Library › Finance AI › FP&A and financial analysts
Test a hiring-freeze trigger and recommend without deciding
- For FP&A and financial analysts
- You practice Catching mistakes and made-up facts
- Time about 5 minutes
- Level Intermediate
About this exercise
You're checking whether a hiring-freeze trigger has been met. Write a prompt for plain text with exactly three lines starting "Test:", "Math:" and "Recommendation:". The rule: the trigger is met when revenue is below 95% of plan in two months in a row. Use the corrected figures, not the booked ones. The Recommendation line says the trigger is met or not met and that the CFO confirms. Under 90 words.
Common mistakes when you ask AI for this
- Using the booked August. The AI uses 650 and says two months in a row. Try: Say: "Use the Controller's corrected August figure."
- Wrong threshold. The AI compares to 700 instead of 95% of plan. Try: Add: "Threshold = 95% of plan = 665."
- Deciding for the CFO. The AI declares a freeze. Try: Add: "Say met or not met and that the CFO confirms."
- Markdown extras. The AI adds bold labels, headings and a closing note. Try: Say: "Plain text, no bold. Output only the lines asked for."
- Trusting the AI to count words. AI is bad at counting and runs past word limits. Try: Ask for fewer words than the real cap and keep each part short.
What a strong prompt includes
- Names the three lines
- Uses corrected data
- Sets the threshold
- Leaves the decision to a person
- Caps length
Related exercises
- Accrue goods received but not invoiced at PO price (Finance AI · Accountants)
- Accrue unbilled legal fees from a range using the midpoint policy (Finance AI · Accountants)
- 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)
- Age open purchase orders and assign an action for each (Finance AI · Accountants)