Explain why an AI-written SQL total is too high

About this exercise

An AI wrote a query that reports $482,000 of revenue, but finance says $310,000. Write exactly 3 labeled lines in plain text, under 100 words: Problem, Evidence and Fix. Evidence must use the exact form 'Order 1001: 3 rows x $200 = $600 instead of $200', and Fix must start with the word 'Sum' and say how to compute the total without repeating orders, with no code block.

Common mistakes when you ask AI for this

• Blaming the date filter. The AI suspects dates or timezones instead of the join. Try: Add: "The join to order_items repeats each order once per item."
• Abstract evidence. The AI says 'rows are duplicated' without an example. Try: Add: "Evidence: order 1001 has 3 items so $200 counts as $600."
• Pasting a new query. The AI rewrites a whole query in a code block. Try: Add: "Fix in one sentence, no code block: sum from orders alone."
• Leaving the format to chance. The AI picks its own length and layout unless told the exact shape. Try: Add: "Plain text, no bold or headings."
• Trusting the AI to count words. AI is bad at counting. Ask for a total word limit and it often lands over it. Try: Cap each part instead, for example "each line under 15 words."

What a strong prompt includes

• Asks for three labels
• Names the join cause
• Uses the order example
• Asks for a concrete fix
• Rules out code

Practice this now ↑

Related exercises

• Accrue unpaid wages for the working days after the last pay period (Finance AI · Accountants)
• Age a returns queue in business days and flag the ones over the limit (Customer Support & Success AI · Customer support teams)
• Alert sales to a competitor's price change, facts only (Research & AI Search · Product managers)
• Annualize recurring revenue without the one-time fee (Data AI · Finance and accounting)
• Answer a credit dispute with the full-hour rule and the math (Customer Support & Success AI · Customer support teams)