Grounding
Grounding means tying an AI model's answer to a specific, trusted source of information, such as retrieved documents, a database or search results, so its claims can be traced and checked. A grounded answer says only what its sources support, and ideally shows which source each part came from.
Example
A grounded chatbot answering "Do you ship to Canada?" quotes the shipping page and links to it, instead of answering from general knowledge about online stores.
Why it matters for a website chatbot
Grounding is the difference between a chatbot that knows your business and one that knows the internet. ChatBento grounds every answer in passages retrieved from your content and shows links to the pages it used, so visitors and you can check where an answer came from.
See it in practice: Pre-sales questions
Related terms
- HallucinationA hallucination is an output from an AI model that sounds confident and plausible but is false or unsupported by its sources, such as an invented fact, quote, price, policy or link. It happens because language models generate likely-sounding text and have no built-in way to know when they lack information.
- Retrieval-augmented generation (RAG)Retrieval-augmented generation (RAG) is a technique in which an AI system first retrieves relevant passages from a chosen set of documents, then gives them to a language model to write its answer. It lets the model answer from current, specific information it was never trained on, and makes answers easier to check.
- Knowledge baseA knowledge base is an organized collection of information, such as help articles, policies, product details and answers to common questions, that people or software can search. In AI chatbots, the knowledge base is the content the chatbot is allowed to answer from, usually built from a company's website, documents and written Q&As.
- GuardrailsGuardrails are rules and checks placed around an AI system to keep its behavior within safe, intended limits. They can restrict topics, block harmful or off-brand output, require answers to come from approved sources, filter inputs for attacks, and send uncertain or sensitive cases to a person.