Inspiration
A friend who seems to always have game ideas at the ready.
What it does
A user enters a prompt for a game idea. The prompt is fed to Gemini with references to skill and role collections to synchronize Gemini's output with the stored freelancers database. Lists of matching freelancers are returned organized by role and ordered by match score.
How we built it
Developed a FastAPI based backend. Connected it to a MongoDB Atlas database using Motor, and hooked up a connection to the Gemini API.
Challenges we ran into
Getting the Gemini API integration to function properly. Lots of debugging :). I also haven't learned much about frontend work yet, so I had to walk through every detail with Copilot to get it functional.
Accomplishments that we're proud of
I could use my backend knowledge to understand what Copilot was suggesting and correct mistakes on the spot.
What we learned
The basics of how to use MongoDB Atlas and integrating a Gemini API key into a project. How to structure LLM output to compare against an existing database.
What's next for Game Freelancer Matcher
- User profiles to save matches and return freelancer analytics.
- Figuring out a way to connect Game Freelancer Matcher to existing freelancer databases.
- Expanding current skill and role catalogs to encompass the breadth of actual skills present in the game development world.
Log in or sign up for Devpost to join the conversation.