Vonage AI Studio
  • Welcome to AI Studio!
  • ✨Platform Updates
  • AI Studio
    • Create a new agent
    • NLU AI Engine Preferences
    • Agent Building Features
    • Agent Templates
      • Take Message
      • Updating Details
      • Survey
      • FAQ
      • Package Tracking
      • Caller Identification
      • Customer Service
      • Hotels
      • Appointment Management
    • Tester
    • Editor Mode & Publish
    • Reports
    • Users
    • Knowledge AI
  • Properties
    • Entities
      • System Entities List
      • Best Practices
    • Intents
      • How do we analyze user input?
      • Generate Training Data
      • System Intents
      • Intent Annotation
    • Parameters
    • Contacts
    • Tags
    • Recordings
  • Voice
    • Get started
      • Create your first conversational flow!
      • Triggering Outbound Call API
      • Sending an Outbound Call Request via Postman
      • Integration via SIP for Telephony Agents
    • Nodes
      • Start node
      • Conversation
        • Classification
          • Intent Ambiguity
        • Collect Input
          • Entity Ambiguation
        • Speak
        • Conditions
        • Listen
        • Q&A Node
      • Advanced
        • Reset Counter
        • Counter
        • Set Parameter
        • Custom Code
        • NCCO Node
      • Actions
        • Send Email
        • Call Routing
        • End Call
        • Start Recording
        • Stop Recording
        • Send SMS
      • Integrations
        • Webhook
        • Legacy SalesForce Authentication Node
          • SalesForce Authentication
            • How to create a SalesForce Connected App
        • SalesForce Actions
        • Generative AI
          • Setting up Generative AI Node Integration
          • Migrating from the GenAI node to Knowledge AI
      • Flow Control
        • Context Switch
        • Flows
    • Events
  • WhatsApp
    • Get started
      • Create your first conversational flow!
      • Triggering an outbound WhatsApp virtual agent
    • Nodes
      • Start node
      • Conversation
        • Collect Input
          • Entity Ambiguation
        • Classification
          • Intent Ambiguity
        • Send Message
        • Conditions
      • Advanced
        • Reset Counter
        • Counter
        • Set Parameter
        • Custom Code
      • Actions
        • Send Email
        • End Conversation
        • Send SMS
        • Live Agent Routing
      • Integrations
        • Webhook
        • Legacy SalesForce Authentication Node
          • SalesForce Authentication
            • How to create a SalesForce Connected App
        • SalesForce Actions
        • Generative AI
          • Setting up Generative AI Node Integration
          • Endless FAQs on WhatsApp With Generative AI and AI Studio
      • Flow Control
        • Context Switch
        • Flows
    • Events
  • SMS
    • Get started
      • Create your first conversational flow!
      • Triggering an outbound SMS Virtual Agent
    • Nodes
      • Start node
      • Conversation
        • Classification
          • Intent Ambiguity
        • Conditions
        • Send Message
        • Collect Input
          • Entity Ambiguation
      • Advanced
        • Reset Counter
        • Counter
        • Set Parameter
        • Custom Code
      • Actions
        • Send Email
        • End Conversation
        • Send SMS
        • Live Agent Routing
      • Integrations
        • Webhook
        • Legacy SalesForce Authentication Node
          • SalesForce Authentication
            • How to create a SalesForce Connected App
        • SalesForce Actions
        • Generative AI
          • Setting up Generative AI Node Integration
          • Use Case Example: Gym Business
      • Flow Control
        • Context Switch
        • Flows
    • Events
  • HTTP
    • Get started
      • Create your first conversational flow!
    • Nodes
      • Start node
      • Conversation
        • Classification
          • Intent Ambiguity
        • Collect Input
          • Entity Ambiguation
        • Send Message
        • Conditions
      • Advanced
        • Reset Counter
        • Counter
        • Set Parameter
        • Custom Code
      • Action
        • Send Email
        • Send SMS
        • Live Agent Routing
          • Websockets connections for Live agent Routing
      • Integrations
        • Webhook
        • Legacy SalesForce Authentication Node
          • SalesForce Authentication
            • How to create a SalesForce Connected App
        • SalesForce Actions
        • Generative AI
          • Setting up Generative AI Node Integration
          • Use case Example : Online Shopping
      • Flow Control
        • Context Switch
        • Flows
    • Events
  • API Integration
    • Authentication
    • Insights
  • There's more
    • FAQs
    • Languages Available
Powered by GitBook
On this page
  • Introducing the NEW Hybrid NLU 🚀
  • How to get started
  • Using the New Hybrid NLU Features Effectively
  • 1. Selecting the right AI Engine
  • 2. Creating Intents
  • 3. Defining Custom Entities
  • 5. Testing and Iterating
  • Migration Tips for Existing VAs

