Introduction

Preparing for an important meeting often involves searching across multiple websites, reviewing company updates, and collecting relevant information.

I wanted to explore how AI and automation could make this preparation process easier. That idea led me to build MeetMind AI, an AI-powered pre-meeting research assistant.

This project was developed as part of my hackathon journey and gave me practical experience in building, integrating, and deploying an AI-based application.

What is MeetMind AI?

MeetMind AI is designed to help users prepare for meetings by collecting relevant company information and organizing research into a meeting-focused workspace.

The project aims to bring research, briefing preparation, and source references together in one application.

Technology Stack

The project uses:

• Python – Core programming language
• Streamlit – Application interface
• Tavily API – Web research integration
• Google Gemini – AI model integration
• GitHub – Source-code management
• Streamlit Community Cloud – Application deployment

How the Application Works

The intended workflow is:

1. Enter the company or organization.
2. Provide meeting details and participants.
3. Specify the meeting objective.
4. Retrieve relevant web research using Tavily.
5. Use the AI integration to prepare a meeting-focused briefing.
6. Review the research sources and references.

Application Features

The application includes several workspace sections:

• Dashboard
• New Research
• My Briefings
• Evidence Explorer
• Settings

These sections organize the research workflow and provide a foundation for future improvements.

Development Challenges

Building this project was a valuable learning experience.

Some of the areas I worked through included:

• Integrating external APIs into a Python application.
• Configuring API keys securely using environment variables and Streamlit Secrets.
• Managing Python dependencies through "requirements.txt".
• Resolving deployment and dependency-related issues.
• Connecting the GitHub repository to Streamlit Community Cloud.
• Testing the application after deployment.

Each challenge helped me understand more about the practical side of software development.

What I Learned

Through MeetMind AI, I gained practical exposure to:

• API integration
• Python application development
• Streamlit UI development
• Environment and secrets management
• Git and GitHub workflows
• Cloud deployment
• Debugging and testing

Most importantly, I learned that building a working project requires patience, experimentation, and continuous improvement.

What's Next?

MeetMind AI is a starting point for further development.

Future improvements could include:

• More structured meeting briefings
• Better evidence organization
• Improved research accuracy
• PDF briefing exports
• Enhanced user experience

Conclusion

MeetMind AI represents my journey from an idea to an AI-focused application.

As a first-year Computer Science student specializing in AI and Machine Learning, projects like this help me connect classroom learning with practical development.

I'm looking forward to building more, learning more, and improving with every project.

Build. Experiment. Learn. Repeat.

Project Links

• GitHub Repository: https://github.com/nischithhg5-maker/MeetMind-AI
• Live Application: https://meetmind-ai-qbzjtdeumruokxrvqhcnwc.streamlit.app/
• Demo Video: https://canva.link/y63fbp14qydm1ly
• My technical article: https://www.linkedin.com/pulse/meetmind-ai-building-ai-powered-pre-meeting-research-nischith-h-g-dzr6f

Feedback and suggestions from the developer community are welcome!

Python #AI #Streamlit #GenerativeAI #WebDevelopment