Introducing Rippit + Decagon
Bring Decagon AI conversations into Rippit. Analyze them alongside human support conversations and account data to find what your team should improve next, and what each problem means for the business.
Rippit's Decagon integration syncs your Decagon AI agent conversations, including resolution, CSAT, voice recordings and Watchtower reviews, into Rippit's Growth Data Platform on a schedule. Rippit reads them next to your human support conversations and account data, and agents send findings with the evidence to Slack or email. Use it to understand whether issues were actually resolved, why they happened and which customers or business outcomes they affect. Rippit's agents analyze conversations; they don't talk to your customers.
A customer asks your AI agent how to change their subscription. The answer explains the steps, but the customer still gets stuck.
Your support team handles similar questions throughout the week. Some need a clearer explanation. Others reveal a problem in the product itself.
You update the guidance. Now you want to know whether it helped—and whether the same friction is showing up elsewhere.
Every conversation offers a chance to improve something: an answer, a support process, or the experience that prompted the customer to reach out. When the same friction keeps reaching accounts close to renewal, fixing it can help protect revenue, not just improve satisfaction scores.
Taken together, those conversations show more than how the AI agent performed: where the experience is breaking down, where the product needs work and which customers are feeling it. Problems rarely show up in a single conversation. They show up as patterns nobody connects. Seeing those patterns early gives your team time to address the underlying problem.
Today, we're introducing Rippit's Decagon integration to help you connect those signals.
Sync Decagon conversations into Rippit, investigate them alongside customer conversations from sources like Zendesk and Intercom and the account data around them, and turn your findings into structured analysis. Then build an agent that keeps checking as new conversations arrive.
See the Decagon integration documentation for setup, data handling, and sync details.
Decagon chat and voice conversations
Helpdesk tickets, calls, chats and email
Classifies issues, root causes and outcomes across AI and human conversations
An agent runs on a schedule and sends a brief with links to the conversations behind each finding
Why add Rippit if you already use Decagon?
Decagon's AI conversations and Watchtower reviews provide valuable context about the experience your AI agent delivers. Rippit brings that context into a broader workflow across your customer conversation data. For a side-by-side look, see Rippit vs. Decagon.
| What Rippit adds | Why it matters |
|---|---|
| Broader conversation coverage | Investigate patterns across Decagon conversations and human support interactions from other connected sources. |
| Structured, reusable analysis | Classify conversations by issue, root cause, or outcome, then save the results in columns your team can filter and chart. |
| Business context | Connect conversations to account data from Salesforce (ready connector) or HubSpot (through MCP), and to product usage or billing through Snowflake, the Bulk API or a CSV, so you can see which problems affect accounts near renewal and understand their broader business impact. |
| Managed recurring work | Turn an investigation into an agent with a defined scope, schedule, and delivery destination. |
Rippit's agents work in the background on the data; they don't talk to your customers in real time.
For example, start with subscription questions handled by your AI agent. Compare the problems customers describe with those reaching your human support team. Then track whether changes to your guidance or product reduce the friction.
The question shifts from how one conversation went to what keeps making this difficult for customers, and what to change.
Bring Decagon conversations into your analysis
Rippit's Decagon integration imports full conversation content on a schedule. Each Decagon conversation becomes a conversation in Rippit, including:
That means your investigation can draw on both what was said and the review context already available in Decagon.
You can examine a pattern, inspect the underlying conversations, and decide which additional classifications would help your team understand it.
Start with a question that needs the broader picture
Imagine customers have been struggling to change their subscriptions. Your AI agent handles many of those questions, while others reach your human support team.
You want to know:
"Analyze subscription-change conversations from Decagon and our connected support sources over the past 30 days. What are customers trying to do, where do they get stuck, and which problems appear across both AI and human support?"
One source and one recurring problem are enough to begin. Add your helpdesk or account data when the question needs them.
Here is how the workflow comes together.
1. Read the conversation behind the outcome
A conversation's status is useful context. The exchange itself helps explain what happened.
Did the customer understand the instructions? Did they say the steps failed? Did the answer address the original question? Was the obstacle a confusing policy, a missing capability, or a suspected bug?
Rippit lets you investigate those questions alongside the available resolution fields, customer feedback, and Watchtower reviews.
Then broaden the investigation to your connected human support conversations. Look for recurring issues, differences in the explanations customers receive, and approaches that appear to help.
