Group Project Mediator AI

• 

  Website

Inspiration

Group projects are a common source of stress for students. Miscommunication, unclear responsibilities, and last-minute scrambling often turn collaboration into conflict. This project was inspired by our own experiences in group work, where frustration usually stemmed from unclear expectations rather than a lack of effort. We wanted to build a tool that helps groups reset, communicate better, and move forward productively.

What it does

Group Project Mediator AI helps student teams navigate group work more effectively. Users can paste group chat messages, meeting notes, or written concerns into the app. Using the Google Gemini API, the system:

• Summarizes what’s actually happening
  
• Detects conflicts, tone issues, and missing tasks
  
• Assigns fair and actionable responsibilities
  
• Generates a polite, human-sounding message teams can send to their group
  The goal is to reduce tension, improve communication, and help teams focus on completing their work.

How we built it

We built the backend using Python and Flask, with the Google Gemini API handling natural language understanding and reasoning. Carefully designed prompts guide Gemini to analyze group dynamics, identify issues, and generate collaborative responses.

The frontend was built with HTML and CSS, providing a simple interface where users can submit conversations and view clearly formatted results.

Challenges we ran into

One of the biggest challenges was getting the AI’s tone right. Early outputs were either too formal or too verbose. We iterated on prompt design and formatting to ensure responses felt supportive, neutral, and human.

We also faced technical challenges integrating the Gemini API, managing environment variables, and debugging Flask under tight time constraints.

Accomplishments that we're proud of

• Successfully integrating the Google Gemini API into a working application
  
• Designing prompts that demonstrate emotional intelligence and reasoning
  
• Building a complete end-to-end product within a limited timeframe
  
• Creating a tool that solves a real, relatable problem for students
  

What we learned

• Prompt engineering plays a major role in output quality
  
• AI systems can meaningfully support emotional and social dynamics
  
• Clear UX and formatting are just as important as backend logic
  
• Debugging and iteration are essential parts of rapid development
  

What's next for Data Queens’ Project

In the future, we’d like to:

• Add real-time collaboration features
  
• Allow users to adjust tone (polite ↔ firm) in generated messages
  
• Support multiple project timelines and deadlines
  
• Expand the tool beyond academics to workplace and team settings
  

Built With

• css
• flask
• gemini
• github
• html
• python
• vscode