Project Info
Inspiration
Students in technical fields are struggling more than ever to land internships and full-time roles, they need a way to gain experience. Motivated students and professionals seek to begin startup ventures, but struggle to get started and find the right people. Existing platforms such as LinkedIn have +1k applications in less than 1 hour (incredibly challenging to get experience) Y-Combinator Cofounder matching helps you find a founder, but the filtering capabilities lack context
What it does
Introducing Upstarter, an all in one platform where everyone wins. Are you a student looking for relevant experience? The recommender system will match you with a relevant project/startup. Are you an ambitious person looking for the right cofounders? The recommender system will once again help you match. Upstarter is a self-feeding pipeline where the users can quickly validate their ideas. If you don't move fast, you aren't a startup.
How we built it
FrontEnd: React-Native BackEnd: Flask AI Agent: Elasticsearch embeddings search, LangChain for QA Agent Database: Supabase
Challenges we ran into
Cold start problem in the recommender system, we solved it by generating our own synthetic data trying to recreate realistic scenarios. It was a large project
Accomplishments we're proud of
Implemented a Recommender system inspired from youtube and TikTok (includes candidate filtering and ranking). Implemented a working social media application which tackles relevant problems for students in technical fields.
What's next
- # 113 Video: https://www.youtube.com/watch?v=RbF5c8w-BKA Github: https://github.com/tonybuii2003/UpStarter
This project did not link a GitHub repository.
Analysis
No indexed repository for this project, so there are no commit stats to show.
Technology
- FlaskUnchecked
- LangChainUnchecked
- OpenAIUnchecked
- PythonUnchecked
- SupabaseUnchecked
No repository was indexed for this project, so these Devpost claims have not been checked against code.
AI coding agents
No repository was indexed, so agent usage could not be checked.
Detected from committed agent config files and commit authorship. Absence of a signal is not proof an agent was unused.
Codebase size
No repository was indexed, so there is no codebase to measure.
This project did not link a GitHub repository, so there is nothing to diagram.
This project did not link a GitHub repository, so its feature claims have not been checked against code.
Export this project's context (description, README, evidence, key source files) to chat with an AI agent elsewhere.