Evaluate seasonal drops versus true performance declines

Determine whether a monthly revenue or traffic drop is normal seasonality or an operational problem. Use this during monthly business reviews.

You getPerformance Diagnostic, historical Comparison Table and key Findings

Prompt

Prompt
Act as a growth analytics consultant. Review the historical monthly performance metrics pasted below.
- Compare recent trend changes against year-over-year baselines to isolate expected seasonal dips from real performance drops.
- Highlight metrics that declined faster or slower than historical seasonal variance.
- Note external factors to consider before taking corrective action.
Output format:
1. Performance Diagnostic (Clear verdict: Expected Seasonality, Core Performance Decline, or Inconclusive)
2. Historical Comparison Table (Columns: Metric, Current Month MoM Change, Prior Year Same Period MoM Change, Variance Difference)
3. Key Findings (bulleted breakdown of what shifted)
4. Immediate Verification Steps (3 items to investigate before changing strategy)
My historical metrics are below:

Example output

Example for: SaaS inbound demo volume dropping 24% in December

  1. Performance Diagnostic
    Expected Seasonality with Minor Operational Underperformance. December historical volumes always experience severe deceleration due to end-of-year holiday closures, though paid lead capture fell 4% further than last year's baseline.
  2. Historical Comparison Table
MetricCurrent Dec MoMPrior Dec MoMVariance Difference
Total Website Sessions-18.2%-19.0%+0.8% (Within normal range)
Organic Demo Requests-23.5%-24.1%+0.6% (Consistent pattern)
Paid Search Demo Requests-31.0%-22.4%-8.6% (Abnormal decline)
Demo Attendance Rate-12.0%-11.8%-0.2% (Within normal range)
  1. Key Findings
  • Organic traffic and demo requests are matching the seasonal slowdown from the previous year almost exactly, caused by business shutdowns between December 18 and 31.
  • Paid search demo capture underperformed historical seasonal expectations by 8.6 percentage points, indicating budget burn on lower-intent holiday traffic or tracking degradation.
  • Pipeline attendance rates mirrored prior holiday periods, confirming that booked prospects behave normally once scheduled.
  1. Immediate Verification Steps
  2. Check Google Ads change history to verify if automated bidding overspent in the first two weeks of December.
  3. Review campaign UTM logs to verify that landing page tracking tags did not drop during early December website updates.
  4. Measure January week 1 and 2 rebound rates against last January before making cuts to headcount or ad spend.
Written by AI from this prompt. Your results will vary.

Paste at least 12 to 24 months of comparable metrics (e.g., visits, leads, sales) into ChatGPT, Claude, or Gemini. As a follow-up, ask the model to outline a control group check to test marketing campaign changes.

Make it repeatable

Keep using this prompt without pasting it in every time.

Keep exploring

More in Data Analysis