The AONE Handbook
Applied AI
Evaluating models honestly, and putting them in front of people without inventing anything.
Evaluating Indic speech recognition honestlyWhy word error rate misleads on Indian-language audio, what to measure instead, and how to design the human gate that stands between a model and an official record.13 min readGrounded assistants that refuse wellRetrieval, guardrails and refusal design for an assistant that speaks to customers — including the failure modes we hit building the one on this site.12 min read