Workflows

Realistic multi-step workflows you can run from Claude Desktop, Cursor, or VS Code using the OpenCX MCP server.

These workflows show what the MCP server handles well in practice. Each one is a series of prompts you can type directly into your AI client.

Investigate a Support Ticket

A customer escalated a ticket. Pull the full investigation into your editor instead of switching to the dashboard.

1. Look up the ticket

   “Investigate ticket #4521 — why did the AI hand off?”

2. Read the AI's reasoning

   “Show me the debug data for that session, including the AI’s reasoning steps and citations.”

3. Add an internal note

   “Add a comment on the last message: ‘Checked — handoff was correct, agent lacked refund policy training.’”

The assistant fetches the session summary, diagnostics, and handoff details, then posts a comment visible only to your team.

Train Your Agent From Unresolved Sessions

Your AI agent handed off 30 sessions last week. Find the patterns and create training so it handles those topics next time.

1. Find unresolved sessions

   “List sessions from the last 7 days that were closed as unresolved.”

2. Analyze handoff reasons

   “Show me handoff analytics for the last 7 days — what are the top reasons?”

3. Create training

   “Create a draft training scenario titled ‘Subscription cancellation flow’ that instructs the AI to walk the customer through cancellation steps and offer a retention discount before confirming.”

4. Review and publish

   Review the draft in your OpenCX dashboard, then:

   “Publish the training scenario ‘Subscription cancellation flow’.”

Pull Insights for a Sprint Review

Your product team meets weekly. Get a summary of what customers asked about most, grouped by theme.

1. List insight categories

   “What customer insight categories do we have?”

2. Fetch recent insights

   “List customer insights — show me the most recent ones with their categories and session counts.”

3. Drill into a theme

   “Show me the details for the top insight — which sessions does it reference?”

4. Assign follow-ups

   “Assign the billing-related insight to the Billing team.”

Set Up a New Phone Agent

Create an AI phone agent, attach knowledge, and make a test call — all from your editor.

1. Browse available voices

   “List available voices — I need a female US English voice.”

2. Create the agent

   “Create a phone agent named ‘Returns Hotline’ with that voice. Instructions: greet the caller, ask for their order number, then look up the return status.”

3. Attach knowledge sources

   “Attach the ‘Returns FAQ’ knowledge source to the Returns Hotline agent.”

4. Make a test call

   “Make an outbound call from the Returns Hotline agent to [phone].”

---

Related Documentation

Prompt Library

Quick single-shot prompts by domain

Tools Reference

Full list of available tools by domain

Get Started

Connect the MCP server to your AI client

Troubleshooting

Common issues and fixes