Library › Leadership AI › Consultants
Rate vendor risks High, Medium or Low using a stated rule
- For Consultants
- You practice Catching mistakes and made-up facts
- Time about 5 minutes
- Level Intermediate
About this exercise
Rate each vendor's risk using this rule: High = a critical service with no backup vendor OR a failed security review; Medium = critical with a backup but a delayed security review; Low = everything else. Output a markdown table with columns Vendor, Critical?, Backup?, Security review, Rating. Use the latest status, one row per vendor, and nothing else.
Common mistakes when you ask AI for this
- Counting a second region as a backup. The AI says Cloudmore has a backup. Try: Say: "Backup means a different company."
- Old Mailbird status. The AI keeps the review as delayed. Try: Say: "Mailbird's review passed Nov 6."
- Misapplying the rule. The AI rates Docuvia High. Try: Say: "High applies only to critical services or failed reviews."
- Wrong table. The AI changes columns. Try: Say: "Columns: Vendor, Critical?, Backup?, Security review, Rating."
- 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 it: "cells hold short values only."
- 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
- Columns
- Rule
- Backup definition
- Update
- Only table
Related exercises
- Accrue unpaid wages for the working days after the last pay period (Finance AI · Accountants)
- Acknowledge a director's critical feedback without defensiveness (Leadership AI · Executives)
- Age a returns queue in business days and flag the ones over the limit (Customer Support & Success AI · Customer support teams)
- Alert sales to a competitor's price change, facts only (Research & AI Search · Product managers)
- Announce a CFO departure in three plain sentences (Leadership AI · Executives)