{"id":"fpa-hiring-freeze-trigger-test","audience":"fpa","category":"finance-work","track":"finance","technique":"verification","level":"intermediate","title":"Test a hiring-freeze trigger and recommend without deciding","free":false,"task":"You're checking whether a hiring-freeze trigger has been met. Write a prompt for plain text with exactly three lines starting \"Test:\", \"Math:\" and \"Recommendation:\". The rule: the trigger is met when revenue is below 95% of plan in two months in a row. Use the corrected figures, not the booked ones. The Recommendation line says the trigger is met or not met and that the CFO confirms. Under 90 words.","materialLabel":"Source material (attached to your prompt automatically)","material":"MONTHLY REVENUE VS PLAN - 2026 ($ thousands)\n\nPlan per month: 700\n\nJul actual: 680\nAug actual as booked: 650\nSep actual: 640\n\nCorrection note (Controller, Oct 6): August included a $30K customer credit that was booked twice. The corrected August actual is 680.\n\nPlan owner: FP&A. Hiring decisions are made by the CFO and COO together after a freeze trigger is reported. The July plan figure and the August plan figure are the same. No other corrections have been issued this year. The hiring policy was approved by the executive team in January and has not been invoked so far in 2026. Finance reports revenue to the executive team on the fifth business day of each month.\n\nTrigger rule from the hiring policy: freeze new requisitions if revenue is below 95% of plan in two consecutive months.\nOpen requisitions: 6.","rules":[{"type":"plainText"},{"type":"maxWords","max":90}],"promptHints":[{"label":"Names the three lines","patterns":["test","math","recommendation"]},{"label":"Uses corrected data","patterns":["correct","controller"]},{"label":"Sets the threshold","patterns":["95%","665"]},{"label":"Leaves the decision to a person","patterns":["cfo","confirm"]},{"label":"Caps length","patterns":["\\d+\\s*words","under \\d+"]}],"mistakes":[{"title":"Using the booked August","why":"The AI uses 650 and says two months in a row.","fix":"Say: \"Use the Controller's corrected August figure.\"","checks":["r0","r2"]},{"title":"Wrong threshold","why":"The AI compares to 700 instead of 95% of plan.","fix":"Add: \"Threshold = 95% of plan = 665.\"","checks":["r0","r1"]},{"title":"Deciding for the CFO","why":"The AI declares a freeze.","fix":"Add: \"Say met or not met and that the CFO confirms.\"","checks":["r2"]},{"title":"Markdown extras","why":"The AI adds bold labels, headings and a closing note.","fix":"Say: \"Plain text, no bold. Output only the lines asked for.\"","checks":["plainText"]},{"title":"Trusting the AI to count words","why":"AI is bad at counting and runs past word limits.","fix":"Ask for fewer words than the real cap and keep each part short.","checks":["maxWords"]}],"hint":"A rule test needs the right inputs. Say which figure is corrected, then ask for the threshold math before the verdict.","rubricLabels":["Output is exactly three lines starting Test:, Math: and Recommendation:, and Math shows the 95% threshold as 700 x 0.95 = 665 and uses corrected August 680 (not 650)","Math shows July 680 and August 680 at or above 665 and September 640 below it, so only one month is below the threshold","The Recommendation line says the trigger is not met and that the CFO confirms (or gives the decision to the CFO), without recommending cuts or a freeze"]}