Learn how to integrate our Conversational AI platform with Zendesk for better customer support

Overview

With our Zendesk integration, your support agent can quickly identify and resolve customer issues by leveraging historical ticket data. This integration streamlines the support process by automatically checking for similar resolved issues, advising customers based on past resolutions, and securely creating new support tickets. Benefits include faster resolutions, reduced manual effort, and enhanced customer satisfaction.

Demo Video

Watch the demonstration of the Zendesk + Conversational AI integration.

Zendesk Integration Demo

How it works

We lay out below how we have configured the Conversational AI agent to resolve tickets by using tool calling to step through the resolution process. Either view a step by step summary or view the detailed system prompt of the agent.

1

Initial Inquiry & Issue Details

Configure your agent to ask for a detailed description of the support issue and follow up with focused questions to gather all necessary information.

2

Check for Similar Issues

Configure the agent to check historical tickets for similar issues by:

  • Using the get_resolved_tickets tool to fetch past tickets
  • Finding similar tickets and their resolutions
  • Extracting relevant comments via the get_ticket_comments tool
  • Using this information to suggest proven solutions
3

Contact Information Collection

If the ticket can’t be deflected:

  • Collect and validate the customer’s full name
  • Verify email address accuracy
  • Confirm any additional required fields for your Zendesk setup
4

Ticket Creation

  • Use the zendesk_open_ticket tool after information verification
  • Follow the ticket template structure
  • Confirm ticket creation with the customer
  • Inform them that support will be in touch

This integration enhances efficiency by leveraging historical support data. All API calls require proper secret handling in the authorization headers.

Tool Configurations

The integration with zendesk employs three webhook tools to create the support agent. Use the tabs below to review each tool’s configuration.

Name: get_ticket_comments
Description: Retrieves the comments of a ticket.
Method: GET
URL: https://your-subdomain.zendesk.com/api/v2/tickets/{ticket_id}/comments.json

Headers:

  • Content-Type: application/json
  • Authorization: (Secret: zendesk_key)

Path Parameters:

  • ticket_id: Extract the value from the id field in the get_resolved_tickets results.
Ensure that you add your workspace’s zendesk secret to the agent’s secrets.

Evaluation Configuration

To improve the observability of customer interactions, we configure the agent with the following evaluation criteria and data collection parameters.

Evaluation criteria for support interactions
Track how well the AI agent performs against key evaluation criteria like issue relevance, sentiment, and resolution success.

These settings are added directly to the agent’s configuration in the “Analysis” tab to ensure comprehensive monitoring of all customer interactions. This enables us to track performance, identify areas for improvement, and maintain high-quality support standards.

Impact

With this integration in place, not only can you resolve tickets faster, but you can also reduce the load on your support team by deflecting tickets that are not relevant to your team.

In addition, you can use the Conversational AI platform to monitor the agent’s usage.

Support agent conversation summary
Get a high-level overview of each conversation and listen to the conversation's audio recording.
Evaluation criteria for support interactions
Track how well the AI agent performs against key evaluation criteria like issue relevance, sentiment, and resolution success.
Data collection parameters from conversation transcripts
Monitor the data collected during each interaction, including tools used, issue details, and customer information.
Detailed conversation transcript example
Review detailed transcripts of conversations to understand agent performance, tool usage and customer interactions.

Security Considerations

  • Use HTTPS endpoints for all webhook calls.
  • Store sensitive values as secrets using the ElevenLabs Secrets Manager.
  • Validate that all authorization headers follow the required format.

Conclusion

This guide details how to integrate Zendesk into our conversational AI platform for efficient support ticket management. By leveraging webhook tools and historical support data, the integration streamlines the support process, reducing resolution times and enhancing overall service quality.

For additional details on tool configuration or other integrations, refer to the Tools Overview.

Built with