# Governance types In Syntphony Conversational AI, **Governance types** defines how user interactions are: * Interpreted; * Routed; * Executed. Governance determines the balance between: * Deterministic control; * Autonomous Agent-based execution. Each Governance type represents an execution type on a continuum, from structured to fully dynamic. ## Overview After creating a Project, certain restrictions may apply when changing the governance type, depending on the components and configurations already in use. SCAI offers multiple AI Governance types to support different business needs and complexity levels. #### Which one to choose? * **NLU**, for structured, intent-based interactions; * **Agentic**, for dynamic problem-solving capabilities; * **Composite**, combining both approaches for flexibility and control. From left to right, Governance types increase in **flexibility** and **autonomy**: * **NLU flows:** Fully structured and deterministic; * **Composite (NLU-first):** Structured with controlled access to Agents; * **Composite (Agentic-first):** Agent-driven with selective structure; * **Agentic:** Fully dynamic, Agent-based execution.

Governance types

Read the explanations below to understand the available options. ## NLU flows The **NLU flows** are designed for **structured, intent-driven interactions with predefined conversational paths.** They perform best in scenarios where interactions are predictable and can be mapped to specific Intents. They are ideal for customer service applications with clear, repetitive workflows, such as order tracking, basic support requests, or information retrieval. In this type, the system accurately identifies user intents and matches them to preconfigured responses. It works best with a well-defined set of user goals and when a reliable, consistent interaction model is required. It can be compared to an **advanced flowchart** that efficiently routes each request to the most appropriate predefined response. {% hint style="info" %} This type provides strong control and reliability, with minimal variability in outcomes. {% endhint %} ## Composite (Hybrid) type The Composite types combines structured intent recognition and dynamic problem-solving by combining NLU and Agentic approaches. **It allows both deterministic and dynamic handling** within the same system, enabling a controlled transition between types: * User input is first matched against predefined intents; * If a match **is found:** Then it will be handled through predefined NLU flows; * If **no match** is found: Then the system can transfer execution to an Agent. ### Composite types have two approachs: #### Composite (NLU - first) In this type, the system **prioritizes intent recognition while maintaining the ability to leverage AI agents for more complex tasks.** \ \ A Supervisor agent first attempts to match user inputs to predefined intents, ensuring efficient handling of common, predictable interactions. When an intent cannot be directly matched or requires more nuanced processing, specialized AI agents are activated to provide more flexible, context-aware responses. This approach is perfect for organizations wanting to maintain the reliability of intent-based systems while introducing adaptability for edge cases. Agents are not directly selectable in this type. They can only be invoked through an explicit [**Transfer cell** ](/user-guide/build-dialogs/dialog-cells/transfer.md) within an NLU flow.

Transfer cell within a NLU-First workspace

{% hint style="info" %} This is a good option if you want to migrate an Intent-based agent to Agentics types. {% endhint %} #### **Composite (Agentic-first)** Conversely, this configuration **prioritizes AI agent capabilities while retaining some intent-based routing mechanisms.** The system first leverages the dynamic problem-solving capabilities of AI agents, using intents as a secondary mechanism, conserving specific and/or deterministic use cases. This type is ideal for complex environments where user interactions are diverse and unpredictable, but some level of structured routing can still enhance efficiency. {% hint style="info" %} It allows for more creative and adaptive responses while maintaining a soft structure through intent-based insights. {% endhint %} ## Agentic type This Agentic type enables fully **dynamic**, **context-driven execution through AI Agents coordinated by the Supervisor**, where: * Requests are evaluated and routed dynamically; * Agents execute tasks using Actions, Tools, and structured capabilities; * Planning and execution can adapt based on context. #### This governance type is suited for: * Complex problem-solving; * Multi-step workflows; * High-variability scenarios. The Agentic type (LLM-based) represents a more dynamic and adaptive approach to interactions. This approach enables complex problem-solving, creative reasoning, and context-aware responses. {% hint style="info" %} It's particularly suitable for scenarios requiring nuanced understanding, open-ended problem-solving, or interactions that cannot be easily predefined. {% endhint %} ## Types compatibility After creating your project, some restrictions for changing the governance type apply:
--- # Agent Instructions: 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: ``` GET https://docs.conversational-ai.syntphony.com/user-guide/ai-agents/governance-types.md?ask= ``` The question should be specific, self-contained, and written in natural language. 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.