Customer Support Ticketing Agent
This is a 'Workflow' template which means that it is a single standalone workflow.
Some workflow templates can be modified to work with other workflow templates - e.g. to convert a data sync between two services from uni-directional to bi-directional
Custom Support Ticketing AgentCopy
OverviewCopy
This accelerator enables you to create an AI-powered CS agent that searches across multiple sources to provide comprehensive answers to your team's questions, leaves comments on tickets in Zendesk, and updates tickets in Zendesk. The agent combines knowledge across sources to deliver accurate, contextualized responses and augment your support team.
Key FeaturesCopy
Public Documentation Search: Leverage your organization's public documentation
Intelligent Response Generation: Uses advanced LLMs to synthesize information from multiple sources
Zendesk Deployment: The agent is deployed directly to Zendesk so it runs asynchronously anytime a new ticket is created
Standard Operating Procedures: Use Google docs as a source of truth for your procedures and FAQs to give the agent easy access to a living document used by the team.
PrerequisitesCopy
Before implementing this template, you will need:
To make sure your organization has this AI feature enabled (Admin access required)
Access to a Tray.io instance with API credentials
URLs for your public documentation
Authentication credentials for Zendesk
Authentication credentials for Google Docs
Getting LiveCopy
Initial SetupCopy
Create a new project
Select "Merlin Agent Builder"
Select the Support Ticket Agent accelerator
Create or select required authentications
Configure Knowledge SourcesCopy
Scrape your Public Documentation
Add documentation URLs to the scraping form or the manual scraping workflow
Set up crawling depth
Google Docs
Add your Google Docs API credentials
Deploy the AgentCopy
Enable the main workflow
Test with sample queries
Monitor performance and adjust the system prompt as needed
Key Workflow ComponentsCopy
Knowledge ProcessingCopy
Documentation Crawler: Indexes public documentation
Vector Creation: Generates embeddings for all content
Knowledge Storage: Manages vector database operations
Query ProcessingCopy
Query Understanding: Agent reasons over the user questions
Response Generation: Synthesizes information into coherent answers
Session Management: Maintains context across invocations of the agent that are related
Best PracticesCopy
Regularly update your knowledge base
Monitor and adjust RAG thresholds (both in the knowledge tool)
Review and refine response quality
Implement feedback loops for continuous improvement
Add more tools that have access to internal knowledge (CRM, Internal Documentation, etc)
Run evaluations - you can follow our guidance here