> 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/getting-started/glossary.md).

# Glossary

Find definitions for the key terms, concepts, features, and resources used throughout Syntphony Conversational AI. Use this glossary as a quick reference to better understand the platform.

<table data-search="false"><thead><tr><th width="183.62579345703125">Term</th><th>Definition</th></tr></thead><tbody><tr><td><strong>Action</strong></td><td>Tasks that an AI Agent can execute to fulfill a user request. An Action defines the required inputs, properties and execution logic and can use Services to interact with external systems.</td></tr><tr><td><strong>Admin</strong></td><td>User role with full access to resources within assigned Organizations. Admins can manage users and permissions, grant Environment access, and enable or disable additional platform features.</td></tr><tr><td><strong>AI Agent</strong></td><td>Specialized agents designed to handle specific user requests using defined Roles, Goals, Instructions, Skills, and other configured resources. They can be used according to the Project’s Agentic Governance configuration.</td></tr><tr><td><strong>AI Feature</strong></td><td>Generative AI capabilities available in Syntphony CAI to enhance conversational experiences, including Knowledge AI, Prompt Cell, Rephrase Answer, and Multilingual capabilities.</td></tr><tr><td><strong>API</strong></td><td>Interface that enables Syntphony CAI and other software applications or services to communicate, exchange data, and access functionality programmatically.</td></tr><tr><td><strong>Bulk Training</strong></td><td>Process for importing multiple training Examples or Intents at once, reducing the effort required to configure NLU resources.</td></tr><tr><td><strong>Cell</strong></td><td>Visual flow element used to build and manage conversational flows in Workspace.</td></tr><tr><td><strong>Channel</strong></td><td>Communication channel through which users interact with a conversational project, such as web, messaging, or telephony.</td></tr><tr><td><strong>Cockpit</strong></td><td>Syntphony Conversational AI platform where users access and manage Organizations, Environments, Projects, and other available resources and features.</td></tr><tr><td><strong>Cognitive Engine</strong></td><td>Natural Language Processing engine used to interpret user input and support Intent recognition.</td></tr><tr><td><strong>Collection</strong></td><td>Topic-based repositories that organize related Sources and Questions within Knowledge. Each Collection defines a focused search scope.</td></tr><tr><td><strong>CTA</strong></td><td>A link, button, or other interactive element that encourages a specific action.</td></tr><tr><td><strong>Disambiguation</strong></td><td>Resource used when building the Knowledge Base to resolve ambiguities or request additional information during an interaction.</td></tr><tr><td><strong>Editor</strong></td><td>User role with access to all resources except critical actions such as creating or deleting conversational projects and enabling features that may impact costs.</td></tr><tr><td><strong>Entity</strong></td><td>Specific information associated with an Intent that can modify or complement it, such as an adjective, noun, product, or service.</td></tr><tr><td><strong>Environment</strong></td><td>Structure within an Organization used to group and manage Projects, access permissions, configurations, and shared resources.</td></tr><tr><td><strong>Evaluable Answer</strong></td><td>Answer that can be evaluated by the user.</td></tr><tr><td><strong>EVG</strong></td><td>Voice Gateway used to connect a conversational project to a contact center or other voice channels.</td></tr><tr><td><strong>Example</strong></td><td>Sentence or phrase representing how a user may express an Intent or ask about a specific topic. Examples are used in both NLU Intents and Knowledge AI Questions.</td></tr><tr><td><strong>Fallback</strong></td><td>Controlled mechanism activated when a request falls outside the Project’s defined capabilities. The Supervisor triggers Fallback when no rule, AI Agent, or Flow can handle the interaction.</td></tr><tr><td><strong>FAQs</strong></td><td>Documents and repositories that provide answers to common questions about Syntphony.</td></tr><tr><td><strong>Generative AI</strong></td><td>AI system capable of generating multimedia content in response to prompts expressed in natural language.