Agent Flows

​

Key Components

​

Choosing an Approach

​

Deterministic

• Regulatory compliance requires exact wording and predictable behavior (legal disclaimers, financial disclosures)
• Audit trails and full traceability are required
• Conversation follows a fixed, linear path
• Consistent responses matter more than natural conversation

​

Agentic

• Natural, human-like interaction is the priority
• User inputs vary widely for the same intent
• Ease of maintenance matters (a single Agent Node handles increasing complexity)
• You’re building toward more autonomous experiences

​

Hybrid

• Mixed requirements exist — some steps need strict control, others benefit from flexibility
• Transitioning gradually from deterministic to agentic
• Different use cases within the same app have different needs

• Banking: transactions are deterministic, general inquiries are agentic
• Healthcare: appointment booking is deterministic, health information is agentic

​

Trade-offs

​

Scoping Agent Flows

​

When to Split a Use Case

• Users have distinct goals (“Book appointment” vs. “Cancel appointment”)
• Fulfillment uses different backend APIs or workflows
• Training phrases are semantically distinct
• Required entities or business rules differ

​

When to Keep Together

• Variations express the same goal (“What’s my balance?” / “How much do I have?”)
• The same API handles all variations
• Training phrases overlap significantly
• Required entities are identical

​

Writing Effective Descriptions

• Semantically rich: Activate more embedding dimensions
• Action and goal-oriented: Include the primary action and desired outcome
• Contextual: Explain when users typically need this

• Check_Order_Status, Track_Order, View_Order_Details, Get_Order_Information

1. Track_Order_Shipment — Track shipping and delivery status for orders in transit. Users want to know WHERE their package is and WHEN it will arrive. Includes tracking numbers, carrier information, and estimated delivery dates.
2. View_Order_History — View past completed orders. Users want to see WHAT they ordered, when, and final totals. For historical reference, NOT active in-transit shipments.
3. Modify_Pending_Order — Make changes to an order that hasn’t shipped. Users want to UPDATE their order — change address, cancel items, or adjust quantities. Only for orders still processing, not yet dispatched.

​

Dialog Tasks

• Sub-intent management and Node Grouping — Configure sub-intents using group nodes or configure a task as a sub-intent
• Component Transitions — Configure if-else conditions between nodes based on custom criteria
• Voice and IVR Integration — Enable voice interaction (see Voice Call Properties)
• User and Error Prompt Management — Customize messaging at each node
• Context Object — Share data across tasks, intents, and FAQs (see Context Object)

​

Creating Dialog Tasks

​

From Scratch

1. Click Start From Scratch.
2. Enter an Intent Name (required) and Intent Description (recommended). Add up to 5 secondary descriptions to broaden semantic coverage and improve intent detection accuracy.
3. Set availability: Customer Use Case, Agent AI Use Case, or both.
4. Configure Intent Settings: set the task as sub-intent only or hide it from help.
5. Set Analytics - Containment Type: Abandonment as Self-Service or Drop Off.
6. Optionally set Conversation Context, Intent Preconditions, or Context Output.
7. Click Proceed.

​

Generate with AI

1. Click Generate with AI.
2. Enter an Intent Name and a meaningful Description, then click Generate.
3. Preview the generated flow. Click Regenerate with a revised description to refine.
4. Click Proceed when satisfied.

​

From Marketplace Templates

1. Click Marketplace and browse categories and integrations. Configured integrations are labeled Installed.
2. For Dialog Action Templates (API call templates): select an integration, then click Install on the desired template.
3. For Dialog Templates (pre-created flows): select a template, click Install, configure name and description, set up utterances and channel experience, then click Finish.

​

Session Management

​

JavaScript API

"EnterpriseContext" : {
    "get"    : function(key){},
    "put"    : function(key, value, ttl){},  // ttl in minutes
    "delete" : function(key){}
},
"BotContext" : {
    "get"    : function(key){},
    "put"    : function(key, value, ttl){},
    "delete" : function(key){}
},
"UserContext" : {
    "get" : function(key){}  // read-only
},
"UserSession" : {
    "get"    : function(key){},
    "put"    : function(key, value, ttl){},
    "delete" : function(key){}
},
"BotUserSession" : {
    "get"    : function(key){},
    "put"    : function(key, value, ttl){},
    "delete" : function(key){}
}

​

Session Variable Types

​

UserContext Read-Only Keys

​

Standard Keys

​

Method Limitations

• delete(): Removes root-level objects only. To delete nested keys, use delete context.session.BotUserSession.{path}. You cannot delete a root-level object using this syntax.
• put(): Inserts at root-level only. BotUserSession.put("Company.Address", val) is not supported.
• get(): Retrieves root-level objects only. BotUserSession.get("Company.name") is not supported.

​

Context Object

​

Context Object Keys

​

Node States

​

Tone Levels

​

Voice Call Properties

• App level: Set during channel enablement.
• Component level: Override per node — applicable to Entity, Message, Confirmation, Agent Node, and Standard Responses.

​

App-Level Channel Settings

​

Node-Level Voice Settings

​

Configuring Grammar

​

Nuance

1. Set Enable Transcription to No.
2. In Grammar: select Speech or DTMF, enter the VXML path to dlm.zip: https://nuance.kore.ai/downloads/kore_dlm.zip?nlptype=krypton&dlm_weight=0.2&lang=en-US (adjust the path and language code for your setup).
3. Click Add Grammar and add the path to nle.zip using the same steps.
4. Save.

​

Voximal / UniMRCP

1. Set Enable Transcription to Yes.
2. Enter the transcription engine source:
   • Voximal: builtin:grammar/text
   • UniMRCP: builtin:grammar/transcribe
3. Leave the Grammar section blank — the transcription source handles speech vetting.
4. Save.

​

Building Multilingual Applications

​

Input Processing

​

Response Processing

​

Hybrid Patterns

​

Decision Guide

​

Testing Checklist

• Verify language detection accuracy.
• Review translations with native speakers.
• Test edge cases: mixed-language input, special characters, RTL languages.
• Measure latency across approaches.
• Monitor API costs per interaction.

​

Common Pitfalls

• Compliance content: Always use locale-specific responses for legal text; never rely on automated translation.
• Double translation: Don’t enable both a Translation Engine and LLM translation simultaneously — this causes double translation and unpredictable output.
• Skipping native speaker review: Translations may be technically correct but culturally inappropriate. Always validate with native speakers.