> For the complete documentation index, see [llms.txt](https://studio.docs.ai.vonage.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://studio.docs.ai.vonage.com/ai-studio/agentic-nlu-ai-engine.md).

# Agentic NLU AI engine

## Introducing Agentic NLU: Vonage’s most advanced AI engine yet 

Powered by cutting-edge NLU and autonomous agents, Vonage's Agentic NLU AI engine enables virtual assistants to understand context, make decisions, and take action, turning static scripts into intelligent, goal-driven conversations.

{% hint style="warning" %}
**Gated feature**

Agentic NLU is currently a gated feature. For more information, please contact Vonage Support or your Account Manager.
{% endhint %}

### How an AI Agent works

To fully leverage Agentic NLU, it is essential to understand that an AI Agent operates in a continuous loop of perception, planning, and execution.

{% stepper %}
{% step %} <mark style="color:$primary;">**Perception**</mark>

The agent observes the user’s input.

*Example input:* "I want to fly to London tomorrow."
{% endstep %}

{% step %} <mark style="color:$primary;">**Goal identification**</mark>

The agent identifies the user's specific objective based on the input received.

*Goal:* Book a flight to London for tomorrow.
{% endstep %}

{% step %} <mark style="color:$primary;">**State evaluation**</mark>

The agent assesses what it knows vs. what it needs.

*Current State:* Missing departure time.
{% endstep %}

{% step %} <mark style="color:$primary;">**Planning**</mark>

The agent generates a sequence of steps to reach the goal.

*Steps:* Ask for time → Search flights → Offer options → Confirm booking
{% endstep %}

{% step %} <mark style="color:$primary;">**Action selection**</mark>

The agent selects the next best move based on the plan (e.g., asking a question or calling an API).

*Action:* “What time would you like to depart tomorrow?”
{% endstep %}

{% step %} <mark style="color:$primary;">**Execution**</mark>

The agent acts and updates the state.

*User response:* “Evening.”
{% endstep %}

{% step %} <mark style="color:$primary;">**Goal check**</mark>

The agent checks if the goal is met.&#x20;

* If the goal is met, the agent marks the goal as completed.
* If the goal is not met, the agent loops back to Step 4 to refine the plan.
  {% endstep %}
  {% endstepper %}

### **Why Agentic NLU is unique**

{% hint style="success" %}
**Pro Tip**

If your current flows rely heavily on complex NLU mapping and repetitive input nodes, switching to Agentic NLU can significantly reduce your maintenance burden.
{% endhint %}

Agentic NLU allows virtual agents (VAs) to engage in dynamic, natural interactions without relying on predefined flows. It is designed to provide human-like intelligence at every touchpoint while maintaining the reliability of deterministic actions.

<details>

<summary><mark style="color:$primary;"><strong>For builders: Effortless configuration</strong></mark></summary>

For the VA builders, Agentic NLU represents a shift from explicit logic mapping to objective-oriented configuration:

* <mark style="color:$primary;">**De-cluttered flow design:**</mark> A single Agentic Capture node can replace multiple Collect Input nodes. Additionally, Agentic nodes have the entire communication layer (Speak & Listen) preconfigured and running in the backend.
* <mark style="color:$primary;">**Low training overhead:**</mark> Define intents with a simple description and a few examples rather than hundreds of user expressions.
* <mark style="color:$primary;">**Instant configuration:**</mark> Add or update intents and parameters instantly using natural language instructions (LLM prompts), drastically reducing manual training data requirements.
* <mark style="color:$primary;">**Robust voice handling:**</mark> Built-in fuzzy matching automatically corrects Automatic Speech Recognition (ASR) transcription errors, preventing unnecessary call failures.
* <mark style="color:$primary;">**Pre-configured governance:**</mark> Each Agentic node includes built-in system instructions, goals, safety guardrails, and memory configurations.
* <mark style="color:$primary;">**End-to-End Agentic Architecture:**</mark> The Agentic NLU Template enables you to route 100% of callers' conversations via AI Agents, providing human-like intelligence at every stage of the interaction.

</details>

<details>

<summary><mark style="color:$primary;"><strong>For callers: An intuitive experience</strong></mark></summary>

Agentic NLU creates an authentic conversational experience where callers feel understood, not just processed.

* <mark style="color:$primary;">**Natural, free-flowing dialogue:**</mark> Callers speak naturally without needing to follow a script or specific keywords.
* <mark style="color:$primary;">**Multi-parameter capture:**</mark> An Agentic node can extract multiple pieces of information (e.g., date, destination, and time) from a single caller utterance.
* <mark style="color:$primary;">**Dynamic context switching:**</mark> If a caller shifts topics mid-flow, the Agentic node recognizes the change request and transitions smoothly to the new topic without restarting the conversation.
* <mark style="color:$primary;">**Automatic contextual responses:**</mark> The engine generates smart replies to handle ambiguity or invalid input, providing corrective guidance without manual scripting.
* <mark style="color:$primary;">**Proactive frustration detection:**</mark> Identifies escalation triggers based on repeated failures or unmet goals before a caller even asks for a human.

</details>

### Agentic NLU limitations

* Available for voice agents and English language only.
* An Agentic Response is automatically generated by LLMs and cannot be manually defined by Studio users.
* Retry behavior and reconfirmation behavior are predefined and cannot be altered manually.
* When using Agentic NLU, AI engine selection becomes fixed and cannot be changed.
* Agentic NLU uses a different set of components and architecture from Hybrid NLU or Traditional NLU, preventing cross-engine migration.&#x20;
  * Once an agent is created with Agentic NLU, it cannot be switched to another NLU engine.
  * Agents built with the Hybrid NLU or Traditional NLU engines cannot be imported or duplicated into Agentic NLU.
  * Similarly, agents built with Agentic NLU cannot be converted to Hybrid NLU or Traditional NLU.
* Agents built on the Agentic NLU engine are not supported by [Virtual Assistant Historical Analytics](https://docs-vcc.atlassian.net/wiki/spaces/DP/pages/5726535743/Virtual+Assistant+Historical+Analytics). To capture and report session data, use Traditional NLU or Hybrid NLU.

