- Agentic AI
- AI that doesn't just answer questions but takes actions on your behalf — booking appointments, sending quotes, updating records — following rules you set. This is the kind we build.
- Large Language Model (LLM)
- The type of AI behind tools like ChatGPT, Claude and Gemini. It predicts text, which lets it write, summarise, answer questions and hold a conversation.
- Generative Engine Optimization (GEO)
- Optimising your website and information so AI assistants like ChatGPT and Gemini mention and recommend your business when people ask them for suggestions.
- Answer Engine Optimization (AEO)
- Structuring your content so it can be used directly as the answer in AI results, voice assistants and featured snippets — not just as a blue link.
- Retrieval-Augmented Generation (RAG)
- A technique where an AI looks up real information from a trusted source before answering, which reduces made-up answers and keeps replies current.
- Prompt
- The instruction you give an AI. A clear, specific prompt with context and examples usually produces a far better result than a vague one.
- Hallucination
- When an AI states something false as if it were true. It happens because the model predicts plausible text, so anything business-critical should be checked or grounded in real data.
- Schema markup (structured data)
- Hidden code on a web page that describes what the page is about in a format search engines and AI can read reliably — helping them show and cite you correctly.
- Token
- The unit AI models measure text in — roughly three-quarters of a word. Most AI pricing and length limits are counted in tokens.
- Fine-tuning
- Further training a general AI model on your own examples so it responds more like your business. For most small businesses, good prompting or RAG is cheaper and usually enough.
- Chatbot vs AI receptionist
- A basic chatbot follows fixed scripts. An AI receptionist understands natural language, knows your prices and availability, and can actually book or route the enquiry.
- Natural Language Processing (NLP)
- The field of AI focused on understanding and generating human language — the foundation of chatbots, transcription and text analysis.
- API
- A way for two pieces of software to talk to each other. AI features are usually added to a business's tools by connecting to an AI provider's API.
- Workflow automation
- Chaining steps together so they run without manual work — for example, a new enquiry automatically creating a quote, a calendar hold and a follow-up message.
- Knowledge base
- The trusted collection of information (prices, policies, FAQs) an AI assistant is given so its answers are accurate and specific to your business.
- Context window
- How much text an AI can consider at once. A bigger context window lets it handle longer documents or conversations without losing track.
- Multimodal AI
- AI that can work with more than just text — also images, audio or video. Useful for things like reading a photo of a document or transcribing a call.
- Vector / embedding
- A way of turning text into numbers so AI can find things by meaning rather than exact words. It's what powers smart search and RAG behind the scenes.
No term matches that search. Try another word.
