Internship Agent

• 

  working screenshot

Inspiration

As a first-year CS student, I noticed how time-consuming it is to apply for internships — reading job descriptions, figuring out if you're a good fit, and writing personalized messages for each one. I wanted to automate that entire process.

What it does

Internship Agent takes a job description and instantly scores how well your profile fits the role (out of 10 with reasoning), then drafts a personalized application message highlighting your matching skills and projects.

How we built it

• Python + Streamlit for the web interface
• Groq (LLaMA 3.3) for AI reasoning
• MongoDB Atlas for candidate profile storage
• python-dotenv for environment management

Challenges we ran into

Python 3.14 has SSL compatibility issues with MongoDB's driver, so the profile data was hardcoded for the demo. Also managing Gemini API free tier quota limits required switching to Groq.

Accomplishments that we're proud of

Built a fully working AI agent solo in one night that produces genuinely useful, personalized output.

What we learned

How to connect LLMs to real data, structure effective prompts, and deploy a working agent end-to-end.

What's next for Internship Agent

• Fix MongoDB integration with a compatible Python version
• Let users upload their resume as PDF
• Track multiple applications and suggest which ones to prioritize

Built With

• groq
• llama-3.3
• mongodb-atlas
• python
• streamlit