AI expert-matching for organizations: builds a knowledge graph from Jira, GitHub, internal docs and resumes — you can even query a person's digital twin before reaching out.
Not knowing who to ask is a pain that grows with headcount, which means the judges were likely users of the problem themselves. What lifts it above an idea is where the graph comes from: Jira, GitHub, internal docs, resumes — sources that already sit inside a company. Letting people query a digital twin before pinging the human is a practical courtesy toward the expert's time and easy to defend on stage. Building on the Llama API kept it aligned with the host's purpose.
Summaries are written by this site. Project pages include demo videos, screenshots and the team's own write-up (videos may autoplay).