Comparing themes across sources can reveal a shared problem even when the conversations involve different customers.
2. Turn the findings into reusable analysis
Ask Rippit to classify the selected conversations using the distinctions your team needs. For this investigation, those might include:
- What the customer wanted to change.
- Where they encountered difficulty.
- The likely cause, with supporting evidence.
- Whether the customer explicitly confirmed success.
- Whether the outcome remained unclear.
- The improvement the conversation suggests.
- Which account it came from, with its plan and renewal date, if you've connected account data.
Save those classifications as structured columns. Then compare the most common obstacles, break the results down by source, and examine how patterns change over time.
Keep "confirmed success" separate from "no further response" so you can see what each conversation actually establishes.
The resulting analysis stays available for follow-up questions, worksheets, and charts. As you learn more, you can refine the categories without starting the investigation over.
3. Make improvement tracking a standing job
Once the analysis is useful, turn it into an agent.
For example:
"Every week, review the past week's subscription-change conversations from Decagon and our connected support sources. Summarize the leading points of friction, highlight examples where customers remained stuck, and compare the themes with the previous week. Send a brief with conversation links to our customer experience Slack channel. If no significant changes appear, say so."
Rippit builds the agent as a pipeline you can inspect: the records it reads, the analysis it performs, the format of the brief, its destination and its schedule. To change it, ask Rippit.
Test the findings, refine the instructions, and put it live. Your team can then review fresh evidence as part of its regular improvement process.
Agents that scan, analyze and deliver
The same approach supports several recurring jobs:
| Agent | Scan | Analyze | Deliver |
|---|---|---|---|
| A custom AI experience review agent | Decagon conversations and available Watchtower reviews | Identify recurring confusion, unresolved requests, and patterns worth investigating | Send a brief with supporting examples to Slack or email |
| A custom contact-driver agent | Decagon and connected human support conversations | Find the underlying reasons customers ask for help across sources | Send a ranked summary to support and product in Slack or email |
| A custom improvement-tracking agent | Conversations before and after a documented change | Compare recurring complaints and evidence of customer difficulty | Report what improved and what still needs attention in Slack or email |
| A custom product feedback agent | Customer requests across AI and human conversations | Group missing capabilities, suspected bugs, and usability problems | Send a recurring product feedback digest to Slack or email |
| A custom renewal-risk agent | Decagon and human support conversations, joined to account data | Flag accounts near renewal whose issues keep coming back unresolved | Send customer success a weekly list in Slack or email, with the conversations behind each flag |
Each row is a custom agent you can build. For renewal risk, Rippit also documents Renewal Risk Watch, which joins conversations with usage, billing and CRM data. For a full method for reviewing AI agent conversations, see The Complete Playbook for AI Agent Monitoring.
Get started
Connect Decagon, let your conversations sync, and start with one recurring customer problem:
"What do customers keep getting stuck on in our Decagon conversations, and does the same issue appear in our human support conversations?"
Review the evidence. Save the classifications that make the problem clearer. Then turn the investigation into an agent that keeps your team informed.
Your AI agent keeps helping customers. Every conversation can help your team make the next experience better.
Connect Decagon with an API key.
FAQ
What does Rippit's Decagon integration sync?
Full Decagon conversations on a schedule: customer and AI messages in order, conversation context (summary, resolution, CSAT, tags and metadata), voice recordings, which Rippit transcribes, and Watchtower review results, flags, rationales and scores.
Do I need to replace Decagon or Watchtower to use Rippit?
No. Teams keep Decagon to run the AI agent and add Rippit as an independent layer. Watchtower reviews come into Rippit with each conversation, so you can analyze them next to your human support conversations and account data. See Rippit vs. Decagon.
Do Rippit's agents talk to my customers?
No. Rippit's agents analyze conversations in the background and send findings, with the evidence, to your team in Slack or email. They don't talk to your customers in real time.
How does Rippit tell whether an AI-handled issue was actually resolved?
It reads the conversation itself alongside Decagon's resolution fields, CSAT and Watchtower reviews, and you can classify whether the customer explicitly confirmed success. Keeping "confirmed success" separate from "no further response" shows what each conversation actually establishes. For a step-by-step method, see How Do You Measure True Resolution for AI Agent Conversations?