Human First Capital

Finding the right people for a hackathon—whether teammates, organizers, or future hosts—is often a manual and fragmented process spread across dozens of websites and communities. This project uses BrightData's MCP to create an autonomous talent discovery agent. Instead of repeatedly searching the web myself, I provide a configuration describing the people I'm looking for, and the agent continuously gathers and evaluates candidates from across the internet. Beyond discovery, the system creates rich profiles of individuals using publicly available information. Rather than simply collecting links and social accounts, it builds a narrative around a person's work, projects, interests, collaborators, and contributions over time. This allows users to understand not only what someone has built, but also who they have worked with, what communities they participate in, and how their interests have evolved. The system learns from my feedback, improving future recommendations and surfacing people who match my interests, experience, and past hackathon projects. It can also identify past hackathon organizers and people planning future events, helping users build stronger connections within the hackathon ecosystem. Using this system, I have already discovered several impressive builders and multiple hackathons—both past and upcoming—that I likely would not have found through traditional search alone. What makes this project stand out is that it transforms web discovery from a one-time search into a continuously running, feedback-driven process. By combining autonomous web discovery, profile synthesis, relationship mapping, and personalized learning, the system acts as a persistent research partner that helps users discover opportunities and the stories behind the people creating them. The result is a continuously improving discovery engine that turns web research into an automated workflow.