Marketing AnalyticsAdvanced68 minSaves 2+ hours

B2B Funnel Conversion Audit: MQL to Opportunity Leak Analysis

Q: How do I handle missing data in my CSV?

For critical columns like `LeadsIn` or `ConversionRate`, missing data will skew results. Fill in gaps with '0' or 'N/A' if appropriate and meaningful, or exclude rows if the data is too sparse to maintain analytical integrity.

For RevOps and marketing leaders, this audit identifies the two largest conversion leaks from MQL to SQL to opportunity, pinpointing fixes with optimal ROI based on source, segment, and content path data.

This prompt guides marketing and RevOps leaders through a detailed B2B funnel audit. It analyzes MQL-to-SQL-to-opportunity conversion by source, segment, and content path, pinpointing the two biggest leaks. The output includes actionable, high-ROI fixes to optimize pipeline efficiency and drive revenue.

ChatGPT Claude Gemini

READY-TO-USE PROMPT

Copy Prompt

prompt.txt

As a Senior RevOps Analyst, your objective is to conduct a thorough audit of the MQL-to-SQL-to-Opportunity funnel. Your analysis should pinpoint the primary conversion leaks and propose data-backed solutions with the highest potential ROI.

### Context
Our organization is experiencing inconsistent conversion rates across our B2B marketing and sales funnel, specifically from Marketing Qualified Lead (MQL) to Sales Qualified Lead (SQL), and then from SQL to Closed-Won Opportunity. We suspect there are significant bottlenecks that are impacting our pipeline efficiency and revenue generation.

I will provide you with comprehensive conversion data, segmented by lead source, customer segment, and content engagement paths. This data set will include volumes and conversion percentages at each stage of the funnel.

### Task
Your task is to perform a detailed analysis of the provided funnel data to:

1.  **Identify the top two most impactful conversion leaks** within the MQL → SQL → Opportunity pipeline. These leaks should represent the largest drops in conversion rates or the highest volume of lost leads.
2.  For each identified leak, **diagnose the probable root causes** based on the provided segmentation data (source, segment, content path).
3.  **Propose specific, actionable solutions** designed to address each of the top two leaks. Each solution should include a brief rationale and an estimate of its potential ROI in terms of improved conversion rate or recovered pipeline value.

### Constraints
*   Focus strictly on identifying and addressing only the *two most significant* leaks.
*   Ensure proposed solutions are practical and directly tied to the data segments provided.
*   Quantify potential ROI for each solution where feasible, even if estimated.
*   The output must be structured precisely as outlined below.

### Input Data
I will provide the following data:

*   **{{conversion_data_csv}}**: A CSV string containing funnel conversion data. This will include columns such as `Stage`, `Source`, `Segment`, `ContentPath`, `LeadsIn`, `LeadsOut`, `ConversionRate`, `LostReason` (if available).
*   **{{target_audience_segments}}**: A list or description of our key target audience segments.
*   **{{content_path_data}}**: A summary of common content consumption paths that lead to MQLs.

### Output Format
Provide your analysis in three distinct sections:

1.  **Funnel Dashboard Specification**
    *   Outline the key metrics and dimensions that should be visualized in a dashboard to continuously monitor MQL → SQL → Opportunity conversion. Include suggestions for filtering by source, segment, and content path.

2.  **Conversion Audit Findings**
    *   **Leak 1: [Description of the biggest leak]**
        *   *Location in Funnel:* [MQL to SQL / SQL to Opportunity]
        *   *Data Evidence:* [Specific data points from {{conversion_data_csv}} supporting this leak, e.g., "X% drop from Source Y, Segment Z"]
        *   *Probable Root Causes:* [2-3 concise bullet points]
    *   **Leak 2: [Description of the second biggest leak]**
        *   *Location in Funnel:* [MQL to SQL / SQL to Opportunity]
        *   *Data Evidence:* [Specific data points from {{conversion_data_csv}} supporting this leak]
        *   *Probable Root Causes:* [2-3 concise bullet points]

3.  **Prioritized Fix List (High ROI)**
    *   **Fix for Leak 1:** [Specific action]
        *   *Rationale:* [Brief explanation]
        *   *Estimated ROI:* [e.g., "+5% MQL-to-SQL conversion for X segment, recovering $Y in pipeline"]
    *   **Fix for Leak 2:** [Specific action]
        *   *Rationale:* [Brief explanation]
        *   *Estimated ROI:* [e.g., "+3% SQL-to-Opportunity conversion for leads engaging with Z content, adding $W to revenue"]

