An AIRecommendedAction entity represents a recommended action based on AI analysis. It provides contextual insights and justifications for decision-making, along with confidence scoring.
Properties
Name
Description
Type
Example
uid
A unique identifier for the recommended action
string
act-456
action
The type of action recommended (reply, estimate, schedule)
string
reply
display
Contains display-related information for the recommendation
object
See Display Properties below
reason
The reason why this action is recommended, providing context for decision-making
string
User needs clarification on pricing
payload
Additional data related to the recommended action. The structure depends on the action type
object
{}
evidence
A list of supporting statements or facts justifying the recommendation
array
["User asked for price estimate"]
Display Properties
Name
Description
Type
Example
title
A human-readable title describing the action
string
Follow up with the client
description
A human-readable description of the action
string
The recommended time for an appointment is Monday 5th of March. Click "Auto-fill" to apply
btn_text
The text on the button
string
The text that should appear on the button for recommendation "Ask for more details"
Possible payloads
Reply
Payload example
{
"uid": "act-456",
"action": "reply",
"display": {
"btn_text": "Generate Reply"
},
"reason": "User needs clarification on pricing",
"payload": {
"email_message":"I need more details to send you a quote<br/>best regards,<br/>ramster",
"sms_message":"I need more details to send you a quot"
,
"FB_message":"I need more details to send you a quot"
},
"other_message":"I need more details to send you a quot"
}
"evidence": ["User asked for price estimate"]
}