an AI-powered matching system that goes beyond simple keyword filtering:

1. Resume & Transcript Parsing

We would use Natural Language Processing (NLP) to extract structured data from unstructured documents. We would use a Large Language Model to generate personalized match explanations. This approach gives tailored recommendations to the user based on their experiences, and bridges the gap in finding research opportunities for undergraduate and post grad students.

Challenges we ran into

1) Defining the problem

• Narrowing the focus from “help students find research” to a clear, trajectory-based academic transition problem rather than building another generic search tool.

2) Meaningful AI

• Ensuring AI added real value through skill extraction and semantic matching instead of simple keyword filtering.

3)Scope control

• Limiting the prototype to realistic, buildable features while still demonstrating innovation and long-term scalability

Accomplishments that we're proud of

We are proud of our personalized recommendations and readable user interface as well as that this app is aiming to solve a real problem that most student face.

What we learned

We learned that we need to narrow scope to make an effective solution.

What's next for weScope

Next for weScope we would try to integrate a tracker thing to track applications of research positions and introducing it to undergraduates and graduates of other institutions.

Built With

• figma
• v0