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.
Balance employee-owned topics, support, feedback, development, and follow-up without scripting judgment
Cluster feedback by underlying progress and breakdown while preserving source, variation, and uncertainty
Strengthen task control and output reliability while removing redundancy, decorative roles, and low-value prose
Turn rubric evidence into specific coaching while keeping revision decisions and prose with the learner
Turn supplied study material into atomic retrieval cards with scheduling and quality checks
Convert recurring, evidenced language errors into spaced contrastive practice with feedback, retries, and transfer checks
Create diagnostic questions that reveal reasoning and inform the next teaching move
Reconcile weekly sales and customer feedback into a decision-ready report without overstating causes
Translate confirmed user and business needs into scoped stories and observable behavior without inventing product decisions
Communicate observed progress, current needs, and shared next steps without labels or unsupported inference
Compare intent, inputs, instructions, and real outputs to identify evidenced failure modes instead of guessing
Create psychologically safer, evidence-seeking questions that move from outcomes and context to controllable experiments
