From Zero to Leaderboard: Agent Evaluation — Wolfram Ravenwolf, Weights & Biases
Weights & Biases workshop teaches agent evaluation from scratch to public leaderboard.
“I evaluate models for breakfast, build agents at night, and preach AI all day.”
Wolfram Ravenwolf of Weights & Biases led a hands-on workshop at AI Engineer on building and evaluating AI agents using the W&B platform, culminating in leaderboard submission. The session targeted agent developers, model selectors, and evaluation newcomers. Content is introductory and workshop-setup-focused rather than a novel research or product announcement.