This glossary provides definitions for technical terms, platform features, and healthcare-specific terminology you'll encounter while using the AlloMia Voice AI platform. Terms are organized alphabetically within categories for easy reference. If you encounter a term not listed here, please contact our support team for clarification.

AI Model

The underlying Large Language Model (e.g., GPT-4o) selected to power the agent's conversational intelligence and response generation.

Agent Template

Pre-configured starting points for creating a voice agent, tailored for specific use cases like Booking, FAQ, or a Blank slate for full customization.

API Integration

A connection between AlloMia and another software system (like an EHR or CRM) using APIs, often configured via 'Tools' to allow data exchange and automated actions.

Barge-in

A call handling setting that allows callers to interrupt the agent while it's speaking. If enabled, the agent will stop talking and listen to the caller's interruption.

Call Analytics

Metrics and insights derived from voice agent conversations, available on the 'Call Logs' page. Includes performance statistics, detected intent, sentiment analysis, and more.

Call Handoff

The process of transferring a conversation from an AI voice agent to a human staff member, configured via a forwarding phone number.

Call Log

A detailed record of a conversation between a caller and a voice agent, accessible on the 'Call Logs' page. Includes audio recording, full transcript, detected caller intent, and sentiment analysis.

Dial Keypad

A feature allowing the agent to interact with external phone systems (IVRs) or collect numeric input (like account numbers) via the caller's phone keypad. Configurable in agent settings.

End Call Function

A feature allowing the agent to politely conclude the call based on specific trigger phrases defined in its configuration or upon completing its task.

Intent Recognition

The process of determining the caller's goal or purpose (their 'intent'), such as scheduling an appointment, asking for information, or requesting a transfer.

Knowledge Base

The repository of documents (e.g., PDFs, text files) uploaded by the user, which the voice agent securely accesses to find answers and provide accurate information.

Max Tokens

A configuration setting that limits the maximum length (in tokens, roughly parts of words) of the agent's generated response in a single turn.

Personality Prompt

A detailed instruction provided during agent configuration that defines the agent's persona, speaking style, tone (e.g., empathetic, professional), and overall character.

Speed (Speech Rate)

A configurable setting (slider) that adjusts how quickly the voice agent speaks.

Stability (Voice)

A configurable setting (slider) that controls the amount of variation in the agent's voice delivery. Higher stability means more consistent tone; lower stability allows for more expression.

System Prompt

The core instruction given to the agent during configuration that defines its primary role, goals, constraints, and how it should generally behave or respond in conversations.

Temperature Setting

A configuration parameter (slider) that controls the randomness or creativity of the agent's responses. Higher values allow more creativity, while lower values make responses more focused and deterministic.

Tools (Custom API Actions)

Configurable integrations that allow the voice agent to perform specific actions by calling external APIs, such as checking appointment availability in a scheduling system or updating records in a CRM.

Voice Agent

An AI-powered conversational assistant designed to handle phone calls, understand caller requests, provide information, and perform tasks based on its configuration.

Voice Characteristics

The configurable aspects of a voice agent's speech, including the selected voice model (gender, accent), speaking rate ('Speed'), and delivery variation ('Stability').

API (Application Programming Interface)

A set of rules and protocols that allows different software applications to communicate and exchange data with each other. Used by AlloMia 'Tools'.

ASR (Automatic Speech Recognition)

The technology that converts spoken language into written text, enabling the agent to understand what the caller is saying.

LLM (Large Language Model)

A type of artificial intelligence model (like GPT-4o) trained on vast amounts of text data, capable of understanding and generating human-like language. The core 'brain' of the voice agent.

NLP (Natural Language Processing)

A field of AI focused on enabling computers to understand, interpret, and generate human language.

NLU (Natural Language Understanding)

A subset of NLP focused specifically on interpreting the meaning and intent behind human language, going beyond literal word recognition.

TTS (Text-to-Speech)

The technology that converts written text into audible speech, allowing the agent to 'speak' its responses.

EHR/EMR (Electronic Health/Medical Record)

Digital versions of a patient's medical history maintained by healthcare providers, which can be integrated with AlloMia for information access.

HIPAA (Health Insurance Portability and Accountability Act)

U.S. legislation that provides data privacy and security provisions for safeguarding medical information. AlloMia is designed with HIPAA compliance in mind.

PHI (Protected Health Information)

Any information about health status, provision of healthcare, or payment for healthcare that can be linked to an individual and is protected under HIPAA regulations.

Patient Portal

A secure online website that gives patients convenient, 24-hour access to personal health information, which can be referenced by AlloMia voice agents.

Practice Management System

Software used to manage the day-to-day operations of a medical practice, including scheduling, billing, and patient records.

Prior Authorization

The approval required from insurance companies before specific procedures or treatments, which voice agents can help facilitate.

Telehealth

The use of digital information and communication technologies to access healthcare services remotely, a process that can be supported and facilitated by AlloMia voice agents.

Triage

The process of determining the priority of patients' treatments based on the severity of their condition, which can be initially assessed by properly configured voice agents.

Average Handle Time (AHT)

The average duration of a complete interaction between a caller and a voice agent, from the start of the call to its conclusion. Visible in Call Logs.

Call Deflection Rate

Conceptually, the percentage of calls successfully handled by the voice agent without needing transfer to a human. May require manual analysis of Call Logs.

Conversation Flow

The path a conversation takes, including the sequence of interactions between the caller and the agent. Can be reviewed via the Call Log transcript.

First Call Resolution (FCR)

Conceptually, the percentage of calls where the caller's issue is resolved in the first interaction. May require manual analysis of Call Logs.

Resolution Rate

Similar to FCR, the percentage of caller inquiries successfully addressed by the voice agent. May require manual analysis.

Sentiment Analysis

The classification of the caller's emotional tone (e.g., positive, negative, neutral) during the conversation, displayed in the Call Log details.

Transfer Rate

The percentage of calls initiated by the agent that are transferred to the configured human handoff number.

Usage Minutes

The total duration of active conversation time for voice agents, often used as a primary metric for billing and subscription plans.