Glossary
What is RAG?
Letting an AI answer from your own documents.
RAG (retrieval-augmented generation): definition
RAG retrieves relevant passages from a knowledge base and gives them to the model, so answers are grounded in your approved content.
RAG: questions and answers
What is RAG?
RAG retrieves relevant passages from a knowledge base and gives them to the model, so answers are grounded in your approved content.
What does RAG mean in simple terms?
Letting an AI answer from your own documents.
What is LLM?
Large language models such as Claude, GPT and Gemini predict and generate text, powering chatbots, agents and writing tools.
What is AI agent?
An AI agent combines a language model with access to tools and data, so it can complete tasks such as booking appointments within rules you set.
What is an Arabic AI chatbot?
A chatbot powered by a language model that understands and replies in Arabic and English, answers from your approved information and hands over to your team when needed.
Can the AI agent work on WhatsApp?
Yes, through the WhatsApp Business API, as well as on your website, email and phone.
How long does it take to launch an AI agent?
A focused first agent usually takes two to five weeks, including testing with real, anonymised conversations.
How much does an AI agent cost to run?
Running costs are AI model usage, hosting and messaging fees. Our AI token cost calculator estimates model costs from your volumes.
Which tools do you use for automation?
n8n (often self-hosted), Make, and custom code, chosen to fit the tools you already use and your data rules.
Can the agent connect to my CRM and calendar?
Yes. Agents read and write to CRMs, calendars, booking systems and accounting tools through their APIs.
Related terms
Related guides
Need help with RAG?
AI agents for WhatsApp and email, and workflow automation.