ai-evals

Systematic evaluation framework for AI products using practitioner-driven methodologies. Help the user create systematic evaluations for AI products using insights from AI practitioners. When the user asks for help with AI evals: Brendan Foody: "If the model is the product, then the eval is the product requirement document." Evals define what success looks like in AI products—they're not optional quality checks, they're core specifications. Hamel Husain & Shreya Shankar: "Both the chief product officers of Anthropic and OpenAI shared that evals are becoming the most important new skill for product builders." This isn't just for ML engineers—product people need to master this. Building good evals involves error analysis, open coding (writing down what's wrong), clustering failure patterns, and creating rubrics. It's a systematic process, not a one-time test. For all 2 insights from 2 guests, see references/guest-insights.md - Guides users through understanding what "good" looks like, designing rubrics and test cases, and implementing scoring criteria aligned with actual user needs - Emphasizes manual review and error analysis as prerequisites to building meaningful evals, with structured workflows for clustering failure patterns - Flags common pitfalls including vague criteria, LLM-as-judge without validation, and Likert scales; recommends binary Pass/Fail decisions instead -...