Library › Finance AI › FP&A and financial analysts
Show how many units a markdown must sell to match margin dollars
- 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 helping a merchandising manager think about a markdown. Write a prompt for plain text with lines starting "Sale price:", "Margin before:", "Margin after:", "Units to match:" and "Read:". The markdown is a percent off the original price. Units to match is how many units at the sale price earn the same total margin dollars as 100 units at the original price. Sale price is the original price times (1 - markdown); margin percent is margin per unit divided by that price. Margin dollars only: ignore demand lift, advertising and carrying costs. Show the math. The Read line states the multiple of 100 units, as a fact only. Under 90 words.
Common mistakes when you ask AI for this
- Trusting the 30 percent rule. The AI says 30% more units is enough. Try: Say: "Compute units from margin dollars, not from the markdown percent."
- Skipping the margin per unit. The AI divides prices instead of margins. Try: Add: "Units = total margin dollars before / margin per unit after."
- Adding opinions. The AI says whether the markdown is wise. Try: Add: "Read: the multiple, as a fact only."
- Wrong line labels. The AI writes a paragraph instead of five labeled lines. Try: Add: "Five lines with these exact labels in order."
- 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 five lines
- Gives the formula
- Asks for the multiple
- Asks for the math
- 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)