Evals are the new PRDs, @hwchase17 It might be my takeaway of the @LangChain Chicago meetup tonight.

Harrison Chase suggests that evaluations (evals) are becoming as critical to AI/LLM development as Product Requirements Documents (PRDs) traditionally were, implying a shift in how teams validate and iterate on language model applications. This reflects the growing importance of systematic testing and measurement in LangChain and broader AI development practices.

Source: Harrison Chase (X) | 2026-06-23