Library › Research AI › Sales and customer success

Rank three territories on target accounts per rep

Practice: Catching mistakes and made-up facts. About 5 minutes.

About this exercise

Your VP asked which of 3 cities to add a sales rep in, based on target accounts per current rep. You want exactly 3 numbered lines, one per city, each showing the math (like "Tulsa: 240 / 2 = 120 per rep"), then a final line starting "Ranking:" from most to fewest accounts per rep. Use the updated account counts where a later note changes them, use only the numbers in the notes, and output nothing else in plain text.

Common mistakes when you ask AI for this

  • Using the old count. Boise's 180 is listed first, and the AI may miss the Nov 2 update. Try: Say: "Use the Nov 2 updated counts where they exist."
  • Not showing the math. The AI states a ranking without numbers, so you can't check it. Try: Add: "Show the math on each line, like 150 / 1 = 150."
  • Adding other factors. The AI weighs win rates and leave schedules, which changes the question you were asked. Try: Say: "Rank only on accounts per rep. Output only the 3 lines."
  • Not saying how many. The AI decides the length itself and usually returns more lines, one per city than you can use. Try: Be exact: "exactly 3 numbered lines, one per city."
  • Getting markdown back. AI defaults to bold labels and headings, which show up as stray symbols in an email to your VP. Try: Ask for "plain text, no bold, no headings."

What a strong prompt includes

  • Uses the update
  • Asks to show the math
  • Sets the ranking
  • Says exactly how many
  • Asks for plain text

Practice this now ↑

Related exercises