Definitions of key terms used in the PolyAI Agent Studio.
Welcome to the PolyAI glossary.
This page explains some of the key terms, acronyms, and concepts used across our platform.
A PolyAI AI-driven voice assistant that interacts with customers in real-time via speech or text. Agents handle customer conversations autonomously while integrating with external data sources.
The primary interface for designing, configuring, and deploying AI agents. Agent Studio serves both builders (creating AI logic) and managers (monitoring performance and analytics).
Full article: Conversation review. A manual tag applied during Conversation Review to highlight issues like incorrect transcriptions or missing knowledge base topics.
The percentage of calls fully handled by the agent without requiring a human handoff.
Structured data about a conversation, including duration, start time, and associated agent variant.
A tool within Conversation Review that shows which flows, function calls, and knowledge base topics were activated during a call.
Full article: End function
A function that finalizes an interaction, used when an AI agent has completed its task. It can:
Full article: Flows
Also known as Talk Tracks, flows use conversation logic system that determines how an AI agent guides a user through an interaction. Flows define:
Full article: Function
A reusable backend operation that an AI agent can execute during a conversation. Functions allow agents to:
A function call is when an agent invokes a function to retrieve information, or perform an action in real time.
Full article: Rules
Predefined behavior constraints applied across all agent interactions to ensure:
Full article: Call handoff
The process of transferring a user from an AI agent to a human agent. Handoffs can be:
Full article: Knowledge base
A structured repository of predefined responses and business-specific information that AI agents use to generate accurate answers.
Refers to the deployment stage of a project, such as sandbox
, pre-release
, or live
. Used in API queries and analytics.
The ability to customize agent responses based on location, using variant management.
PolyAI’s proprietary model, optimized for real-time voice interactions. Offers low-latency responses with high alignment to voice assistant use cases.
Custom rules used to adjust how the agent pronounces specific terms via IPA and regex-based substitution.
See: Containment Rate, Conversation Metadata, Safety Dashboard
Full article: RAG
A method where the AI first retrieves relevant knowledge from the KB before generating a response, ensuring more accurate, context-aware replies.
Full article: Response control
A system that modifies how AI agents respond in different scenarios. Includes:
A specialized dashboard to monitor flagged content, risky user utterances, and the performance of safety filters.
Sensitive credentials or tokens that can be securely stored and accessed by the agent for integrations.
Full article: Start function
A function triggered at the beginning of an interaction, often used to:
See flows.
Full article: Speech recognition
A feature that enables users to edit AI-generated conversation transcripts, improving:
Full article: Flows
A moment in the conversation where the agent checks whether the information provided by the user is complete, accurate, or matches expected criteria.
Validation may include:
Validation ensures the agent gathers usable information before continuing with a task or triggering a function.
Full article: Variables
Variables are used to store and retrieve values during a conversation. In PolyAI, they are accessed through the conv.state
object, which behaves like a dictionary. Variables allow agents to track context, user inputs, flags, counters, and other custom values needed for decision-making across turns.
Example:
All variables persist for the duration of a single conversation and are cleared at the end unless explicitly saved elsewhere.
Full article: Variant management
A tool for testing multiple conversational styles within an AI agent, allowing:
Fields used in API filters and analytics to identify and segment conversations by specific agent variant versions.
For any questions or to suggest additions, contact platform-support@poly-ai.com.
Definitions of key terms used in the PolyAI Agent Studio.
Welcome to the PolyAI glossary.
This page explains some of the key terms, acronyms, and concepts used across our platform.
A PolyAI AI-driven voice assistant that interacts with customers in real-time via speech or text. Agents handle customer conversations autonomously while integrating with external data sources.
The primary interface for designing, configuring, and deploying AI agents. Agent Studio serves both builders (creating AI logic) and managers (monitoring performance and analytics).
Full article: Conversation review. A manual tag applied during Conversation Review to highlight issues like incorrect transcriptions or missing knowledge base topics.
The percentage of calls fully handled by the agent without requiring a human handoff.
Structured data about a conversation, including duration, start time, and associated agent variant.
A tool within Conversation Review that shows which flows, function calls, and knowledge base topics were activated during a call.
Full article: End function
A function that finalizes an interaction, used when an AI agent has completed its task. It can:
Full article: Flows
Also known as Talk Tracks, flows use conversation logic system that determines how an AI agent guides a user through an interaction. Flows define:
Full article: Function
A reusable backend operation that an AI agent can execute during a conversation. Functions allow agents to:
A function call is when an agent invokes a function to retrieve information, or perform an action in real time.
Full article: Rules
Predefined behavior constraints applied across all agent interactions to ensure:
Full article: Call handoff
The process of transferring a user from an AI agent to a human agent. Handoffs can be:
Full article: Knowledge base
A structured repository of predefined responses and business-specific information that AI agents use to generate accurate answers.
Refers to the deployment stage of a project, such as sandbox
, pre-release
, or live
. Used in API queries and analytics.
The ability to customize agent responses based on location, using variant management.
PolyAI’s proprietary model, optimized for real-time voice interactions. Offers low-latency responses with high alignment to voice assistant use cases.
Custom rules used to adjust how the agent pronounces specific terms via IPA and regex-based substitution.
See: Containment Rate, Conversation Metadata, Safety Dashboard
Full article: RAG
A method where the AI first retrieves relevant knowledge from the KB before generating a response, ensuring more accurate, context-aware replies.
Full article: Response control
A system that modifies how AI agents respond in different scenarios. Includes:
A specialized dashboard to monitor flagged content, risky user utterances, and the performance of safety filters.
Sensitive credentials or tokens that can be securely stored and accessed by the agent for integrations.
Full article: Start function
A function triggered at the beginning of an interaction, often used to:
See flows.
Full article: Speech recognition
A feature that enables users to edit AI-generated conversation transcripts, improving:
Full article: Flows
A moment in the conversation where the agent checks whether the information provided by the user is complete, accurate, or matches expected criteria.
Validation may include:
Validation ensures the agent gathers usable information before continuing with a task or triggering a function.
Full article: Variables
Variables are used to store and retrieve values during a conversation. In PolyAI, they are accessed through the conv.state
object, which behaves like a dictionary. Variables allow agents to track context, user inputs, flags, counters, and other custom values needed for decision-making across turns.
Example:
All variables persist for the duration of a single conversation and are cleared at the end unless explicitly saved elsewhere.
Full article: Variant management
A tool for testing multiple conversational styles within an AI agent, allowing:
Fields used in API filters and analytics to identify and segment conversations by specific agent variant versions.
For any questions or to suggest additions, contact platform-support@poly-ai.com.