What is Knowledge Base?
A curated, indexed collection of an organization's knowledge — docs, wikis, tickets, repos — that an AI assistant retrieves from when answering questions.
In an AI context, a knowledge base is more than a folder of articles: it is the retrieval boundary. The assistant can answer from what is inside it and must decline what is not — which makes deciding what belongs in a knowledge base the central act of governing an AI assistant.
Modern knowledge bases aggregate many sources: a docs website, GitHub READMEs, Notion pages, Confluence spaces, help-desk articles, Slack threads, uploaded PDFs. Ingestion pipelines normalize these formats into one searchable index and keep them synchronized as the sources change.
Structure within a knowledge base — permissions, document visibility, groupings by product or version — determines who can retrieve what, and lets one platform serve public customers and internal teams safely.
How BeforeQuery uses this
The knowledge base is BeforeQuery's core unit: connect any of 19 source types, and content is crawled, normalized, chunked, embedded, and kept fresh on automatic refresh schedules. Per-knowledge-base permissions, restricted documents, and source groups control exactly who retrieves what, across every channel from widget to MCP.
Related terms
Chunking
Splitting documents into smaller passages before embedding, so retrieval can return the precise section that answers a question rather than a whole page.
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.
Deflection Rate
The percentage of support questions resolved by self-service — typically an AI assistant — without creating a ticket or reaching a human agent.
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