Glossary of AI, automation and GEO
The terms you will come across when hiring AI for your business, explained plainly and with an applied example. No technical fog.
GEO
- GEOGEO (Generative Engine Optimization) is the practice of optimising your content, schema and entity signals so that generative AI engines such as ChatGPT, Claude and Perplexity cite you when answering questions in your sector.
- llms.txtllms.txt is a plain-text file served from the root of your domain (https://tudominio.com/llms.txt). It holds a structured description of your business, products, pricing and policies, written specifically for generative AI engines (ChatGPT, Claude, Perplexity) to read. Think of it as the modern equivalent of robots.txt, but for LLMs.
Automation
- n8nn8n is an open-source automation platform that connects APIs, databases and SaaS tools through visual workflows. It lets you automate business processes without writing glue code, while keeping control of your data.
- AI AutomationAI automation combines traditional workflows (n8n, Zapier, Make) with large language models (LLMs) to carry out tasks that used to need human judgement: sorting messages, drafting replies, summarising documents, deciding escalation routes, creating content. It goes a step beyond the classic "if X happens, do Y".
Applied AI
- AI AgentAn AI agent is a software system that combines a large language model (LLM) with access to tools (APIs, databases, messaging) and a goal, so it can carry out tasks with minimal human involvement. The difference from a traditional chatbot is that an agent doesn't just chat: it acts.
- AI phone agentAn AI phone agent is a system that answers (or makes) phone calls using a natural synthesised voice, understands the caller in real time, holds a coherent conversation and carries out actions (booking appointments, logging leads, transferring calls). It works 24/7 and handles several calls at once with no queues.
- RAGRAG (Retrieval-Augmented Generation) is a technique that combines a language model (LLM) with a search system over your own knowledge base. Before answering, the system looks for relevant documents in your content (FAQs, products, pricing, contracts) and hands them to the LLM as context, so it answers from verifiable data rather than whatever the model remembers from its training.
- AI virtual receptionistAn AI virtual receptionist is a voice system that answers your business calls in a natural voice, trained on your business's real information: it answers questions, takes the caller's details, books appointments and hands over to a person when the conversation calls for it. Unlike an answerphone or a phone menu, it holds a real conversation, 24/7.
- AI customer serviceAI customer service is a layer of voice and chat systems, built on language models, that answers a business's calls and messages: it handles common questions, captures the details of interested customers, books appointments and hands over to a person anything that needs judgement. Its value isn't in replacing your team, but in covering what currently goes unanswered.
- Answering calls with AIAnswering calls with AI means connecting a business phone to a voice agent built on language models that picks up, talks in a natural voice, answers with the business's information, takes details and books appointments. It is set up with a dedicated number or by diverting calls from your current number, with no need to change provider.
- AI WhatsApp AgentAn AI agent for WhatsApp is an assistant connected to a business's WhatsApp (via the WhatsApp Business API) that replies to messages using a language model trained on that business's own information: it answers frequently asked questions, captures the details of interested customers and alerts the owner straight away. It replies 24/7, within seconds, with no rigid button templates.