Library › Leadership AI › Consultants

Build a two-level issue tree for slow onboarding using given data

  • For Consultants
  • You practice Asking for a format you can use
  • Time about 5 minutes
  • Level Beginner

About this exercise

Build a two-level issue tree for why customer onboarding takes 38 days instead of 25. Plain text numbered like 1, 1a, 1b, 2, 2a, 2b, 3, 3a, 3b: three branches with two sub-questions each, nine lines in total. Each line is under 14 words and each sub-question can be answered from the data in the notes. Branches must be stages of onboarding. Last line: Pull first: and one data source.

Common mistakes when you ask AI for this

  • Wrong structure. The AI adds extra levels. Try: Say: "Exactly 1, 1a, 1b, 2, 2a, 2b, 3, 3a, 3b."
  • Unavailable data. The AI asks for satisfaction scores. Try: Say: "Only data in the available list."
  • Branches not stages. The AI uses themes like people and process. Try: Say: "Branches are the three onboarding stages."
  • Markdown. The AI uses nested bullets. Try: Say: "Plain text with the numbering given."
  • Trusting the AI to count words. AI is bad at counting. Ask for a total word limit and it often lands over it. Try: Cap each line: "each line under 14 words."
  • Trusting the AI to count words. AI is bad at counting. Ask for a total word limit and it often lands over it. Try: Cap each part instead, for example: "each line under 12 words."

What a strong prompt includes

  • Numbering
  • Stages
  • Available data
  • Pull first line
  • Short

Practice this now ↑

Related exercises