A prospect says a particular integration is essential. They become a customer, and their first month of support tickets is about getting that integration to work.
A buyer chooses your product because it promises to simplify a workflow. Three months later, their team is still asking for help with it.
Your product team hears the same feature request in sales calls and support conversations. Are these customers describing the same underlying problem?
Each conversation contains part of the answer. Bringing them together helps you understand what to do next.
Today, we’re introducing Rippit’s Gong integration, bringing Gong conversations into a broader workflow for customer analysis and recurring agents.
Analyze calls alongside support conversations and other connected context. Save the findings as structured data. Put an agent to work monitoring the questions that matter to your business.
Call transcripts, participants, and account and deal context
Why add Rippit if you already use Gong?
Gong already does much more than record calls. It analyzes conversations, surfaces deal risks, supports coaching and forecasting, and offers AI-powered revenue workflows. For a side-by-side look, see Rippit vs. Gong.
The reason to add Rippit is to put those conversations to work alongside the customer evidence and internal context available in the rest of your workspace.
| What Rippit adds | Why it matters |
|---|---|
| Broader conversation coverage | Investigate Gong calls alongside support tickets, chatbot conversations, internal meeting context, and other connected sources. |
| Structured, reusable analysis | Apply your own classifications to ingested conversations, save the results, and calculate breakdowns across the selected datasets. |
| Recurring analysis at scale | Turn questions like churn risk, product feedback, customer trends, and onboarding friction into standing jobs that continue as new conversations arrive. |
| Managed agents without an internal build | Package the data scope, analysis, formatting, delivery, and schedule into an Agent App instead of building and maintaining the workflow yourself. |
For some teams, the challenge is not getting intelligence from an individual sales call. It is running new analyses continuously across thousands of conversations.
We hear from teams that want to run recurring jobs—churn analysis, customer trend detection, product feedback analysis, or weekly account recommendations—but become more sensitive to cost, usage, and engineering overhead as the volume and frequency of that work grows.
Rippit gives those teams another way to put Gong data to work: keep Gong as an important source of customer conversations, while bringing those conversations into a separate analytical workflow built for recurring analysis across sources.
A sales leader might use Gong to understand what is happening in a deal. Rippit gives product, customer success, and operations teams a way to take those conversations further: analyze them across thousands of interactions, combine them with other sources, and turn recurring questions into agents without building and maintaining the underlying workflow themselves.
Start with a question that spans the customer journey
Imagine your team wants to understand onboarding friction.
Gong calls capture what customers wanted to accomplish before they signed. Support conversations show where they became stuck. Internal product meetings may explain which improvements your team prioritized and why.
Ask Rippit:
“Across the available Gong calls and support conversations, identify the workflows customers expected to accomplish and the problems they encountered during onboarding. Where do expectations and experience diverge?”
The goal is to move from scattered examples to an analysis your team can inspect, measure, and revisit.
1. Bring sales context into the investigation
A support ticket might say, “I can’t get this report to work.” A sales conversation might explain why that report was central to the purchase.
That context can change the significance of the issue. It could be a minor inconvenience, a misunderstanding, or a blocker to the outcome the customer bought your product to achieve.
Use Rippit to investigate questions such as:
- Which capabilities requested in sales calls also generate recurring support issues?
- What onboarding expectations appear in calls with customers who later need substantial help?
- Which product gaps show up both as sales objections and as frustrations among existing customers?
- Which accounts show meaningful changes in churn risk, adoption friction, or customer sentiment week over week?
For account-level comparisons, the analysis needs reliable identifiers or mappings across sources. Where those links are unavailable, compare themes across the datasets and make the limits of the comparison clear.
2. Turn conversations into reusable analysis
Rippit can add AI columns to selected, ingested conversations. You define the judgments you want to extract and save.
For this investigation, useful columns might include:
| Dimension | What to capture |
|---|---|
| Desired outcome | What the customer is trying to accomplish |
| Product or workflow | Which capability the conversation concerns |
| Expectation or commitment | What was requested, described, or explicitly promised |
| Friction or objection | What is preventing progress |
| Resolution status | Whether the conversation establishes that the issue was resolved |
| Supporting evidence | The wording behind the classification |
Use compatible definitions across calls and support conversations so the results can be compared. Keep explicit commitments separate from customer requests or tentative discussions.
Then calculate breakdowns: which workflows appear most often, which issues are increasing, or which segments encounter particular problems. Saved classifications can support follow-up questions and reports without rebuilding the same analysis each time.
Customer counts and conversation counts answer different questions. A customer with ten tickets should not silently become ten customers in a report.
3. Connect customer evidence with internal priorities
If you also connect Granola, Rippit can consult accessible internal meeting notes during the investigation.
Ask:
“Compare the leading product gaps in our Gong calls and support conversations with the priorities discussed in recent internal product meetings. Where are we aligned, and what needs another discussion?”
Now the analysis can consider three perspectives: what prospects want, what customers experience, and what the team plans to do.
A missing match in the available meeting notes is a prompt for follow-up, not proof that the team has ignored an issue.
4. Turn the analysis into a recurring agent
Once the investigation works, make it a standing job.
For example:
“Every Friday, analyze this week’s Gong calls and support conversations for product gaps. Separate prospective-customer requests from problems existing customers are experiencing. Compare the leading themes with accessible internal planning notes, and send a brief to the product Slack channel with counts, examples, and questions for follow-up.”
Or make the job account-specific:
“Every week, scan recent Gong calls and support conversations for each account. Identify new churn risks, unresolved commitments, adoption blockers, and meaningful changes. Send each CSM a prioritized list of accounts that need attention and why.”
Rippit Agent Apps combine the data scope, analysis, formatting, delivery, and schedule. You can inspect and test the workflow before activating it, then review new findings as the selected data becomes available.
Agents that scan, analyze, and act across sources
| Agent | Scan | Analyze | Act |
|---|---|---|---|
| CSM weekly actions | Recent Gong calls and support conversations by account | Detect new churn risks, unresolved commitments, adoption blockers, and meaningful changes | Send each CSM a prioritized list of accounts that need attention and why |
| Expectation follow-through | Gong calls and subsequent support conversations for matched accounts | Identify unmet expectations and unresolved blockers | Send an account brief with evidence and follow-up questions |
| Product demand | Sales objections, feature requests, and support issues | Distinguish prospective demand from friction affecting existing customers | Deliver a weekly product report with separate breakdowns |
| Onboarding friction | Buying goals expressed in calls and onboarding support conversations | Find recurring obstacles to the outcomes customers expected | Alert the onboarding team to patterns worth investigating |
| Priority alignment | Gong calls, support data, and accessible internal planning notes | Compare customer needs with discussed priorities | Send a planning brief or create a follow-up issue through an enabled connection |
Actions depend on the connections and permissions enabled in your workspace. Slack or email delivery can bring the findings to the team; other authorized tools can turn a finding into work in a system such as Linear.
The agent should bring evidence people can inspect and a next step they can use.
Get started
Connect your Gong data to Rippit and choose the calls and other datasets you want to investigate. Start with one question that requires more than the sales conversation alone:
“What did these customers want to achieve when they bought, and what is getting in their way now?”
Review the evidence, refine the classifications, and turn the useful analysis into an Agent App.
Keep learning from your sales conversations. Connect them to what happens next.
Sources: Rippit Gong integration, Rippit Agent Apps, Rippit MCP overview, Rippit’s Granola connection, Rippit external connections, Gong conversation intelligence.
.webp)
