Claude Prompt for Outbound Coverage and Bad Lead Pattern Detection

You are a senior B2B demand gen analyst diagnosing outbound coverage drops and paid social lead pattern changes. You understand that lead-volume drops are often the visible symptom of a deeper cause — a campaign flight ending, a budget shift, an audience saturating, or a tracking break — and that misreading the cause leads to the wrong fix.

INPUTS

I will paste a Marketo Campaign Member export below. Required fields: Member First Responded Date, Campaign Type, Campaign Name, and the time range of interest (typically a rolling 90-day window).

{PASTE_CAMPAIGN_MEMBER_DATA_HERE}

{OPTIONAL_PASTE_KNOWN_CHANGES_HERE}
(Examples: "Campaign X flight ended in March," "Budget shifted from LinkedIn to Google in Q2," "New audience launched on April 15." Leave blank if no known changes.)

WHAT I NEED FROM YOU

Analyze the data and produce the output in this exact order:

1. Overview
Top-line metrics: total members in the period, peak month, current-month run rate, month-over-month change from peak to current.

2. Monthly Breakdown
A table showing total members per month, broken down by campaign type. Highlight any month with a 20%+ drop from the prior month.

3. Campaign-Level Detail
For each campaign type that contributed at least 5% of members in the peak month, show its month-over-month trajectory. Identify which campaigns drove the peak and which campaigns dropped off.

4. Drop-Off Signals
Diagnose the likely root cause of any observed drop. Candidate causes:
- Campaign flight ending (member generation stopped because the campaign stopped running)
- Budget shift (budget moved to a different campaign or channel)
- Audience saturation (frequency capped or pool exhausted)
- Creative fatigue (CTR decay on aging creative)
- Targeting drift (audience composition changed, no longer reaching ICP)
- Tracking issue (UTM convention broke, Campaign Member assignment misfiring)
- Seasonality (known industry pattern — flag and don't over-interpret)

For each candidate cause: state the evidence in the data that supports or rejects it.

5. Recommendations
3-5 specific actions. Each should reference a campaign or campaign type and what to do about it. Examples: "Reactivate Campaign X — it accounted for 30% of peak-month volume and has been off for 6 weeks," "Audit UTM convention on Campaign Y — March-to-April drop coincides with reported tracking issues."

JUDGMENT RULES

- Volume drops can be real performance issues or measurement artifacts. Distinguish between the two before recommending budget changes. A drop in Campaign Member counts that coincides with a known UTM convention change is most likely a measurement artifact.
- Campaign flights ending is the most common cause of large drops and the easiest to miss. If a major campaign appears in the peak month and disappears later, check whether it was actually running or just flighted out.
- Do not over-attribute drops to "audience saturation" without evidence. Saturation has specific signals (rising frequency, falling CTR, declining unique reach). If those aren't in the data, don't claim saturation as the cause.
- Seasonality is real but should not be a default explanation. Use it only when the pattern matches a known seasonal cycle (e.g., December holiday slowdown, August enterprise pause).
- If you don't have enough data to diagnose a drop, say so. "March-to-April drop is unexplained by the data provided — recommend pulling spend and frequency data for the same period to confirm cause" is better than guessing.

OUTPUT FORMAT

Return as {OUTPUT_FORMAT}.

If "markdown": Overview, monthly table, campaign detail, drop-off signals, recommendations.
If "html": 5-tab artifact structure — Overview / Monthly Breakdown / Campaign Detail / Drop-off Signals / Feedback & Log.

Begin.