Analyze · Forecasting & Gap-to-Quota

Analyze Forecast Accuracy by Rep

Score each rep on how accurate their commit number actually is — and surface who consistently sandbags or over-promises.

managerfounderAdvanced⏱ 2 hours per quarter close
When to use
Run quarterly after results are in. Use to coach reps whose forecasts are systematically off in one direction and to weight your roll-up forecast more intelligently. Especially helpful when you have 3+ reps and inconsistent call quality.
The prompt
You are a sales leader who runs forecast calls at digital marketing agencies. You hold reps accountable for the accuracy of their call, not just the outcome.
Agency: [AGENCY_NAME] — [SERVICES]
Last [N_QUARTERS] quarters of rep-level forecast vs actual:
[REP_FORECAST_DATA]
Format per row: Rep | Quarter | Commit $ | Best Case $ | Actual Closed $ | Quota $
Benchmarks: a healthy commit is within ±10% of actual; sandbagging = actual > commit + 20%; over-promising = actual 
Score each rep on forecast accuracy across [N_QUARTERS] quarters and classify them as: Accurate, Sandbagger, Over-promiser, or Inconsistent.

- Show ALL math: per-quarter variance %, average variance, classification.
- Use signed variance: (Actual − Commit) / Commit. Positive = sandbag, negative = over-promise.
- A rep needs ≥3 data points to be classified; flag 'insufficient data' otherwise.
- Be specific about pattern: 'over-promises in late-stage deals' vs 'inflates Discovery'.
- Recommend a forecast adjustment multiplier per rep for next quarter's roll-up.

1. Per-rep accuracy table: Rep | Quarters | Avg Variance % | Std Dev | Classification | Suggested Multiplier
2. Roll-up implication: applying multipliers to current commits, the team forecast adjusts by $X
3. Coaching note per rep (1 line each)
Variables
  • [AGENCY_NAME] — Your agency name
  • [SERVICES] — Services sold
  • [N_QUARTERS] — Number of quarters of history (3-8 ideal)
  • [REP_FORECAST_DATA] — Per-quarter rep forecast vs actual rows
Example input
Agency: BeaconWorks — SEO + paid
N_QUARTERS: 4
Data:
Sara | Q2-25 | Commit $90k | Best $130k | Actual $95k | Quota $100k
Sara | Q3-25 | Commit $85k | Best $125k | Actual $88k | Quota $100k
Sara | Q4-25 | Commit $95k | Best $140k | Actual $102k | Quota $100k
Sara | Q1-26 | Commit $90k | Best $130k | Actual $93k | Quota $100k
Marco | Q2-25 | Commit $120k | Best $160k | Actual $78k | Quota $100k
Marco | Q3-25 | Commit $110k | Best $150k | Actual $65k | Quota $100k
Marco | Q4-25 | Commit $130k | Best $170k | Actual $84k | Quota $100k
Marco | Q1-26 | Commit $115k | Best $155k | Actual $70k | Quota $100k
Example output
Per-rep accuracy:
- Sara | 4Q | Avg variance +5.6% | Low std dev | Accurate (slight sandbag) | Multiplier: 1.05
- Marco | 4Q | Avg variance −38% | Low std dev (consistently over) | Over-promiser | Multiplier: 0.62

Roll-up implication: If current quarter commits are Sara $95k, Marco $125k, raw roll-up = $220k. Multiplier-adjusted = $99.75k + $77.5k = $177.25k. Roll-up drops by ~$43k — that's the realistic team forecast.

Coaching:
- Sara: hold her to Best Case more aggressively — she's leaving deals out.
- Marco: every Commit needs a written 'why this closes by EOQ' — late-stage progression looks weak.
Pro tips
  • Keep a running quarterly log in a sheet so this prompt has clean data — accuracy compounds with history.
  • Don't fire over-promisers automatically — coach the call first, then escalate if patterns don't change in 2 quarters.
  • Sandbaggers are dangerous in their own way — you under-hire and miss upside.
Works with
ClaudeChatGPTGemini
Done with prompts? Time to install the system
Book a STAOS call
Related prompts