Documentation
Chat
- Getting Started
- Installation
- Core Concepts
- Escalation System
- Widget Keys
- Secret Keys (sk_)
- REST API
- Channels & Integrations
- Messaging Platform API
Voice
- Voice Agent
- Setup Guide
- Phone Numbers
- Outbound Campaigns
Platform
- Billing & Pricing
- Glossary
- FAQ
Escalation System
Learn how to handle customer escalations and connect with human support agents.
What is Escalation?
Escalation is the process of transferring a conversation from your AI chatbot to a human support agent. This happens when:
- Customer explicitly requests to speak with an agent
- Chatbot detects low confidence in its answer
- Chatbot cannot find a relevant answer in the knowledge base
How Escalation Works
1. Trigger
A conversation is escalated when a customer requests it or when the chatbot detects it needs human assistance. The visitor is asked for their name and email so the agent can follow up.
2. Queue
The conversation enters the escalation queue for the workspace. If an agent is online, they're assigned automatically. Otherwise the request is queued until an agent comes online.
3. Assignment
An agent accepts the conversation and takes over the chat with full context from the previous interaction.
4. Resolution
The agent resolves the issue and closes the conversation.
Agent Dashboard
Support agents have access to a dedicated dashboard where they can:
- View the escalation queue for their workspace
- Accept and respond to conversations in real time
- See full conversation history and context
- Add private notes for internal collaboration
- Toggle online/offline status
- Track response times
Set up escalation rules in your chatbot configuration to automatically escalate certain types of conversations.
