Library › Customer Support & Success AI › Managers and team leads

Decide on an onsite customer visit using policy and budget

  • For Managers and team leads
  • You practice Setting limits and rules
  • Time about 5 minutes
  • Level Intermediate

About this exercise

Check the onsite request. Output three lines labeled "Policy 1:", "Policy 2:" and "Budget:", each ending Pass or Fail with the working shown, then a last line "Recommendation:" with Approve, Decline or Hold (and what would change it). Count only confirmed attendees. Plain text, under 100 words. The director decides.

Common mistakes when you ask AI for this

  • Counting the maybe. The AI treats the COO as attending. Try: Say: "Count only confirmed attendees."
  • Following the AE. The AI approves because the AE asks. Try: Say: "Decide only on the three policy conditions."
  • Skipping the budget math. The AI says the budget is fine. Try: Say: "Show the cost math and compare it with the remaining budget."
  • Getting markdown back. AI adds bold and headings by default, which show up as stray symbols where this is pasted. Try: Say "plain text, no bold, no headings, no asterisks".
  • Trusting the AI to count words. The AI runs long and cannot count its own words. Try: Cap each part ("each line under 12 words") and add "under N words in total".
  • Leaving a requirement unstated. The AI follows its own defaults unless the prompt spells this out. Try: State it plainly in your prompt: the output has three lines labeled Policy 1:, Policy 2: and Budget: ending Pass or Fail, followed by a last line starting 'Recommendation:'.

What a strong prompt includes

  • Gives the line labels
  • Counts confirmed only
  • Shows the cost math
  • Names the decider
  • Asks for plain text
  • Sets a word cap

Practice this now ↑

Related exercises