Maggie Konstanty
AI product manager focused on building and evaluating AI agents for food ordering and ecommerce at scale, with deep practical experience in LLM evaluation, failure-mode analysis, and embedding evaluations into product teams.
Best podcasts with Maggie Konstanty
Ranked by the Snipd community
29 snips
Apr 21, 2026 • 41min
It's 2026, and We're Still Talking Evals
Maggie Konstanty, an AI product manager who builds and evaluates large-scale agents for food ordering and ecommerce. She explains why single accuracy numbers mislead. She contrasts pre‑ship sims with production traces. She digs into drop‑off analytics, the dangers of many disconnected evaluators, and why teams often end up building custom eval tooling.
