> For the complete documentation index, see [llms.txt](https://docs-conversational-ai.syntphony.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs-conversational-ai.syntphony.com/studio/ai-agents.md). # AI Agents Build conversational experiences with specialized AI Agents coordinated through intelligent and governed orchestration. ## Overview **Agentics** introduces a more flexible approach to conversational AI, combining **LLM-based reasoning with governed decision logic**. Instead of relying only on predefined paths and intent-based rules, Agentic architectures can interpret requests, determine the appropriate handling path, and delegate execution to specialized capabilities. This enables more contextual conversations while maintaining control over how requests are routed and executed. Interactions are evaluated, classified, and routed through a controlled orchestration model before execution begins. In this model, intelligence exists not only in response generation, but also in how the system determines which component should handle each request. ## How Agentics works in Syntphony CAI In an Agentics governance, a **Project** combines a **Supervisor** with one or more specialized AI Agents. The typical orchestration follows this structure: **User request → Supervisor → Specialized AI Agent → Skills → Response** The **Supervisor** evaluates the user's request and determines the appropriate handling path. Once an AI Agent is selected, it becomes responsible for executing the task within its defined scope. This creates a clear separation of responsibilities:

Component	Responsibility
Supervisor	Orchestrates interactions and determines how requests should be handled.
AI Agent	Executes specialized tasks within its defined scope.
Skills	Provide the capabilities an AI Agent can use to fulfill a request.

## What is an AI Agent? An **AI Agent** is a specialized component designed to handle a defined set of responsibilities within a conversational experience. Each AI Agent operates within a specific scope and uses its **Role,** **Goal, Instructions, and Skills** to understand requests, generate responses, retrieve information, or execute actions. Instead of concentrating every capability in a single assistant, Syntphony CAI allows you to distribute responsibilities across specialized AI Agents. This creates a model similar to a team of specialists: **each Agent focuses on what it does best, while orchestration determines when its expertise is required.**

--- # 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 by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs-conversational-ai.syntphony.com/studio/ai-agents.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. 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.