Vibe Querying Episode 9: Vibing for Revenue Operations

The ninth episode of our Vibe Querying series takes us into the world of revenue operations, where we explore how FP&A leaders can leverage CData's Salesforce MCP Server to gain actionable insights from complete customer journey data. Joining us for this episode is Elliot York, Director of FP&A at CData Software, who demonstrates how he uses MCP to transform his customer acquisition and renewal analysis workflow.

Watch Now: Vibe Querying with MCP - Episode #9

Introducing MCP, CData MCP Servers, and Vibe Querying

Model Context Protocol (MCP) is a standard protocol designed to connect AI models to external data sources, tools, and workflows securely and efficiently. MCP enables AI models to access real-time data and interact naturally with that information through conversational AI or agent-driven actions.

CData MCP Servers, released in beta, connect CData's connector library of 350+ data sources to your favorite AI clients like Claude or Gemini. This combination gives AI models access to the work data they need to be genuinely useful in business contexts.

This brings us to the concept of "vibe querying" - much like vibe coding, it's a conversational approach to data exploration. You no longer need intimate knowledge of data schemas or prebuilt pipelines. You simply ask questions in natural language, and the MCP server provides live access to data while the AI uses its knowledge to provide answers.

Today's focus: Complete customer journey analysis

For today's episode, we're tackling a challenge that every revenue operations team faces: understanding the complete customer journey to identify what drives successful customer acquisitions and why renewals are lost. Elliot's focus centers on two critical questions: "Why do we land new business?" and "Why do we lose renewals?"

Elliot manages revenue analysis across CData's entire customer lifecycle, requiring deep investigation into deal progression, stakeholder interactions, and customer success patterns. Traditional approaches require manually navigating Salesforce for hours, often getting "lost in a complex deal for a day" while still having an incomplete picture.

As Elliot explains: "There's tons of information that you can find on why what a customer used the software for, why maybe they weren't happy if that was the case, they didn't renew, or why their use case went away. However, it's all over the place and a lot of it's very qualitative."

The setup: From exploration to purposeful prompting

What makes Elliot's approach particularly compelling is how he developed his comprehensive analysis methodology. Starting with basic exploratory questions about customer journeys, Elliot refined his approach over days and weeks of testing.

The breakthrough came from a technique we call "purposeful prompting" - when Elliot found an analysis output he liked, he simply asked Claude: "What prompts can I ask to get this output again?" This generated the comprehensive prompt template he now uses consistently.

As Elliot notes: "I didn't create this from scratch. It was actually very intuitive to get to the point where I created this, and from here, I'll continue to iterate because I ask a lot of additional prompts, but a lot of times, it depends on the situation."

The queries and insights

Query 1: Comprehensive customer journey analysis

The question

Elliot uses a sophisticated primary prompt that requests:

"Can you provide a detailed timeline of the purchase/buyer journey for the following deals closed won in [YEAR]: Customer ID: [CUSTOMER_ID]? Please use this specific format: Start with a deal overview section showing key metrics, create a day-by-day timeline with clear phases, include specific timestamps, key stakeholders, critical moments, stage changes, and direct quotes from conversations. Add sections for key success factors, stakeholder dynamics, velocity drivers, and strategic insights."

What Claude did

Claude automatically executed comprehensive analysis across multiple Salesforce data sources:

• Multi-object Integration: Analyzed opportunities, contacts, activities, emails, support cases, and custom objects

• Chronological Organization: Created timeline following deal stages from discovery through close

• Stakeholder Mapping: Identified all participants and their roles throughout the journey

• Qualitative Analysis: Extracted insights from emails, call notes, and support interactions

• Pattern Recognition: Highlighted critical success factors and velocity drivers

The impact

Claude delivered immediate, comprehensive customer intelligence:

Complete Journey Visibility:

• Lead source attribution with additional context beyond structured fields

• Discovery phase interactions across multiple teams (BDR, Sales, Support, Customer Success)

• Evolution of customer requirements and solution fit over time

• Critical decision moments and stakeholder progression

Hidden Pattern Discovery:

• Partner relationships that influenced deal creation and progression

• Product evolution within deals (e.g., basic JDBC to comprehensive sync solution)

• Existing customer relationships spanning multiple departments and use cases

• Implementation partner involvement that drove initial opportunity creation

Actionable Intelligence:

• Specific success factors that can be replicated across similar deals

• Stakeholder engagement strategies that accelerated timeline progression

• Product positioning insights for future similar opportunities

• Early warning indicators for risk identification

As Elliot reflected on the efficiency gain: "I can get a very well documented summary of all of that disparate information, a lot of it very qualitative in nature, but I can get it all in one place in a very digestible format, and it doesn't take long at all."

Query 2: Deep-dive stakeholder analysis

The question

Building on initial insights, Elliot asked:

"Give me more information about this particular contact and their role in other deals."

What Claude did

Claude leveraged the comprehensive relationship data already gathered to provide:

• Contact History Analysis: Previous interactions across multiple opportunities

• Influence Pattern Recognition: Role in driving deals forward or creating obstacles

• Relationship Mapping: Connections to other stakeholders and decision-makers

• Cross-Deal Intelligence: Patterns of involvement across different product lines

The impact

This analysis revealed critical relationship intelligence:

Implementation Partner Discovery:

• Identified critical implementation partner involvement that wasn't obvious from lead source

• Partner had driven multiple previous opportunities and relationships

• Partner relationship was fundamental to opportunity creation, not just deal progression

Strategic Relationship Value:

• Understanding of which contacts represent broader relationship opportunities

• Identification of referral potential and expansion opportunities

• Cross-functional relationship mapping across departments and use cases

This type of stakeholder intelligence would require extensive manual investigation across multiple Salesforce objects and historical data analysis.

