Audit and improve one live chain-of-thought prompt Use this on a real work artifact: vendor renewal, incident triage, policy recommendation, data analysis, hiring scorecard, or roadmap trade-off. I will rewrite my [specific prompt] using Goal, Source, Criteria, Reason, Check, and Answer before I use it. I will save the old output and new output, then note one quality difference. In 3 days, check whether the rewritten prompt produced a more grounded, reviewable answer. A vendor-renewal prompt where the model must compare cost, reliability, and switching risk from pasted notes An incident-triage prompt where the model must separate evidence, likely cause,…
Read the full lesson
Sign up free: one personalized lesson every day, matched to your role and goals.
Already have an account? Sign in