Skip to main content
CHAIN-OF-THOUGHT-PROMPTING5 MIN READ

Use least-to-most for policy comparison

Apply least-to-most prompting to a multi-policy comparison with source evidence.

Sofia needs a remote-work policy recommendation from messy notes across HR, Legal, managers, and employee feedback. Options -> constraints -> scores -> risks -> recommendation The common trap is asking for the final policy before the model has built the comparison table that justifies it. Options Define three real options: office-first, team-choice hybrid, and role-based remote eligibility. Options make the decision space explicit, which prevents the final answer from comparing an unstated favorite against straw alternatives. Constraints Extract constraints: labor-law coverage, manager readiness, onboarding quality, support load, and employee retention risk. Constraints keep the model from recommending a culturally appealing…

Read the full lesson

Sign up free — one personalized lesson every day, matched to your role and goals.

Already have an account? Sign in

← Back to library
Contact us