Walk through

Overview

Let's examine how RedaXion allows you to navigate within a conversation using the example below.

Example

The business requirement is to capture the customer's answer when asked for their token.

Scenario #1

AGENT: May I have your token?

CLIENT: Hold on, I need to find it. [UTTERANCE 1]

AGENT: Please take your time.

CLIENT: Found it. it's 4567. [UTTERANCE 2]

Advanced Example

Normally we would expect the answer immediately after the question, but in this case the answer is located within the customer's second utterance from the question.

Scenario #2

CLIENT: My token in 4567. [UTTERANCE 1]

AGENT: Thanks for providing that information.

Configuration

The configuration for the scenarios above is as follows:

{
    "sid": "NER005",
    "name": "NER_Processing",
    "active": true,
    "agent_location": "left",
    "inbound": true,
    "scrubaudio": true,
    "scrubtext": true,
    "insights":[
        {
            "name": "Token_Request",
            "label": "[TOKEN]",
            "active": true,
            "description": "token validation",
            "leg": "agent",
            "validation": true,
            "real_time": true,
            "trigger":{
                "expression": "(\"can i\" | digit)  ~> token",
                "redaction": {
                    "type": "all"
                }
            },
            "response": {
                "expression": "\\b\\d{3,5}\\b",
                "before": 2,
                "after": 2,
                "redaction": {
                    "type": "all",
                    "audio": true,
                    "text": true
                }
            }
        }
    ],
    "rules": [
        {
            "name": "Email",
            "active": true,
            "mask_type": "Placeholder",
            "setting": "[EMAIL]",
            "real_time": true
        },
        {
            "name": "Person",
            "active": true,
            "mask_type": "Placeholder",
            "setting": "[NAME]",
            "real_time": true
        }
    ]
}

Before Field

The before field allows you to search the specified number of utterances before the triggered event. Covers scenario #2.

After Field

The after field allows you to search the specified number of utterances after the triggered event. Covers scenario #1.