Estimated results

DifficultyAdvanced

Setup time68 min

Time saved2+ hours

Best modelsChatGPT, Claude, Gemini

Best audienceMarketing, Sales

Editor's note

Why this prompt matters

Many B2B organizations struggle with inconsistent conversion rates across their marketing and sales funnel. Pinpointing exactly where leads drop off, understanding the underlying causes, and prioritizing fixes often becomes a complex, data-intensive challenge. This workflow is designed for RevOps and marketing leaders who need to quickly diagnose pipeline inefficiencies, particularly in the MQL-to-SQL-to-Opportunity stages.

It addresses the common issue of identifying significant conversion leaks without getting lost in an overwhelming amount of data. By focusing on critical segmentation – lead source, customer segment, and content engagement paths – it provides a structured approach to uncover the most impactful bottlenecks. This structured analysis is crucial when revenue targets are at stake and every marketing and sales dollar needs to demonstrate clear ROI.

This workflow provides a framework to move beyond anecdotal observations to data-driven insights. It's particularly useful when preparing for quarterly business reviews, strategizing for the next fiscal period, or when a sudden dip in pipeline velocity demands immediate investigation and corrective action. The output delivers not just problems, but actionable solutions tied to quantifiable impact.

Anatomy

Prompt engineering breakdown

Role

This prompt directs the model to act as a Senior RevOps Analyst, auditing B2B funnel conversion data from MQL to opportunity to identify top leaks and propose ROI-driven solutions.

Context

Our organization is experiencing inconsistent conversion rates across our B2B marketing and sales funnel, specifically from Marketing Qualified Lead (MQL) to Sales Qualified Lead (SQL), and then from SQL to Closed-Won Opportunity. We suspect there are significant bottlenecks that are impacting our pipeline efficiency and revenue generation. I will provide comprehensive conversion data, segmented by lead source, customer segment, and content engagement paths.

Goal

Conduct a thorough audit of the MQL-to-SQL-to-Opportunity funnel. Pinpoint the primary conversion leaks and propose data-backed solutions with the highest potential ROI. This includes identifying the top two leaks, diagnosing probable root causes, and proposing specific, actionable solutions with rationales and estimated ROI.

Constraints

Focus strictly on identifying and addressing only the two most significant leaks. Ensure proposed solutions are practical and directly tied to the data segments provided. Quantify potential ROI for each solution where feasible, even if estimated. The output must be structured precisely as outlined.

Output format

Three distinct sections: 1. Funnel Dashboard Specification (metrics and dimensions), 2. Conversion Audit Findings (for two leaks, including location, data evidence, and probable root causes), and 3. Prioritized Fix List (for two leaks, including specific action, rationale, and estimated ROI).

Why this structure works

Role priming establishes the expected analytical depth and perspective, ensuring the model adopts the mindset of a RevOps expert. Explicit constraints on the number of leaks and solution practicality guide the model to deliver focused, actionable insights. The structured output format guarantees consistency and makes the complex analysis immediately digestible for revenue and marketing leaders.

Pick your version

Prompt variations

BeginnerWorks with any model

For users new to funnel analysis or with simpler data sets, needing a basic overview of conversion issues.

prompt.txt

You are a Marketing Analyst. Help me understand why leads aren't converting from MQL to Opportunity. I will give you {{simple_conversion_data}} which includes lead counts at each stage. Your goal is to find the single biggest drop in conversion rate in our funnel. Explain what you think might be causing this issue, based on the data I provide. Then, suggest one clear action we can take to improve it. Keep your language straightforward. Your output should list: 1. The main conversion problem. 2. Why it might be happening. 3. One suggested fix.

ProfessionalBest with chatgpt

When a detailed, structured analysis is required with comprehensive input data for B2B marketing and sales leaders.

prompt.txt

As a Senior RevOps Analyst, conduct a thorough audit of the MQL-to-SQL-to-Opportunity funnel. Pinpoint the two primary conversion leaks and propose data-backed solutions with the highest potential ROI. Our organization faces inconsistent conversion rates. I will provide {{conversion_data_csv}}, {{target_audience_segments}}, and {{content_path_data}}. Your task is to identify the top two most impactful leaks, diagnose probable root causes using the segmented data (source, segment, content path), and propose specific, actionable solutions with rationale and estimated ROI. Focus strictly on two leaks, ensure solutions are practical and data-tied, and quantify ROI. The output must be structured: Funnel Dashboard Specification, Conversion Audit Findings (for two leaks with location, data evidence, root causes), and Prioritized Fix List (for two leaks with action, rationale, estimated ROI).

