{"id":"risk-finding-ccce-single","audience":"compliance","category":"legal-compliance","track":"legal","technique":"format","level":"beginner","title":"Write one audit finding as condition, criteria, cause, effect","free":false,"task":"Write a prompt that turns workpaper notes into one finding with four plain-text lines starting Condition:, Criteria:, Cause:, Effect:. Under 100 words in total. Criteria quotes the policy. If the notes do not establish a cause, write \"Cause: Not yet established.\" and then attribute what was said. Effect uses only what the notes state, with no estimates.","materialLabel":"Your material (attached to your prompt automatically)","material":"WORKPAPER - Bank detail changes, Accounts Payable, Q3\nPolicy AP-12: \"Any change to a supplier's bank details must be verified by a call-back to a known number, and the call recorded in the ticket.\"\nTest: 25 bank detail changes sampled. 4 had no call-back recorded in the ticket.\nDiscussion with AP clerk (Neil Ostrow): the quarter-end rush was busy. No other explanation given; not verified.\nOutcome: no payment in the sample went to an account that turned out to be wrong. Nobody has checked the 4 changes with the suppliers yet.\nNote from the auditor: could be a bigger problem but not tested.","rules":[{"type":"plainText"},{"type":"maxWords","max":100}],"promptHints":[{"label":"Four labels","patterns":["condition:","criteria:","cause:","effect:"]},{"label":"Cause rule","patterns":["not yet established","unverified","attribute"]},{"label":"Quote policy","patterns":["quote","ap-12","policy"]},{"label":"No estimates","patterns":["no estimates","only what"]},{"label":"Caps length","patterns":["under \\d+","\\d+\\s*words"]}],"mistakes":[{"title":"Inventing a cause","why":"AI writes 'lack of training' or 'weak oversight' as the cause.","fix":"Say: \"If the notes don't establish a cause, write 'Not yet established.' and attribute what was said.\"","checks":["r0"]},{"title":"Not quoting the criteria","why":"AI paraphrases a general best practice instead of policy AP-12.","fix":"Say: \"Criteria: quote policy AP-12.\"","checks":["r1"]},{"title":"Speculating on effect","why":"AI warns of fraud risk and financial loss.","fix":"Say: \"Effect: only what the notes state; no estimates.\"","checks":["r2"]},{"title":"Getting markdown back","why":"AI adds bold, headings and bullets by default, which show up as stray symbols when pasted.","fix":"Say \"plain text, no bold, no headings, no asterisks\".","checks":["plainText"]},{"title":"Trusting the AI to count words","why":"AI is bad at counting and usually runs long, so a vague \"keep it short\" lands over the limit.","fix":"Cap each part instead of the total, for example \"each line under 15 words\".","checks":["maxWords"]}],"hint":"Give the four labels and say what to write when the cause is unknown.","mission":"Write a four-part finding without inventing a cause.","musts":["Four labeled lines","Policy quoted","Cause not invented"],"rubricLabels":["There are four lines starting Condition:, Criteria:, Cause:, Effect: in that order, and Condition says 4 of 25 changes had no call-back recorded","Criteria quotes or closely follows policy AP-12 (call-back to a known number, recorded in the ticket)","Cause starts with \"Not yet established\" and attributes the quarter-end rush to the AP clerk, and Effect says no wrong payment was found in the sample without estimating wider impact"]}