</td></tr><tr><td><strong>Goal</strong></td><td>Primary objective of the Supervisor or an AI Agent. The Supervisor Goal is predefined and governs request routing, while the AI Agent Goal defines what the AI Agent is responsible for achieving.</td></tr><tr><td><strong>Guardrails</strong></td><td>Protective layer that reinforces behavioral boundaries and helps keep AI Agent and Flow behavior aligned with Project guidelines without altering the Supervisor’s orchestration rules.</td></tr><tr><td><strong>Handoff</strong></td><td>Process in which a human agent takes over a conversation, usually when the Conversational Project or the AI Agent does not understand the user or the issue is not covered by the Knowledge Base.</td></tr><tr><td><strong>Insights</strong></td><td>Area for monitoring Conversational Project performance through key metrics.</td></tr><tr><td><strong>Instructions</strong></td><td>Behavioral guidance that defines how the Supervisor or an AI Agent operates. Instructions guide working methods, response consistency, and interaction handling.</td></tr><tr><td><strong>Integration</strong></td><td>Connection between Syntphony CAI and external or supported technologies.</td></tr><tr><td><strong>Intent</strong></td><td>Component of NLU Flows used to recognize the purpose of user input and determine the appropriate conversational path.</td></tr><tr><td><strong>Jump Flow</strong></td><td>Reusable Flow that can be called from another Flow through a Jump cell. After completion, the conversation returns to the original Flow by default.</td></tr><tr><td><strong>Knowledge AI</strong></td><td>Feature that interprets user questions and generates context-sensitive answers from Sources uploaded to the platform.</td></tr><tr><td><strong>Knowledge Base</strong></td><td>Set of AI Agents, NLU Flows, Collections, Sources, and Services in a Conversational Project.</td></tr><tr><td><strong>LLM</strong></td><td>A machine learning model that can understand and generate human-language content based on a large pre-trained data set.</td></tr><tr><td><strong>Manager</strong></td><td>Human role with access to all resources except user management. Permissions include managing Environments, Channels, and Conversational Projects; enabling Generative AI features; accessing Analytics dashboards; and importing or exporting Conversational Projects.</td></tr><tr><td><strong>Masking</strong></td><td>Process of obscuring or replacing sensitive personal data to protect individual privacy.</td></tr><tr><td><strong>MCP</strong></td><td>Integration that connects AI Agents to external tools through the Model Context Protocol (MCP), enabling them to retrieve information, perform actions, and execute workflows in external systems.</td></tr><tr><td><strong>Metric</strong></td><td>Quantitative measurements used to monitor and analyze Conversational Project performance.</td></tr><tr><td><strong>NLU Flow</strong></td><td>Structured, Intent-driven Flows that route user requests through predefined conversational paths. They are designed for predictable interactions that can be mapped to specific Intents and preconfigured responses.</td></tr><tr><td><strong>Not Expected Answer</strong></td><td>Fallback response triggered when the Conversational Project cannot understand the user’s context or Intent.</td></tr><tr><td><strong>Not Expected Flow</strong></td><td>Flow executed when the Conversational Project does not understand the user’s context. It is mandatory and cannot be deleted.</td></tr><tr><td><strong>Organization</strong></td><td>Top-level structure in Syntphony Conversational AI that contains Environments, which in turn contain Conversational Project and their associated resources.</td></tr><tr><td><strong>Parameter</strong></td><td>A reusable fixed value that centralizes configuration across an Environment or Project.</td></tr><tr><td><strong>Persona</strong></td><td>Configuration that defines how the Supervisor and AI Agents generate responses, including tone of voice, personality, and background.</td></tr><tr><td><strong>Project</strong></td><td>Core configuration that defines the conversational solution, including its Governance type, integrations, language, organizational context, and Persona.</td></tr><tr><td><strong>Prompt</strong></td><td>Input instruction provided to a Large Language Model (LLM) to define the task to perform and how the response should be generated.</td></tr><tr><td><strong>Property</strong></td><td>JSON code used as commands for voice agents in a technical text field.