Library › AI Evals › Finance and accounting

Write 4 test cases for an AI accounts-payable assistant

Practice: Giving the right context. About 5 minutes.

About this exercise

Before your AP team trusts its AI invoice assistant, you want 4 test cases: a duplicate invoice, an invoice in a foreign currency, an invoice with no PO number, and one over the approval limit. Write exactly 4 numbered lines, each 'N. Case | Invoice: short exact description (vendor, number, amount) | Expected: what the assistant does per the AP rules'. Plain text, under 170 words.

Common mistakes when you ask AI for this

  • Tests no one can run. The AI writes 'an invoice in another currency' with no vendor, number or amount. Try: Say: "Each Invoice names a vendor, invoice number and amount."
  • Not naming the cases. The AI tests normal invoices and skips the ones that cost money last time. Try: List them: "duplicate, foreign currency, no PO, over $10,000."
  • Vague expected results. The AI writes 'flags it for review' instead of the exact queue and label. Try: Add: "Expected uses the rules' exact labels and queues."
  • A long test plan. The AI writes a full testing strategy. Try: Be exact: "Exactly 4 numbered lines."

What a strong prompt includes

  • Names the 4 cases
  • Asks for specific invoices
  • Ties expected to the rules
  • Says exactly how many
  • Asks for plain text

Practice this now ↑

Related exercises