Reference
AI & RAG Glossary
16 key terms explained — from embeddings and vector databases to prompt engineering and CSAT.
AI & RAG Fundamentals
RAG (Retrieval-Augmented Generation)
Retrieval-Augmented Generation (RAG) is an AI architecture that combines information retrieval with text generation. Instead of relying solely on training data, a RAG system first retrieves relevant documents or knowledge from a database, then feeds them to a language model to generate accurate, context-aware answers. This enables AI chatbots to provide factual, up-to-date responses grounded in your own content.
Large Language Model (LLM)
A Large Language Model (LLM) is a deep learning model trained on vast amounts of text data to understand and generate human-like language. Examples include GPT-4, Claude, and Llama. In customer support, LLMs power the natural conversation abilities of AI chatbots, enabling them to understand complex queries, maintain context, and generate helpful responses.
Embedding
An embedding is a numerical vector representation of text that captures its semantic meaning. Embeddings allow AI systems to measure the similarity between pieces of text — for example, matching a customer question to the most relevant knowledge base article. They are a core component of RAG systems, enabling fast and accurate document retrieval.
Vector Database
A vector database stores and indexes embeddings for fast similarity search. When a customer asks a question, the AI converts it into an embedding and searches the vector database for the most similar content. This enables real-time retrieval of relevant knowledge, making RAG-powered chatbots fast and accurate even with large knowledge bases.
Hallucination
In AI, hallucination refers to when a language model generates confidently incorrect or fabricated information. RAG systems significantly reduce hallucinations by grounding responses in retrieved knowledge rather than relying solely on the model's training data. This is why RAG-powered chatbots are preferred for customer support and other accuracy-critical applications.
Fine-Tuning
Fine-tuning is the process of further training a pre-trained LLM on a specific dataset to adapt it for particular tasks or domains. While fine-tuning can improve performance on narrow tasks, RAG is often preferred for customer support because it allows knowledge updates without retraining the model.
Prompt Engineering
Prompt engineering is the practice of designing input prompts to guide LLMs toward desired outputs. Effective prompts include clear instructions, context, and examples. In a RAG chatbot, the system prompt defines the bot's personality, behavior rules, and how it should use retrieved knowledge to answer customer questions.
Context Window
The context window is the maximum amount of text (measured in tokens) an LLM can process at once. It includes the prompt, retrieved documents, and conversation history. A larger context window allows the AI to consider more information when generating responses, leading to more coherent and accurate answers in customer support conversations.
Semantic Search
Semantic search understands the meaning and intent behind a query rather than just matching keywords. RAG-powered chatbots use semantic search to find relevant information even when the customer's phrasing doesn't exactly match the knowledge base content, resulting in more accurate and helpful responses.
Support & Operations
CSAT (Customer Satisfaction Score)
CSAT is a metric that measures how satisfied customers are with a support interaction, typically collected through post-conversation surveys. AI chatbots can improve CSAT by providing instant, accurate answers 24/7, reducing wait times, and escalating complex issues to human agents when needed.
First Response Time (FRT)
First Response Time is the average time it takes for a customer to receive their first reply after submitting a support request. AI chatbots dramatically reduce FRT from hours or minutes to instant responses, improving customer experience and satisfaction.
Ticket Deflection
Ticket deflection is the practice of resolving customer issues through self-service channels (like AI chatbots and knowledge bases) instead of creating support tickets. High deflection rates reduce support costs, free up human agents for complex issues, and provide faster resolutions for customers.
Knowledge Base
A knowledge base is a centralized repository of information — articles, FAQs, documentation, policies — that an AI chatbot uses to answer customer questions. In a RAG system, the knowledge base is vectorized and indexed so the AI can retrieve the most relevant information for each query in real time.
Omnichannel Support
Omnichannel support provides a consistent customer experience across multiple communication channels — website chat, WhatsApp, Slack, email, social media, and phone. UnifiedRAG enables omnichannel support by integrating with all major messaging platforms while maintaining conversation history and context across channels.
Technical
API (Application Programming Interface)
An API allows different software systems to communicate with each other. UnifiedRAG provides APIs for custom integrations, enabling businesses to connect their AI chatbot with internal systems, CRMs, and other tools. APIs are essential for building custom workflows beyond native integrations.
Webhook
A webhook is an automated HTTP callback that sends real-time data from one system to another when a specific event occurs. UnifiedRAG supports webhooks to trigger actions in other tools — such as creating a ticket, sending a notification, or updating a CRM record — based on chatbot interactions.
FAQ
Frequently asked questions
What is RAG in AI?
Retrieval-Augmented Generation (RAG) is an AI technique that retrieves relevant information from a knowledge source and uses it to generate more accurate, context-aware responses.
What is an AI chatbot?
An AI chatbot is a software application that uses artificial intelligence to understand user questions and provide automated, conversational responses.
What is an LLM?
A Large Language Model (LLM) is an AI model trained on large amounts of text to understand and generate human-like language.
What is Retrieval-Augmented Generation?
Retrieval-Augmented Generation combines information retrieval with generative AI so that an AI system can use relevant external information when generating responses.
What is an AI agent?
An AI agent is a system that can understand goals, make decisions, use tools, and perform tasks with limited human intervention.
What is AI customer support?
AI customer support uses artificial intelligence to answer customer questions, retrieve information, automate support tasks, and assist human support teams.
Build an AI Chatbot for Your Website in Minutes
Train your AI agent in minutes. Deploy to your site with one line of code. Watch deflection rates climb from day one.