Escalation to Human Agent from an Agent

Use ESCALATE when an agent cannot safely or confidently continue execution and requires human intervention. Escalation transfers the conversation to a human operator or handling system, ensuring continuity while preventing incorrect or risky automated responses.

Unlike agent-to-agent routing (HANDOFF / DELEGATE), escalation is specifically designed for human involvement and should not be modeled as a handoff to a human agent.

When to Use Escalation

Typical scenarios include:

• User frustration
• Customer complaints
• Policy validation requirements
• System failures
• Repeated routing failures
• High-risk or high-value operations

How Escalation Works

1. Agent evaluates escalation triggers.
2. When a trigger condition is met:
   • A new task is created in the Inbox for a human agent to review and proceed.
   • Agent execution is suspended.
3. A human agent reviews and completes the task.
4. After completion:
   • The system executes configured post-completion actions.
   • The workflow may resume, transfer, or end.

DSL Configuration

ESCALATE:
  triggers:
    - WHEN: condition
      REASON: "reason for escalation"
      PRIORITY: medium
      TAGS: [tag1, tag2]

  context_for_human:
    - variable1
    - variable2

  routing:
    queue: "queue_name"
    skill_tags: [skill1, skill2]
    priority_boost: 1

  on_human_complete:
    - IF human.resolved == true: COMPLETE

Trigger Properties

Property	Type	Required	Description
WHEN	string	Yes	Condition that triggers escalation.
REASON	string	Yes	Human-readable reason for the escalation.
PRIORITY	string	Yes	Priority level: low, medium, high, or critical.
TAGS	string[]	No	Tags for routing and categorization in the human agent queue.

Priority Levels

Level	Use case
low	Non-urgent requests (for example. general feedback).
medium	Standard requests (for example. user requests human assistance).
high	Urgent issues (for example. repeated failures, outages).
critical	Immediate attention required (for example. compliance violations, fraud).

Context for Human

The context_for_human block defines what data is sent to the human agent. This ensures the human agent has full context without asking the user to repeat information.

context_for_human:
  - customer_id
  - customer_name
  - amount
  - conversation_history

Structured Context

context_for_human:
  - NAME: case_summary
    TEMPLATE: "Customer {{customer_name}} requesting wire of {{amount}} {{currency}}"
    INCLUDE: [fraud_score, sanctions_match_score]

Routing Configuration

Controls how escalation is routed to the human system.

Property	Type	Required	Description
queue	string	No	Target queue in the human agent system.
skill_tags	string[]	No	Required skills for the human agent.
priority_boost	number	No	Additional priority applied to the task.

Post-Completion Behavior

Defines what happens after the human agent completes the task.

on_human_complete:
  - IF human.resolved == true: COMPLETE
  - IF human.needs_agent == true: HANDOFF to specified_agent
  - IF human.needs_followup == true: CONTINUE

Action	Behavior
COMPLETE	End the workflow
HANDOFF	Transfer back to an agent
CONTINUE	Resume the current agent

Examples

Escalation from Supervisor

SUPERVISOR: Customer_Service_Hub
VERSION: "2.0"
GOAL: "Route customers to the right specialist"

PERSONA: |
  Professional customer service coordinator. Routes requests
  efficiently and preserves context across agent transfers.

ESCALATE:
  triggers:
    - WHEN: routing_failures >= 3
      REASON: "Multiple routing failures"
      PRIORITY: high

    - WHEN: user.wants_human_agent == true
      REASON: "Customer requesting human specialist"
      PRIORITY: medium

  context_for_human:
    - user_id
    - conversation_summary
    - routing_failures
    - conversation_history

  routing:
    queue: "customer_support_l2"
    skill_tags: [support, escalation]
    priority_boost: 1

  on_human_complete:
    - IF human.resolved == true: COMPLETE
    - IF human.needs_agent == true: HANDOFF to Support_Agent

Escalation via ON_ERROR

THEN: ESCALATE triggers the escalation flow after retry attempts are exhausted.

ON_ERROR:
  tool_error:
    RESPOND: "I encountered an issue. Let me connect you with a specialist."
    RETRY: 1
    THEN: ESCALATE

  routing_failure:
    RESPOND: "I am having trouble routing your request."
    RETRY: 1
    THEN: HANDOFF Live_Agent_Transfer

Escalation vs Handoff

Aspect	ESCALATE	HANDOFF
Target	Human operator	Another agent
Visibility	User interacts with human	User interacts with agent
Use case	Failure / escalation scenarios	Multi-agent routing
Control flow	Suspends agent execution	Transfers execution

Troubleshooting

Issue	Resolution
Escalation never triggers	Verify the WHEN condition references variables that are actually set during the conversation. Test with explicit values.
Human agent lacks context	Include conversation_history in context_for_human. List all relevant session variables-IDs, collected data and current state.
Conversation stalls after human completes	Define on_human_complete handlers for all possible human outcomes (resolved, needs_agent, needs_followup).