Analyze Deal Slippage Patterns Across Reps

You are a head of sales who has run pipeline at three different digital marketing agencies. You know slippage is rarely random — it's usually one rep, one stage, or one service line.
Agency: [AGENCY_NAME] — [SERVICES]
Reps in scope: [REP_LIST]
Slippage log (deals where close_date was pushed at least once, last [TIME_WINDOW]):
[SLIPPAGE_DATA]
Analyze the slippage log and surface the patterns. Specifically: (1) which rep slips most often and by how many days on average, (2) which stage produces the most slippage, (3) which service line produces the most slippage, (4) any deal that has slipped 3+ times (chronic).

- Use ONLY records in [SLIPPAGE_DATA]. Do not extrapolate to deals not in the data.
- Express findings as 'X out of Y' not 'most' — be precise.
- If sample size for any rep is 

## Slippage by Rep
| Rep | # Slipped | Avg Days Slipped | Confidence |

## Slippage by Stage
| Stage | # Slips | % of total |

## Slippage by Service Line
| Service | # Slips | % of total |

## Chronic Slippers (3+ pushes)
[deal — rep — # of pushes — total days slipped]

## Pattern Summary
[2-3 sentences — is this a person, stage, or service problem?]

• [AGENCY_NAME] — Your agency name
• [SERVICES] — Service lines you sell
• [REP_LIST] — Names of reps in scope
• [TIME_WINDOW] — e.g. last 90 days, last quarter
• [SLIPPAGE_DATA] — CSV: deal, rep, service_line, original_close_date, current_close_date, # of pushes

Agency: Northwind Digital — SEO, paid social, web design
Reps: Jamie, Priya, Marcus
Window: last 90 days
Slippage data:
deal,rep,service,original_close,current_close,pushes
Acme,Jamie,SEO,2026-03-01,2026-04-15,2
BlueTrail,Priya,Web,2026-03-10,2026-05-30,3
Cedar,Jamie,Paid,2026-04-01,2026-05-15,1
Delta,Marcus,SEO,2026-02-15,2026-05-10,4
Echo,Marcus,SEO,2026-03-20,2026-05-05,3
Foxtrot,Marcus,Web,2026-04-01,2026-05-20,2
Golf,Priya,SEO,2026-04-10,2026-05-25,1

## Slippage by Rep
| Rep | # Slipped | Avg Days | Confidence |
| Marcus | 3 | 56 | low (n=3) |
| Jamie | 2 | 37 | low (n=2) |
| Priya | 2 | 50 | low (n=2) |

## Slippage by Stage
Not in data — recommend adding stage_at_slip column.

## Slippage by Service Line
| SEO | 4 | 57% |
| Web | 2 | 29% |
| Paid | 1 | 14% |

## Chronic Slippers (3+ pushes)
- Delta — Marcus — 4 pushes — 85 days
- BlueTrail — Priya — 3 pushes — 81 days
- Echo — Marcus — 3 pushes — 46 days

## Pattern Summary
SEO deals slip more than other services (57% of slippage, low confidence due to sample). Marcus owns 2 of 3 chronic slippers — worth a 1:1 on qualification. Sample size is too small for any rep-level conclusions to be statistically meaningful.

• Track close_date changes in your CRM as a property history — this prompt is useless without it.
• Run quarterly, not weekly. Slippage patterns need time to emerge.
• If SEO slips more than paid, the issue is usually proof — case studies, not the rep.