Was this helpful?

  1. AI Studio

NLU AI Engine Preferences

Reliable traditional NLU model vs. upgrading to the power of our new LLM-driven Hybrid NLU! 🌟

PreviousCreate a new agentNextAgent Building Features

Last updated 2 days ago

Was this helpful?

What is an NLU AI Engine?

Natural language understanding (NLU) is a subtopic of natural language processing in artificial intelligence that deals with machine reading comprehension.

Language understanding is a fairly complicated task as it involves understanding the meaning of the sentence, extracting the entities, and making a decision regarding the action to be taken.

The NLU's ability to understand the user relies on training in knowledge domains. This means that we can expand NLU capability to understand new domains by adding a new knowledge domain for it to train on.

The main goal is to understand user textual input and convert it into structured data that holds, among other things, the extracted entities, an action to be taken, and a textual response for the user.

Learn more .

Introducing the NEW Hybrid NLU 🚀

AI Studio’s new Hybrid NLU is a major leap forward in language understanding -

Powered by cutting-edge transformer models from Google Gemini, it goes beyond rigid, rule-based systems to truly grasp context, intent, and the subtle meaning behind every user input. This next-gen engine brings smarter intent recognition and sharper entity extraction - no heavy lifting required.

🌟 Why It’s a Big Deal 🌟

  • Boosts performance: Up to 20% better intent detection and improved entity extraction (based on internal VAI testing), leading to higher VA containment rates and fewer human escalations. That means smoother experiences and real cost savings.

  • Reduces manual effort: No more wrestling with giant synonym lists or rigid classification trees. Hybrid NLU handles nuance with minimal training.

  • Accelerates language support: Onboarding new languages is faster and more flexible, making it easier to adapt to evolving customer needs. The following languages are available with the New Hybrid NLU model: Arabic, Danish, Dutch, English, Finnish, French, German, Hebrew, Indonesian, Italian, Japanese, Korean, Norwegian, Polish, Portuguese, Spanish, Swedish, Thai.

  • Built to scale: Ideal for global rollouts, this model makes your VA more robust, responsive, and context-aware from day one.

How to get started

This guide will walk you through how to build, train, and optimize your Virtual Agents using the new Hybrid NLU model.

Using the New Hybrid NLU Features Effectively

Key new capabilities you should leverage:

  • Intent Ambiguation: Automatically detects multiple possible intents and allows your VA to clarify with the user.

  • Entity Ambiguation: Handles conflicting or multiple entities intelligently after extraction.

  • Multi-value Parameters: Supports capturing multiple values in one go (e.g., "I want a red shirt and blue jeans").

1. Selecting the right AI Engine

When creating or duplicating an agent, you will see an AI Engine dropdown with two options:

  • Hybrid NLU 🚀

  • Traditional NLU

Important: Once a VA is created, the AI Engine cannot be changed later. Choose carefully during setup. However, if you still need to change the AI engine, then you will have to duplicate/ import an existing VA and choose the appropriate AI engine.

