Build a per-rep pipeline JSON with weighted totals

About this exercise

Turn the opportunity list into one JSON array in a single code block, one object per rep, keys exactly rep, open_pipeline, weighted_pipeline, coverage, uncovered_quota. Open pipeline counts only open stages (not Closed-Won or Closed-Lost). weighted_pipeline is each open amount times its stage probability, summed. coverage is open_pipeline divided by remaining_quota, rounded to 1 decimal. All values after rep are plain numbers. uncovered_quota is remaining_quota minus weighted_pipeline, but 0 if that is negative. Outside the block write at most one line of 12 words or fewer.

Common mistakes when you ask AI for this

• Counting closed deals. The AI includes Ben's Closed-Won and Cleo's Closed-Lost in open pipeline. Try: Add: "Open pipeline excludes Closed-Won and Closed-Lost."
• Unweighted totals. The AI forgets the stage probabilities. Try: Add: "weighted_pipeline = each open amount x its stage probability, summed."
• Wrong coverage base. The AI divides by total quota or weighted pipeline. Try: Add: "coverage = open_pipeline / remaining_quota, 1 decimal."
• Extra keys or prose. The AI adds fields and an explanation. Try: Add: "Exactly these five keys; one code block; at most one line outside it."

What a strong prompt includes

• Names the keys
• Excludes closed
• Weights by stage
• Defines coverage|uncovered
• One code block

Practice this now ↑

Related exercises

• Accept the buyer's counteroffer on three stated conditions (Sales AI · Sales and customer success)
• Adapt one ad image to 3 sizes with Midjourney (Image & Video AI · Marketing and content)
• Age open requisitions as of today and flag the old ones (Finance AI · FP&A and financial analysts)
• Announce a discount-approval process change in three bullets (Sales AI · Managers and team leads)
• Announce a new regional structure with a reporting table (Leadership AI · Executives)