Shinobi tells you which Profs are really taking PhDs this year?
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle A friend of mine was applying for a PhD. She had a list of professors she wanted to work with and emailed them one by one. Most never replied. She asked me for help because I had been through this myself when I applied for my Master's. I had found a supervisor and secured a scholarship, so I thought I could…
This article details the story of an AI tool called Shinobi, developed to help applicants for PhD programs determine which professors are open to accepting students. The author explains how they helped a friend navigate the process of applying for a PhD, finding that the information was often scattered and outdated on professors' websites.
This led to the creation of Shinobi, which uses AI to analyze a professor's website and publications, providing a score and label indicating whether they are accepting students. The tool took a month to develop and is now available as a service for a small fee. The author breaks down the technical aspects of Shinobi, explaining the use of three open-source AI models: Gemma, vLLM, and Mastra.
They also discuss the stack used to run the tool, including SerpApi for web searches, OpenAlex and NSF for data, MongoDB Atlas for storage, Sentry for monitoring, and Render for deployment. The author emphasizes the importance of using accurate and up-to-date information when applying to PhD programs, and how Shinobi aims to streamline the process by providing clear and reliable data for applicants.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
