Design a PM-runnable evaluation suite for an AI feature, implementing Anthropic's eval framework (Demystifying Evals for AI Agents). Walks the user through Anthropic's 8-step roadmap — source tasks from real failures, write unambiguous tasks with reference solutions, build balanced problem sets (tes
Design a PM-runnable evaluation suite for an AI feature, implementing Anthropic's eval framework (Demystifying Evals for AI Agents). Walks the user through Anthropic's 8-step roadmap — source tasks from real failures, write unambiguous tasks with reference solutions, build balanced problem sets (test where behavior should AND shouldn't occur), choose graders thoughtfully (code / model / human). Us