Build a budget bridge and check it against the stated total

About this exercise

Build a bridge table with the header Item | Change ($M) | Running total ($M), starting with a row for the original budget and then one row per adjustment in the order listed. Then one line: "Check: computed" with the final number, "vs stated" with the stated total, and then either "Match" or "Mismatch". Plain text, under 90 words.

Common mistakes when you ask AI for this

• Trusting the stated total. The AI ends at 5.6. Try: Say: "Compute the running total yourself and compare it to the stated total."
• Math slips. The AI skips a step or mis-adds. Try: Say: "Show the running total after each row."
• Adding the unapproved request. The AI adds 0.5. Try: Say: "Use only the four listed adjustments."
• Wrong table. The AI reorders or merges rows. Try: Say: "Original budget then four adjustments in order."
• Markdown. The AI bolds the check line. Try: Say: "Plain text."
• 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

• Gives the header
• Row order
• Running total each row
• Gives the check line
• Only listed adjustments

Practice this now ↑

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)