Library › Data AI › Finance and accounting
Build a customer concentration table after merging duplicate names
- For Finance and accounting
- You practice Catching mistakes and made-up facts
- Time about 5 minutes
- Level Advanced
About this exercise
Your CFO wants the revenue concentration of the top 5 customers. Make one markdown table with columns Customer, Revenue and % of total for the 5 largest customers after merging customers listed under two names, highest first, then a last line 'Top 5 share:' with the sum and percent. Percent of total uses the company total, one decimal, plain text apart from the table, under 100 words.
Common mistakes when you ask AI for this
- Leaving the duplicates split. The AI lists Alder Co and Alder Company as two customers. Try: Add: "Merge Alder Co and Alder Company: 250 + 170 = 420."
- Ranking the bucket. The AI treats 'All other customers' as the biggest customer. Try: Add: "Don't rank the 'All other customers' bucket."
- No total line. The AI never gives the combined share. Try: Add: "Last line: Top 5 share: $1,140K = 57.0%."
- Leaving the format to chance. The AI picks its own length and layout unless told the exact shape. Try: Add: "Plain text, no bold or headings."
- 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 15 words."
What a strong prompt includes
- Names the columns
- Says merge
- Excludes the bucket
- Asks for the share line
- Cuts extras
Related exercises
- 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)
- Alert sales to a competitor's price change, facts only (Research & AI Search · Product managers)
- Annualize recurring revenue without the one-time fee (Data AI · Finance and accounting)
- Answer a credit dispute with the full-hour rule and the math (Customer Support & Success AI · Customer support teams)