***

## Understanding the architecture: Agentic nodes

Agentic NLU relies on two specialized AI Agents implemented as Agentic nodes. These nodes structure how conversations are handled, ensuring that every caller's input is evaluated and routed appropriately through a continuous reasoning loop, enabling fluid, goal-driven interactions.

#### <mark style="color:$primary;">**Agentic Classification node (The Hub)**</mark>

As the Hub, this node serves as the assistant's central brain. It identifies the caller's intent or topic at each stage of the conversation and routes the flow accordingly. It includes key functionalities such as:

* **Intent recognition:** Classifies the caller's input against Agentic Intents to determine the most relevant intent or topic.
* **Global Intent support:** Recognizes and processes global intents (e.g., “Cancel,” “Talk to agent”) when configured.
* **LLM-powered matching:** Employs large language models (LLMs) for prompt-based classification, requiring minimal training data.
* **Outcome handling:** Delivers one of three outcomes, Success, Missed, or Failed, based on the classification result.
* **Intent storage & Agentic fallbacks:** Records the detected intent for downstream use. If no match is found, it automatically generates an informed response suggesting available intent options.
* **Isolated testing:** Features a Save and Test option for standalone classification performance testing during configuration.

#### <mark style="color:$primary;">**Agentic Capture node (The Branch)**</mark>

As a Branch, this node functions as the specialist. It is triggered by the Hub to gather the specific data points (parameters) needed to fulfill a chosen intent. It includes key functionalities such as:

* **Intent tracking:** Continuously monitors the active intent and recognizes context changes (e.g., switching to a new intent during a conversation).
* **Multi-parameter capture:** Acquires multiple parameters within a single process when required to complete an intent.
* **Retry handling:** Facilitates parameter retries to ensure accurate value capture in the desired format.
* **Reconfirmation support:** Validates captured parameter values with callers, particularly valuable in voice interactions where ASR errors occur frequently.
* **Agentic responses:** Automatically produces contextual replies to address incomplete or incorrect caller's inputs, maintaining conversation fluency.
* **Proactive escalation detection:** Detects potential escalation scenarios during interactions and pinpoints the specific parameter that triggers them. Escalation is managed automatically — no additional setup needed.

{% hint style="info" %}
**The hub-and-branch loop**

The conversation remains within the Agentic Capture node (the Branch) until the task is complete or an escalation is triggered. If the AI Agent detects a topic shift, it triggers an “Intent Change” scenario. This seamlessly routes the caller back to the Agentic Classification node (the Hub) to re-evaluate the request and re-orient the flow.
{% endhint %}

For instructions on creating and configuring an Agentic NLU agent, see:

{% content-ref url="/pages/c3xdhgHFXr9kHMVQeUyM" %}
[Building an Agentic NLU agent](/ai-studio/agentic-nlu-ai-engine/building-an-agentic-nlu-agent.md)
{% endcontent-ref %}

***

## Reports: Call logs

<figure><img src="/files/JqUXP6xKpyzuo09jDjdO" alt=""><figcaption></figcaption></figure>

Every conversation is logged and visible under **Reports.** Call logs show input, detected intent, captured parameters, and, if capture failed, the reasons for escalation. You can use call logs to improve coverage and adjust flows.&#x20;

The Call log modal consists of the following elements:

* **Session Information:** Summarizes essential call details: agent name, event type, caller and agent phone numbers, date and time, and session ID.
* **Transcript:** Contains the full agent-caller conversation transcript, clearly indicating who spoke and when.
* **Parameters**: Displays all parameters captured during the call, showing exactly how input was processed and where it succeeded or failed.
* **Flow Path**: Displays a complete trail of every node triggered during a call. Additionally, it exposes the underlying Communication Layer to ensure full transparency:
  * It displays a count of the total number of nodes used from the Communication Layer across all conversation loops.
  * Every node activated throughout the session is documented, showing the specific order of the "Perceive-Plan-Act" cycle.
  * You can access the Input and Output details for each node within the loop by selecting the "Show More" option.
  * It provides the status code for every triggered node, confirming successful execution at each step.

<div align="center" data-with-frame="true"><figure><img src="/files/egY0sS7tPr7xKNQ2Ogyb" alt="" width="375"><figcaption></figcaption></figure></div>

To access call logs, perform the following steps:

1. Navigate to **Reports** in the black ribbon at the top of the screen.
2. Select **Reports** from the dropdown menu.
3. In the Generate Report section, select **Call Log** as the Report type.&#x20;
4. The session list updates automatically. Click the session ID of the session you wish to inspect.

***

## Migration and Compatibility&#x20;

To duplicate your Agentic NLU agent, perform the following steps:

1. Find the agent you want to duplicate.
2. Click **More Actions** (⋮) and select **Duplicate**.&#x20;
3. Edit the fields available in the Duplicate Agent modal.
4. Click **Duplicate Agent** to save your new VA.

To import an Agentic NLU agent, perform the following steps:

1. Click **Import Agent** on the right-hand side.&#x20;
2. Upload or drag and drop the zip file with your agent.
3. The fields in the Import Agent modal autopopulate with the agent's information. You can check and edit them if required.
4. Click **Import Agent** to save your new VA.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://studio.docs.ai.vonage.com/ai-studio/agentic-nlu-ai-engine.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.