{"id":"data2-email-ask-data-owner-three-questions","audience":"analysts","category":"data","track":"data","technique":"audience","level":"beginner","title":"Email a data owner three questions about an unclear column","free":false,"task":"You found a column you don't understand and need its owner, Wen Zhao in data engineering, to explain it. Write a plain-text email under 90 words with a Subject: line and exactly 3 questions, each on its own line starting 'Q1:', 'Q2:' and 'Q3:'. Include one example row, don't blame anyone, and don't ask for anything else.","materialLabel":"What you found (attached to your prompt automatically)","material":"Table: subscriptions_daily (Orchard Software warehouse)\n\nColumn: status_cd, values seen: A, P, X, 7\nColumn: end_dt, values seen: dates, plus 9999-12-31 on many rows, and NULL on others\n\nExample row: sub_id 48213, customer 3391, status_cd = 7, start_dt 2025-03-01, end_dt = 9999-12-31, mrr = 80.00\n\nFacts:\n- There is no description for status_cd or end_dt in the data catalog.\n- A = 62% of rows, P = 21%, X = 15%, 7 = 2%.\n- You are building a churn report and need to know which rows are active.\n- 9999-12-31 may mean \"no end date\", but you don't know; NULL may mean the same, or missing data.\n- The churn report is due Friday.\n- Wen answers in Slack within a day.","rules":[{"type":"plainText"},{"type":"maxWords","max":90}],"mistakes":[{"title":"Vague questions","why":"The AI asks 'can you explain these columns?'","fix":"Add: \"Q1 asks what A, P, X and 7 mean; Q2 asks about 9999-12-31; Q3 asks about NULL.\"","checks":["r0"]},{"title":"No example","why":"Without the row, Wen has to look it up.","fix":"Add: \"Include the example row: sub_id 48213, status_cd 7, end_dt 9999-12-31.\"","checks":["r1"]},{"title":"Blaming or adding asks","why":"The AI says the docs are missing or asks for a meeting.","fix":"Add: \"No blame, no extra requests.\"","checks":["r2"]},{"title":"Leaving the format to chance","why":"The AI picks its own length and layout unless told the exact shape.","fix":"Add: \"Plain text, no bold or headings.\"","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":"Names the reader","patterns":["wen"]},{"label":"Asks for the Q lines","patterns":["q1:","q2:","q3:","exactly 3"]},{"label":"Gives the example row","patterns":["48213","example row"]},{"label":"Gives the context","patterns":["churn report","friday"]},{"label":"Sets limits","patterns":["no blame","under 90 words"]}],"hint":"Good questions to a data owner are specific, include an example, and ask nothing extra.","mission":"Ask Wen about this unclear column.","musts":["Three Q lines","Example row","No blame"],"rubricLabels":["The email starts with a Subject: line, mentions the subscriptions_daily table and the churn report, and includes the example row (sub_id 48213, status_cd 7, end_dt 9999-12-31)","There are exactly three questions on lines starting Q1:, Q2: and Q3: covering what the status_cd values A, P, X and 7 mean, what 9999-12-31 in end_dt means, and what NULL in end_dt means","The email doesn't blame anyone for missing documentation, doesn't ask for anything beyond the three questions, and does not state a guess as fact"]}