Topics
AI review prompt templates for diagnosing drafts, checking evidence, organizing feedback, finding risks, and planning targeted revisions
Useful feedback names observable issues, their impact, and the evidence behind them. These recipes avoid guessing motives, separate blocking problems from preferences, and preserve the human reviewer’s judgment.
Turn observed behavior and impact into a fair conversation that invites context and agrees on next evidence
Convert observations and contributing conditions into small, owned, measurable system changes
Reconcile comments against the brief and sequence revisions without silently accepting scope changes
Convert traceable customer questions and friction into useful topics without overstating demand
Extract the task contract, variables, decision rules, and checks that actually produced a useful result
Turn session observations into evidence-counted usability issues without blaming participants or overstating prevalence
Aggregate ratings and comments into privacy-safe themes with denominators, variation, counterevidence, and limits
Practise one realistic exchange at a time with bounded corrections, retries, adaptive difficulty, and progress evidence
Practice one answer at a time with evidence-based feedback, follow-ups, and a final improvement pattern
Diagnose a learner's draft against instructions and rubric while preserving authorship
Trace causality, knowledge, motivation, setup, payoff, tension, and scene load without replacing the writer's story
Organize observable work evidence, expectations, context, and fair questions without inferring motives or predetermining outcomes