Short VersionBest with claude

For quick, high-level insights or when iterating rapidly on funnel issues, requiring a concise summary.

prompt.txt

Analyze the provided {{funnel_metrics_summary}} to identify the most significant conversion bottleneck between MQL and Opportunity. Pinpoint the primary reason for this leak by referencing relevant data points. Subsequently, propose a single, high-impact corrective action designed to address this specific issue, including a clear estimation of its potential improvement to conversion rates or overall pipeline value. The output should be a concise, single-paragraph summary covering: 1. The key conversion leak identified. 2. Its most probable cause based on the data. 3. The recommended action with its estimated impact.

EnterpriseBest with gemini

In large organizations where cross-functional alignment, risk assessment, and stakeholder communication are critical for strategic planning.

prompt.txt

As a Lead RevOps Strategist, conduct a comprehensive, multi-dimensional audit of our MQL-to-SQL-to-Opportunity funnel, focusing on pipeline integrity and revenue predictability. Your analysis must identify the two most critical conversion leaks, diagnose their systemic root causes, and develop strategic, cross-functional solutions with detailed ROI projections and risk assessments. We face inconsistent conversion impacting enterprise-level revenue targets. I will supply {{detailed_conversion_data_json}}, {{strategic_segment_definitions}}, and {{compliance_guidelines}}. Your task is to identify top two leaks, analyze root causes considering operational, compliance, and stakeholder impacts, and propose solutions with resource requirements, stakeholder implications, and estimated ROI. Solutions must adhere to {{organizational_risk_framework}}. Output must be a formal report: Executive Summary, Detailed Audit Findings (two leaks with systemic causes, cross-functional impact), Strategic Fixes (action plan, stakeholder matrix, ROI, risk mitigation), and a Compliance Checklist.

What you'll get

Expected output

Funnel Dashboard Specification

* Key Metrics: MQL volume, SQL volume, Opportunity volume, MQL-to-SQL Conversion Rate, SQL-to-Opportunity Conversion Rate, Average Deal Size, Sales Cycle Length. * Dimensions: Lead Source (e.g., Organic Search, Paid Social, Referral), Customer Segment (e.g., Enterprise, SMB), Content Path (e.g., Blog Post Series, Webinar Series, Case Studies). * Visualizations: Trend lines for conversion rates over time, bar charts comparing conversion rates by dimension, funnel stage drop-off visualization, heatmaps showing conversion by source/segment. * Filters: All dimensions should be filterable. Include filters for time range (daily, weekly, monthly, quarterly) and individual content assets.

Conversion Audit Findings

* Leak 1: Low MQL-to-SQL Conversion for SMB Leads from Organic Search (Blog Post B Engagement) * *Location in Funnel:* MQL to SQL * *Data Evidence:* Organic Search leads in the SMB segment, specifically those engaging with 'Blog Post B', exhibit a 20% MQL-to-SQL conversion rate (300 MQLs, 60 SQLs). This is significantly lower than Enterprise segments from Organic Search (e.g., 'Blog Post A' at 30%) and other SMB sources (e.g., Referral, SMB, 'Whitepaper D' at 30%). The primary 'LostReason' for these leads is 'Lack of Fit' during qualification. * *Probable Root Causes:* * Misaligned content: 'Blog Post B' may be attracting a high volume of SMB leads who do not meet our ideal customer profile or sales qualification criteria. * MQL scoring criteria: The current MQL definition for SMBs originating from organic search may be too broad, qualifying leads who are not genuinely sales-ready or a good fit. * Sales enablement: The sales team may lack specific playbooks or messaging tailored to effectively qualify and convert SMB leads sourced from organic content. * Leak 2: Low MQL-to-SQL Conversion for SMB Leads from Paid Social (Webinar Series Y Engagement) * *Location in Funnel:* MQL to SQL * *Data Evidence:* Paid Social leads in the SMB segment, particularly those engaging with 'Webinar Series Y', show a 20% MQL-to-SQL conversion rate (250 MQLs, 50 SQLs). This contrasts sharply with Enterprise segments from Paid Social (e.g., 'Webinar Series X' at 45%). A significant portion of these leads are lost due to 'Budget Constraints'. * *Probable Root Causes:* * Targeting inaccuracy: Paid social campaigns for 'Webinar Series Y' might be reaching SMBs with insufficient budget or premature interest, indicating poor audience segmentation. * Offer mismatch: The webinar series content may be attracting leads interested in free information but not yet ready for a sales conversation or product purchase, leading to early disqualification. * Lead nurturing gap: Absence of a dedicated nurturing track for SMB leads from paid social to address common budget concerns or build product value pre-sales.

