Skip to main content
Manual actions let the AI Agent request a human agent to perform tasks that can’t be automated – either because no API exists or the task requires human judgment. Best for:
  • Systems without API or integration support
  • Sensitive tasks requiring human judgment
  • Bridging gaps while implementing full integration

​
How manual actions work

  1. AI Agent identifies need – during a conversation, it determines a manual action is required
  2. AI Agent collects information – gathers required data from the customer
  3. Request sent to human agent – conversation hands off with a pending action
  4. Human agent executes – performs the action in the external system
  5. Human agent confirms – marks the action complete or rejected

​
Configure a manual action

Manual action configuration form
FieldDescription
Action nameDescriptive name (e.g., “Refund Order”, “Update Billing Address”)
Action descriptionWhen the AI Agent should suggest this action
Required informationData the AI Agent must collect before requesting

​
Required information fields

Each field has:
  • Name – identifier (e.g., order_id, refund_reason)
  • Description – what to ask the customer
  • Type – Text, Number, or Yes/No

​
Human agent workflow

When the AI Agent requests a manual action, human agents see it in their inbox.

​
View pending actions

The ticket shows:
  • Action requested (e.g., “Refund Order”)
  • Collected information from the customer
  • Conversation context

​
Accept or reject

To accept:
  1. Review the collected information
  2. Perform the action in your external system
  3. Click Accept to confirm
  4. Optionally add a note describing what you did
To reject:
  1. Click Reject
  2. Provide a reason (helps the AI Agent respond appropriately)
  3. Conversation returns to AI Agent handling with your feedback

​
Example: Refund order

Configuration:
FieldValue
Action nameRefund Order
DescriptionUse when a customer requests a refund. Collect order ID and reason first.
Required information:
NameDescriptionType
order_idOrder number to refundText
refund_reasonWhy the customer wants a refundText
refund_amountAmount to refund (or “full”)Text
Human agent sees: 
Action Requested: Refund Order

Collected Information:
- Order ID: ORD-12345
- Refund Reason: Item arrived damaged
- Refund Amount: full

Customer Context:
"I received my order yesterday but the package was crushed
and the item inside is broken. I'd like a full refund please."
The human agent processes the refund, then clicks Accept.

​
See also