Query 3: Pre-opportunity journey investigation

The question

For complete journey understanding, Elliot requested:

"Tell me about interactions before the opportunity was created."

What Claude did

Claude analyzed historical relationship data to uncover:

• Existing Customer Context: Multi-year relationship spanning different departments

• Multiple Use Cases: Different contacts, departments, and product applications

• Relationship Evolution: How business relationship developed over time

• Opportunity Catalyst Events: Specific triggers that led to formal opportunity creation

The impact

Claude revealed the complete relationship context:

Multi-Dimensional Customer Intelligence:

• Existing customer for several years with three different contacts

• Different departments with separate use cases and product applications

• Complex relationship history that influenced current opportunity

Strategic Business Context:

• Understanding of account potential beyond single opportunity

• Cross-selling and expansion opportunities identification

• Relationship investment ROI across multiple touchpoints

This comprehensive view emerged through 15-30 minutes of conversational analysis rather than hours of manual Salesforce investigation.

The business impact: From manual investigation to automated intelligence

The transformation in revenue operations efficiency was dramatic. Traditional customer journey analysis requires:

• Hours per Deal: Manual navigation through Salesforce objects and related records

• Incomplete Pictures: Missing qualitative insights buried in notes and emails

• Verification Challenges: Uncertainty about data accuracy and completeness

• Limited Scale: Ability to analyze only individual deals due to time constraints

With the MCP-powered approach, Elliot can now:

• Comprehensive Analysis: Complete customer journey summary in 15-30 minutes

• Qualitative Integration: Automated extraction of insights from unstructured data

• Confident Intelligence: Reliable, well-documented analysis for strategic decisions

• Strategic Application: Integration into weekly go-to-market meetings and team processes

As Elliot summarized the value: "We've rolled this into our weekly sales process. Every week, we run a go-to-market meeting and we send out the results of our new business to the go-to-market team and a few other folks, and we've started incorporating these customer journeys."

Technical excellence: SQL transparency and business context

One of Elliot's favorite aspects was the SQL query visibility provided by CData MCP Servers. As an FP&A professional familiar with Salesforce reporting, he found the transparent query approach invaluable:

"When I first started utilizing MCP, I found it very helpful that it uses SQL personally. Because being a finance person, typically, we're not always the most educated around these technologies, but SQL is very easy to follow. So I use Salesforce every day and I build reports. So I can look at the SQL query and see what it's querying to gather the information."

This transparency provides several benefits:

Query Validation: Ability to verify exactly what data is being accessed and how

Learning Opportunity: Understanding of Salesforce data relationships and structure

Confidence Building: Clear visibility into analysis methodology and data sources

Accuracy Verification: Ability to spot-check results against known Salesforce patterns

The SQL-based approach leverages Claude's extensive training on database operations while providing the transparency that finance and operations professionals need for confident decision-making.

What this means for revenue operations teams

This episode showcases how AI-powered customer journey analysis can transform revenue operations:

Speed: Compress hours of manual Salesforce investigation into minutes of conversational analysis

Depth: Uncover hidden patterns, relationships, and qualitative insights that manual analysis often misses

Scale: Move from individual deal analysis toward pattern recognition across customer cohorts

Accuracy: Eliminate manual data compilation errors and incomplete investigation

Strategic Focus: Shift from data gathering to insight application and strategic decision-making

From individual analysis to scale

Elliot identified the next frontier for his MCP usage: scaling customer journey analysis across hundreds or thousands of customers simultaneously. Currently performing individual deal analysis, he envisions comprehensive cohort analysis that could reveal patterns across entire customer segments.

"The next part of the journey for me is gonna be trying to understand how I can do this at scale. How do I gather this information and summarize it in a meaningful way for 5,000 customers all at once?"

This represents the evolution from tactical deal analysis to strategic customer intelligence, where AI can identify patterns across entire customer populations that would be impossible to detect through manual analysis.

Getting started with your own customer journey analysis

If you want to unlock similar insights for your revenue operations:

• Download the free beta: Visit cdata.com/solutions/mcp to access the Salesforce MCP Server

• Remote MCP capabilities: Try Connect AI at cdata.com/cloud for multi-source access

• Simple installation: Follow the automated installer for Claude Desktop integration

• OAuth connection: Authenticate with your existing Salesforce credentials

• Start conversations: Visit our CData prompt library to see proven queries and begin asking strategic questions about your customer journey data

For more examples of vibe querying in action, explore our complete episode series covering marketing, project management, product management, and sales use cases.

Beyond manual CRM analysis: The shift to conversational customer intelligence

This episode demonstrates that we're moving beyond manual Salesforce reporting and into conversational customer intelligence. When AI can access, analyze, and synthesize complete customer journey data through natural language, revenue operations becomes strategic rather than administrative.

Revenue teams can now ask the complex questions they've always wanted to explore: What patterns distinguish successful deals from lost opportunities? Which stakeholder engagement strategies accelerate deal velocity? How can we replicate success factors across our entire pipeline?

For deeper insights into how MCP is transforming revenue operations and customer intelligence, explore our comprehensive blog series on MCP implementation strategies and use cases.

Join us for future episodes of Vibe Querying with MCP, where we continue exploring how natural language AI transforms business intelligence. Until next time, stay curious and keep vibing with your data.