{"id":"exec-budget-reforecast-bridge-check","audience":"executives","category":"leadership-work","track":"leadership","level":"intermediate","technique":"verification","title":"Build a budget bridge and check it against the stated total","free":false,"task":"Build a bridge table with the header Item | Change ($M) | Running total ($M), starting with a row for the original budget and then one row per adjustment in the order listed. Then one line: \"Check: computed\" with the final number, \"vs stated\" with the stated total, and then either \"Match\" or \"Mismatch\". Plain text, under 90 words.","materialLabel":"Reforecast notes (attached to your prompt automatically)","material":"Operating budget reforecast, FY25 (in $ millions)\n\nOriginal approved budget: 5.0\n\nAdjustments, in the order agreed:\n1. New hires approved in August: +0.4\n2. Travel freeze savings: -0.2\n3. Vendor price rise on the hosting contract: +0.3\n4. Tool consolidation savings: -0.1\n\nThe summary slide states the reforecast total as 5.6.\n\nNot included in the reforecast: a possible $0.5M marketing request that has not been approved.\n\nBackground: the CFO's team prepared the summary slide on Friday, before the tool consolidation savings were finalized, and the board meets on Thursday. The board pack asks that every reforecast shows how each adjustment moves the total, in the order the adjustments were agreed, so that directors can follow the path from the original number to the new one. Amounts are rounded to the nearest 0.1 million.","rules":[{"type":"maxWords","max":90},{"type":"plainText"}],"mistakes":[{"title":"Trusting the stated total","why":"The AI ends at 5.6.","fix":"Say: \"Compute the running total yourself and compare it to the stated total.\"","checks":["r1","r2"]},{"title":"Math slips","why":"The AI skips a step or mis-adds.","fix":"Say: \"Show the running total after each row.\"","checks":["r1"]},{"title":"Adding the unapproved request","why":"The AI adds 0.5.","fix":"Say: \"Use only the four listed adjustments.\"","checks":["r2"]},{"title":"Wrong table","why":"The AI reorders or merges rows.","fix":"Say: \"Original budget then four adjustments in order.\"","checks":["r0"]},{"title":"Markdown","why":"The AI bolds the check line.","fix":"Say: \"Plain text.\"","checks":["plainText"]},{"title":"Trusting the AI to count words","why":"AI is bad at counting. Ask for a total word limit and it often lands over it.","fix":"Cap each part instead, for example: \"each line under 15 words.\"","checks":["maxWords"]}],"promptHints":[{"label":"Gives the header","patterns":["item \\|","running total"]},{"label":"Row order","patterns":["original budget","in the order"]},{"label":"Running total each row","patterns":["running total"]},{"label":"Gives the check line","patterns":["check: computed","mismatch"]},{"label":"Only listed adjustments","patterns":["only the","listed"]}],"hint":"Give the header, row order and the exact form of the check line.","rubricLabels":["Has the header Item | Change ($M) | Running total ($M) and exactly five rows: Original budget then the four adjustments in the listed order","The running totals are 5.0, 5.4, 5.2, 5.5 and 5.4","The last line is \"Check: computed 5.4 vs stated 5.6 - Mismatch\" (or equivalent wording with those numbers and the word Mismatch) and the marketing request is not included"]}