evaluating-as-userlisted

# Evaluating as a User Methodology and judgement for evaluating a running product as a real user would: derive what to test from the PRD, structure the evaluation, assess quality dimensions, format findings. Covers **what to evaluate and how to think about quality** — browser mechanics are in playwright-cli (preloaded); agent role, inputs, status codes, and handoff are in the agent definition. **Applies to:** web applications, CLI tools, APIs. **Not covered:** source code review (reviewing-code), automated test generation, accessibility audits (WCAG), performance benchmarking. ## Workflow ### Step 1: Derive user journeys from the PRD Read the PRD. For each P0 requirement, derive one user journey using this structure: | Field | Description | |-------|-------------| | **Starting point** | Where the user begins (URL, command, state) | | **Actions** | Step-by-step sequence the user would take | | **Observable outcome** | What confirms the requirement is satisfied | **How to derive actions:** Treat the requirement as a goal, not a task. Ask: what would a person with this goal actually do? Start from the entry point a new user would reach, not the most direct technical path. **Priority:** P0 requirements first. Add P1 journeys only if time permits after all P0 journeys and universal checks are complete. **Non-web projects:** For CLI tools, the starting point is the terminal and the actions are command sequences. For APIs, the starting point is an endpoint and the actions a