Prioritized Fix List (High ROI)

* Fix for Leak 1: Refine MQL scoring and content targeting for SMB Organic Search leads. * *Rationale:* Implement stricter MQL scoring criteria for SMB leads from organic search engaging with 'Blog Post B' to ensure higher qualification standards. Collaborate with the content team to either revise 'Blog Post B' or develop follow-up content that better pre-qualifies for sales intent. Provide sales with clearer guidelines for disqualification and better-fit lead profiles. * *Estimated ROI:* +10% MQL-to-SQL conversion for SMB leads from Organic Search (from 20% to 30%), recovering approximately 30 additional SQLs per month. Assuming an average SQL value of $5,000, this adds an estimated $150,000 to the pipeline monthly. * Fix for Leak 2: Optimize Paid Social campaign targeting and introduce a pre-sales nurturing track for SMB leads. * *Rationale:* Adjust paid social audience parameters for 'Webinar Series Y' to focus on SMBs matching ideal customer profiles more closely, specifically those with demonstrated budget capacity or higher intent signals. Develop a targeted email nurturing sequence that addresses common SMB budget objections and articulates product value before a direct sales handoff. * *Estimated ROI:* +8% MQL-to-SQL conversion for SMB leads from Paid Social (from 20% to 28%), recovering approximately 20 additional SQLs per month. Assuming the same SQL value, this adds an estimated $100,000 to the pipeline monthly.

Under the hood

Why this prompt works

This prompt workflow yields precise, actionable analysis due to several key prompt engineering techniques. Role priming as a 'Senior RevOps Analyst' immediately sets the appropriate tone and expertise level for the AI, guiding it to think critically about funnel dynamics, data interpretation, and revenue impact. This ensures the output is not merely descriptive but analytical and strategic, aligning with the expectations of a seasoned professional.

Explicit constraints are critical for focus. By specifically limiting the analysis to the 'top two most impactful conversion leaks' and requiring solutions to be 'practical and directly tied to the data segments,' the prompt prevents diffuse, superficial recommendations. This forces the AI to prioritize based on data significance, mimicking how a human analyst would approach a problem with limited resources.

The structured output format is another essential component. By dictating sections for 'Funnel Dashboard Specification,' 'Conversion Audit Findings,' and 'Prioritized Fix List,' along with specific sub-headings and required data points (e.g., 'Data Evidence,' 'Probable Root Causes,' 'Estimated ROI'), the prompt ensures comprehensive coverage and consistency. This eliminates ambiguity in the AI's response, making the output immediately usable for RevOps and marketing leaders without further interpretation or reformatting. This structure acts as a form of scaffolding, guiding the AI through a complex analytical process step-by-step.

Model fit

Best AI models for this prompt

ChatGPT

ChatGPT handles structured data inputs well, making it suitable for identifying patterns in conversion rates and suggesting actionable improvements. Its ability to generate clear, concise summaries and recommendations is beneficial for producing the prioritized fix list. It may require explicit guidance to ensure quantitative ROI estimates are practical. See the full ChatGPT hub for deeper guidance.

Claude

Claude excels at processing and interpreting complex, multi-faceted data sets, which is crucial for understanding nuanced conversion leaks across various segments and content paths. Its strong contextual understanding allows for more insightful root cause analysis and detailed rationale for proposed solutions. Claude maintains coherence over longer analyses, which benefits a comprehensive audit. See the full Claude hub for deeper guidance.

Gemini

Gemini is effective at breaking down complex analytical problems and generating structured outputs, which aligns well with the required dashboard specification and audit findings format. Its capabilities in synthesizing information from various data points help in diagnosing probable root causes and linking them to specific solutions. Gemini can efficiently organize the identified leaks and proposed fixes. See the full Gemini hub for deeper guidance.

