Skip to main content

Documentation Index

Fetch the complete documentation index at: https://koreai.mintlify.app/llms.txt

Use this file to discover all available pages before exploring further.

The Platform supports event-driven context sharing with AI for Service. When a handoff occurs, configured parameters—including conversation history, user data, and system metadata—are passed to AI for Service without loss of context. 
Configure Handoff Event → Map Parameters → Trigger Handoff → Access in AI for Service

​
Step 1: Configure the Handoff Event in Agent Platform

  1. Go to Settings > Events and enable the Agent Transfer Event.
  2. In the Description field, specify the conditions that trigger the event (for example, fallback, confidence drop, intent match, or explicit user request). By default, the event triggers when a conversation needs to be transferred to a human agent.
  3. Configure the parameters to pass to AI for Service during handoff. Two parameter types are supported:
LLM Collected parameters — Gathered automatically by the LLM based on the parameter description. Use for dynamic data such as conversation summaries or user sentiment. System-defined parameters — Explicitly defined with static or dynamic values from context or memory. Static value example: 
"source": "Agent Platform"
Dynamic value examples: 
username: {{memory.userProfile.firstName}}
ordernumber: {{memory.orderDetails.orderNumber}}
userPreferences: {{memory.sessionMeta.userPref}}
Learn more about event configuration →

​
Step 2: Access Metadata in AI for Service

Parameters passed from the Platform are available in the AI for Service Experience Flow under the Automation Node context. Use the following syntax to access them: 
{{context.steps.<<nodename>>.<<keyname>>}}
Example (Automation Node named queryResolver): 
{{context.steps.queryResolver.firstName}}
{{context.steps.queryResolver.orderNumber}}
{{context.steps.queryResolver.userPreferences}}