What is Citations?
Links from an AI answer back to the specific source documents used to generate it, allowing users to verify every claim.
A citation is the difference between an answer you can trust and an answer you have to take on faith. Because RAG systems know exactly which retrieved passages informed a response, they can attach the source URL, title, and excerpt for each — something a bare LLM cannot honestly do.
Citations serve three audiences: users, who can verify claims with one click; teams, who can audit what the AI told a customer and why; and content owners, who see which documents actually carry the load.
Well-implemented citations are structured data, not just markdown links — so every channel (widgets, bots, APIs) can render them natively.
How BeforeQuery uses this
Every BeforeQuery answer includes a structured citations array with URL, title, and excerpt per source, rendered across the widget, Slack/Discord/Teams bots, the Ask portal, the public API, and MCP responses. Conversation history and traces preserve citations for audit.
Related terms
RAG (Retrieval-Augmented Generation)
An AI architecture that retrieves relevant documents from a trusted knowledge source and passes them to a language model, so answers are grounded in real content instead of the model's training data.
Hallucination
When a language model generates fluent, confident content that is factually wrong or entirely invented.
Eval (LLM Evaluation)
A systematic method for measuring the quality of AI-generated answers — often using a second model as a judge — so quality is tracked rather than assumed.
From definition to deployment
Connect a knowledge source and see cited AI answers on your own content in minutes — free, no credit card required.
Get Started Free