2. Creating Intents

With the new Hybrid NLU, training just got a whole lot smarter! Keep these best practices in mind to get the most out of your intents -

Do
Don't

Use full, rich sentences for training your intents to give better context.

Example:

✅ "I’d like to book a reservation for Saturday."

Don’t rely on single-word expressions unless absolutely necessary.

Example:

❌ "Reservation"

Define custom entities with a detailed "Description" field using natural language - think of it like giving the AI clear instructions.

Example:

✅ entity name: delivery_method

✅ description: “The way the item is sent, such as mail, email, or fax.”

❌ No description or vague labels like "method" - poor prompts = poor extraction.

✅ Keep your user expressions meaningful but concise - quality over quantity.

❌ 10 near-identical expressions - don’t flood intents with redundant data.

Flatten your classification design - NLU V2 handles nuanced intent detection better without complex hierarchies.

Example: ✅ Use standalone intents like “Check account balance” instead of nested flows.

❌ "Banking > Balance > Checking" - don’t overcomplicate with rigid parent-child trees.

Test intents and entities thoroughly using the VA Tester after each major update.

Example: ✅ Simulate user input like “Can I get a transcript from last semester?” to verify behavior.

❌ Don’t assume the VA behaves the same as Legacy NLU - always revalidate.

Use the "New" AI Engine when creating or duplicating agents to leverage NLU V2 capabilities.

Example: ✅ Select “New AI Engine” during agent creation for better performance.

❌ Don’t change the AI Engine after creation — it’s locked once the VA is built (unless you create a duplicate/ import copy of an existing VA)

Use both Closed Lists and Descriptions for critical entities when maximum precision is needed.

Example: ✅ Closed list: “email, mail, fax” + description: “A method of communication.”

❌ Don’t write robotic, keyword-stuffed expressions - NLU V2 understands real conversation.

3. Defining Custom Entities

The New Hybrid NLU allows three methods to define custom entities:

Description Write natural language rules about what the entity should capture. Use this when the entity has a clear structure but no predefined values.

Example: “Order number consists of four letters, an underscore, and four digits.”

Both Description and Closed List Provide a list of acceptable values and optional synonyms - Ideal for well-bounded value sets.

Example: Entity: communication_type Description: "The method someone wants to use to communicate

Values and Synonyms: Phone → "call", "phone call", "mobile" Fax → "facsimile", "fax message" Email → "e-mail", "mail"

Using Closed Lists?

Toggle "Enable fuzzy matching" checkbox to leverage closed lists with low training data (i.e, synonyms for values in closed list).

Entity Definition Tips

  • Use clear, detailed descriptions (up to 500 characters).

  • Descriptions act like LLM prompts - the better you describe it, the better the extraction you'll get.

  • Use meaningful names and keep entity structures consistent across your VA.

5. Testing and Iterating

Use the VA Tester extensively to:

  • Validate intent detection

  • Verify entity extraction

  • Identify any gaps or edge cases early

During testing, compare the new Hybrid NLU behavior against the legacy NLU expectations: Expect better accuracy, but slightly slower response times (~100ms extra), which are imperceptible to end users.

Migration Tips for Existing VAs

Duplicating an old VA to the new Hybrid NLU?

Step 1: Select "New" AI Engine during duplication.

Step 2: Review and possibly simplify your classification nodes.

Step 3: Add richer user expressions if your old VA relied heavily on single-word triggers.

Step 4: Redefine custom entities using the new "Description" field for better performance.

Traditional NLU to Hybrid NLU will show an error with custom entities and this error will have to resolved by adding “Description” for custom entities.

🚨 Important: Migrations should be tested thoroughly before going live.

Pro Tips 🔥

  • Smarter AI needs smarter input: think about context and clarity in your expressions and entities.

  • The New Hybrid NLU minimizes manual effort, but a good initial design is still crucial.

  • Stay updated: More improvements will be rolled out, including further documentation and best practices based on community feedback.

here