When to use

When pipeline conversion rates are stagnant or declining and root causes are unclear.
When needing to identify specific bottlenecks between MQL, SQL, and Opportunity stages.
When preparing for a quarterly business review and need data-backed recommendations for improvement.
When prioritizing marketing or sales initiatives based on potential ROI in the conversion funnel.
When you have granular conversion data segmented by source, customer, and content paths.
When a structured, data-driven analysis of funnel leaks is required for leadership.

When not to use

If you lack granular conversion data across lead source, customer segment, or content paths.
If your organization's funnel stages are not clearly defined as MQL, SQL, and Opportunity.
For a quick, high-level overview without deep diagnostic requirements or specific fix proposals.
When the primary objective is to increase top-of-funnel lead volume, not conversion efficiency.
If data privacy policies prevent sharing detailed customer journey or lost reason data.

Get more from it

Pro tips

1
Pre-process your CSV data: Ensure `LeadsIn`, `LeadsOut`, `ConversionRate` are clean numbers. This prevents misinterpretations of funnel performance metrics.
2
Clearly define your MQL, SQL, and Opportunity stages before inputting data. This avoids stage ambiguity leading to flawed leak identification.
3
Include 'LostReason' data if available. This crucial context helps diagnose why leads dropped, improving root cause analysis accuracy.
4
Start with a broad dataset, then iteratively narrow down segments if the initial output is too generalized. This refines leak pinpointing.
5
Verify the LLM's ROI estimations against internal benchmarks. This prevents over-optimistic or unrealistic financial projections.
6
Input a manageable CSV size. Extremely large datasets can lead to truncated or incomplete analysis, missing key leaks.
7
Provide concise descriptions for `target_audience_segments` and `content_path_data`. This ensures the analysis aligns with your business context.

Don't ship this

Common mistakes

✗ Inputting dirty or inconsistent CSV data, like mixed data types in numeric columns.
Fix — Clean and standardize all numeric and categorical fields in your CSV before feeding it to the prompt.
✗ Providing vague or incomplete descriptions for target audience segments.
Fix — Detail each segment with clear demographic, firmographic, and behavioral attributes for accurate analysis.
✗ Not defining the MQL, SQL, and Opportunity stages precisely within your organization.
Fix — Ensure internal alignment on stage definitions; this consistency is critical for valid funnel comparisons.
✗ Expecting the LLM to access external or historical data beyond your input.
Fix — Provide all necessary context and data within the prompt; the LLM only uses what it's given.
✗ Inputting an excessively long CSV string, causing truncation or processing errors.
Fix — Break down very large datasets or summarize key conversion points if the full raw data exceeds token limits.
✗ Ignoring the 'LostReason' column, even if partially available in the data.
Fix — Always include `LostReason` data; it offers direct insights into why leads are dropping off.

Frequently asked questions

Q.What if my conversion data is not in CSV format?

You'll need to convert your data into a CSV string. Most spreadsheet software can export to CSV, which you can then copy and paste. Ensure headers match the prompt's expected columns for accurate parsing.

Q.How specific should `target_audience_segments` be?

Provide enough detail for the model to understand distinct groups. For example, 'SMB (1-50 employees), Enterprise (1000+ employees), Mid-Market (51-999 employees).' This level of specificity aids segment-specific analysis.

Q.Can this prompt analyze more than two leaks?

The prompt is explicitly constrained to identify the *two most significant* leaks. This focus ensures actionable, high-impact recommendations. Modifying this constraint would require altering the prompt instructions directly.

Q.How accurate are the estimated ROI figures?

The ROI figures are estimates based on the provided data and the model's analytical capabilities. They serve as a guide for prioritization, not a precise financial forecast. Always validate these with internal financial metrics and benchmarks.

Q.What if my funnel stages differ from MQL, SQL, Opportunity?

The prompt is designed for these specific stages. You could adapt your input data to map to these stages or consider modifying the prompt's stage definitions if your funnel nomenclature is fundamentally different to align with your internal process.

Q.How do I handle missing data in my CSV?

For critical columns like LeadsIn or ConversionRate, missing data will skew results. Fill in gaps with '0' or 'N/A' if appropriate and meaningful, or exclude rows if the data is too sparse to maintain analytical integrity.

Version 1.0Last reviewed July 12, 2026

Reviewed by PromptInFlow Editorial Team