RevOpsMarketing Operations Managerintermediate 45 min saved

Quarterly Lead Quality & Performance Auditor

Transform raw lead data and sales feedback into evidence-based marketing optimization strategies.

Customise & copy

Add the context you have. The prompt updates as you work.

Marketing Acquisition Sources and Campaign Metadata *

Paste campaign metadata and source names.

Audience Segment Definitions and Lead Characteristics *

Describe the audience segment traits and definitions.

Sales Feedback and Pipeline Progression Data *

Provide sales team feedback and pipeline stage movement.

Lead Volume versus Qualified Opportunity Counts *

Provide quantitative breakdown of volume versus qualified conversions.

Live prompt

4 fields

Analyze the provided marketing-generated lead data and sales feedback to evaluate quarterly performance. Your goal is to strictly separate raw lead volume from actual lead quality, identify high-converting patterns, flag low-performing segments, and recommend evidence-based marketing optimizations without assuming unproven channel causality.

Input Data:
1. Acquisition Sources & Campaigns: Google Search (Brand): 5000 leads; Meta Retargeting: 8000 leads; LinkedIn Sponsored Content: 1200 leads.
2. Audience Segment Traits: Enterprise IT Directors (company size > 500); Mid-market Operations Managers (company size 100-500); SMB Solopreneurs.
3. Sales Feedback & Progression: Meta Retargeting leads frequently lack budget authority. LinkedIn leads show longer sales cycles but higher contract values.
4. Volume vs Quality Metrics: Google Search: 5000 leads -> 250 MQLs -> 50 SQLs -> 10 Closed-Won. Meta Retargeting: 8000 leads -> 100 MQLs -> 10 SQLs -> 1 Closed-Won.

Provide your analysis in the following structured format:
1. Volume vs Quality Separation: Contrast raw acquisition volume against qualified opportunity and closed-won counts per segment.
2. High-Value Patterns: Identify specific acquisition sources or audience traits that correlate directly with high-value opportunities based strictly on the supplied data.
3. Weak Lead Samples: Flag campaigns or segments generating high volume but low conversion.
4. Evidence-Backed Adjustments: Recommend specific marketing optimizations supported directly by the input data without claiming unsupported channel causality.

Proof before you use it

A real example

Tested on gemini-3.1-flash-lite on 2026-09-06

{
  "sales_feedback": "Cold email contacts are unresponsive to clinical software pitches. Hospital Procurement Officers require strict security compliance documentation before calls.",
  "volume_metrics": "Cold Email: 3000 contacts -> 50 replies -> 2 opportunities -> 0 wins. Webinar Series: 450 registrations -> 120 qualified leads -> 30 opportunities -> 8 wins.",
  "acquisition_data": "Healthcare Webinar Series: 450 registrations; Industry Podcast Sponsorship: 900 listeners; Cold Email Outreach: 3000 contacts.",
  "segment_definitions": "Hospital Procurement Officers; Private Practice Physicians; Clinic Practice Managers."
}

A small ritual that works

How to use it

01Paste your raw acquisition source data and campaign metadata.
02Input your audience segment definitions and sales team feedback.
03Provide the quantitative volume vs. conversion metrics.
04Run the prompt to generate an evidence-backed performance report.

Why it works

The prompt structures a complex, multi-variable marketing analysis by demanding a strict separation of raw lead volume from actual conversion quality, preventing vanity metrics from dictating strategy. By requiring a breakdown of acquisition sources, segment definitions, sales feedback, and volume metrics, it forces the respondent to cross-reference quantitative funnel drop-offs with qualitative pipeline realities.

Where it fails

INSUFFICIENT_EVIDENCE

Customisation tips

To adapt this prompt for different business models, replace the default acquisition channels and audience segment definitions with your own specific CRM sources and buyer personas, or inject specific CAC and LTV metrics into the variable inputs to force financial accountability into the optimization recommendations.

Watch-outs

Do not let models conflate high lead volume with channel success; ensure they explicitly calculate and address drop-offs at the MQL and SQL stages.
Watch for unsupported channel causality where models recommend budget reallocations to channels that lack complete performance data.
Ensure sales feedback regarding friction points (e.g., missing compliance documents or budget authority) is used to target actual process blocks rather than writing off entire audience segments prematurely.