</td></tr><tr><td><strong>Question</strong></td><td>Knowledge resources that organize specific information into question-and-answer pairs, improving how the conversational project matches different user inquiries with relevant responses.</td></tr><tr><td><strong>Repository</strong></td><td>Location where Agents, NLU Flows, Cells, Parameters, Variables, Collections, and Trainings are stored.</td></tr><tr><td><strong>REST Connector</strong></td><td>Connector used to configure REST-based transactional services, including the request method, URL, headers, content type, authentication, request body, and expected output.</td></tr><tr><td><strong>Role</strong></td><td>Definition of the function and responsibilities of the Supervisor or an AI Agent. </td></tr><tr><td><strong>Skill</strong></td><td>Resources assigned to an AI Agent to define its capabilities and support its tasks.</td></tr><tr><td><strong>Source</strong></td><td>Knowledge resources added to a Collection to provide information for retrieval and content generation.</td></tr><tr><td><strong>SSML</strong></td><td>Speech Synthesis Markup Language. An XML-based markup language that provides annotations for speech synthesis applications.</td></tr><tr><td><strong>Supervisor</strong></td><td>Orchestration component that processes user requests according to the Project’s Governance type. It determines the appropriate next step, routes requests to an AI Agent or Flow, handles Fallback and chit-chat responses, clarifies ambiguous requests, and passes relevant conversation context to AI Agents.</td></tr><tr><td><strong>Syntphony NLP</strong></td><td>NTT DATA proprietary Natural Language Processing (NLP) engine.</td></tr><tr><td><strong>System Prompt</strong></td><td>A set of system-defined instructions and rules that guide the behavior, responsibilities, and interactions of the Supervisor or AI Agent.</td></tr><tr><td><strong>Test</strong></td><td>Process used to verify that the conversational project provides a response compatible with the expected Intent.</td></tr><tr><td><strong>Token</strong></td><td>Units of text processed by a language model. A token can represent a character, part of a word, a word, or another text segment depending on the model.</td></tr><tr><td><strong>Tool</strong></td><td>An MCP-enabled capability that allows an AI Agent to interact with external systems and services to retrieve data, perform functions, and execute workflows.</td></tr><tr><td><strong>Training</strong></td><td>Process that trains the conversational project to interpret user input and prepares the Knowledge Base for retrieving relevant information.</td></tr><tr><td><strong>Transactional Answer</strong></td><td>Answer that depends on information retrieved from an external source through an API.</td></tr><tr><td><strong>User</strong></td><td>Person interacting with the conversational project.</td></tr><tr><td><strong>User Journey Flow</strong></td><td>Dialog Flow used to build structured conversational experiences with Syntphony Conversational AI tools. It starts with an Intent cell created as new or selected from the existing Intent Repository.</td></tr><tr><td><strong>Value Range</strong></td><td>Configurable limits used by Syntphony CAI during execution, such as the amount of time a project waits for a Generative AI response or the number of tokens a supported model can use.</td></tr><tr><td><strong>Variable</strong></td><td>Runtime values stored in context that can change during conversation execution. Variables can retain, reuse, update, and pass information as the user interacts with the conversational project.</td></tr><tr><td><strong>Viewer</strong></td><td>User role with limited access, with permissions to view the project content and test dialogs.</td></tr><tr><td><strong>Webhook</strong></td><td>Mechanism that sends data between applications when a specified event occurs.</td></tr><tr><td><strong>Welcome Flow</strong></td><td>Initial Flow that starts the conversation and welcomes the user in the conversational project.</td></tr><tr><td><strong>Workspace</strong></td><td>Main canvas for creating dialogs and building the conversational project Knowledge Base.</td></tr><tr><td><strong>Zero-Shot LLM</strong></td><td>LLM-based model for classifying user input into Intents in real time. It requires minimal to no training Examples and uses Intent context to determine the most relevant match.</td></tr></tbody></table>


---

# 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/getting-started/glossary.md?ask=<question>&goal=<user_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.
