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 research questions into realistic, non-leading tasks with success evidence, observations, prompts, and prototype limits
Turn a prompt contract into repeatable cases with expected behavior, evidence rules, and pass criteria
Investigate real work gaps, causes, conditions, and transfer needs before prescribing training
Translate standards into observable, distinct, and consistently scorable criteria
Diagnose the highest-impact problems without replacing the author’s intent
Review observable outcomes, process conditions, and improvement experiments without assigning blame
Turn an approved close process into sequenced checks with evidence, reconciliations, exceptions, approvals, and reopening rules
Structure a joint review around outcomes, evidence, unresolved value, risks, and mutually confirmed next steps
Evaluate two prompts on matched inputs instead of judging wording, length, or a single attractive output
Allocate limited study time by exam date, importance, current mastery, energy, and uncertainty
Compare a draft response with every customer question, fact, constraint, and requested outcome
Map each atomic claim to evidence, contradiction, source quality, and a calibrated status
