Skip to content
PlatroomPlatroom
← Your pathLevel 1 · Beginner

The entitlement calendar, built backwards from a hearing

Lesson 3 of 6 · From flip to development

1 · Learn the move · Cognitive verifier

A rezoning lives or dies on dates you do not control, and the one date everyone fixes on - the hearing - is the one furthest from where the work starts. Build the calendar backwards from it. The cognitive verifier pattern keeps the counting honest: the model first breaks the job into questions (what must be true by the hearing, whose task each item is, what must happen before filing, what could move the hearing), then derives each date in the open from a quoted clause, then re-checks every date against its clause and its day count. Two traps sit in every procedure. Most do not say whether days are calendar or business days, and most do not say what happens when a deadline lands on a weekend. Both become labelled assumptions or open questions, never silent choices. And the hearing itself is a target: the planning office schedules it once the application is complete. The calendar never says it will be heard on that date, or approved at all.

Build my rezoning calendar backwards from the target hearing date. First list the questions the calendar must answer. Then derive each date from a quoted clause, arithmetic shown, tagged [COMPUTED - verify on a calendar]. Then re-check every date, flag the day-count convention and any weekend deadline. Anything the procedures do not state is UNKNOWN.

2 · Your turn. You write the prompt

You hold 41 acres in Kesterly County zoned A-1 and want a rezoning heard at the planning commission's meeting on Tuesday, March 16, 2027. You have pasted the planning office's application procedures, its published 2027 meeting calendar, and your surveyor's email quoting 'four to six weeks from authorization' for the boundary survey and legal description. Write the prompt that builds the calendar backwards from the hearing and shows every count.

Write the prompt for this scenario as given, or swap in a real one from your own work. The score works the same either way.

Remember: the AI sees only your prompt, not this page. If the situation isn't in your prompt, it doesn't exist.

Optional. These shape the output when you run your prompt below, not your score.