Skip to content
BizQuery BizQuery BizQuery

Getting started

You can be asking grounded questions of your own documents in a few minutes.

1. Create a library

A library is a named collection of documents — a knowledge base the AI can search. Where you create one depends on your account:

  • In an organization, libraries live inside Projects. Open Projects, open (or create) a project, and add a library from its Libraries tab. A project’s libraries are reachable by its members; an admin can also keep a library org‑wide.
  • On an individual account, open Knowledge and create a library — it’s private to you.

Give it a name (e.g. “Company policies”).

2. Import a document

Open the library (or the project’s Documents tab) and drag a file onto it. PDF, Word, Excel, PowerPoint, CSV, Markdown, and text are supported. BizQuery then:

  • extracts the text (with OCR fallback for scanned pages),
  • splits it into passages and builds embeddings for search,
  • gives it a clean, standardized title and assigns tags automatically.

You can watch progress and adjust a document’s title or tags at any time.

3. Ask a grounded question

Open Ask, make sure you’re working in the right project (or All sources), and ask. The advisor searches your knowledge, answers in plain language, and shows the evidence — the exact passages it used — so you can verify every claim.

That’s the core loop. From here:

  • Organize knowledge and access with Projects.
  • Turn a library into a reusable Advisor with a fixed role and tone.
  • Pose a goal in Decisions to orchestrate several advisors into an approved plan, or request a single advisor’s recommendation when an answer is a decision that needs human sign‑off.
  • Turn a prompt or a file into a document with Skills.
  • Drive all of this from the API.