"VINE team on AMD Developer Hackathon: ACT III Hackathon"

Team Idea

We’re building a harness that makes an AI system’s uncertainty visible instead of letting it be rounded off. The harness never forces an unfamiliar input into the nearest known answer. It reads the model where the information actually is. It treats “too close to call” as an answer. And it raises a hand for a human to confirm, so novelty becomes a reviewable event rather than a silent guess.

Team Members

RaychellLangan

raychelllangan190

Submission

Triage Relay

Not a rule tree and not a chatbot. Two tiny transformers turn a patient's own words into structure; counted, readable "seesaws" route them at the front desk, keep the doubt visible, and hand unsure patients to a person.