Make docs nobody reads actually useful
Turn a passive docs site into an interactive answer engine.
You invested heavily in documentation, but users skim, miss the relevant section, and file tickets anyway. Analytics show decent traffic and terrible outcomes: people land on the right page and still cannot extract the answer.
BeforeQuery turns your docs into an interactive assistant: users ask their exact question and get a synthesized answer with citations linking to the source pages. The docs keep doing the work — but now they meet users at their question instead of requiring users to find and parse the page themselves.
How it works
- 1Index your existing docs site — no rewriting or restructuring required.
- 2Add the widget so users can ask their exact question instead of hunting for the page.
- 3Answers are synthesized from the relevant sections, with citations linking back to them.
- 4Suggested questions guide users toward the topics your docs answer best.
What you get
Features that make it work
Frequently asked questions
Do I need to restructure my docs for AI?
No. BeforeQuery crawls your site as-is, normalizes HTML to markdown, strips navigation, and chunks content heading-aware. Well-structured docs help, but no rewrite is required to start.
Will this cannibalize my docs traffic?
Answers cite the source pages, so users click through to the docs for depth — the assistant routes people to the right page instead of replacing it. Citation analytics show which pages get used most.
What are suggested questions?
Per-project suggested questions shown in the widget to prompt users with high-value, answerable queries — useful for guiding first-time users into productive conversations.
How long does setup take?
Most teams are live the same day. You connect a source — a docs URL, GitHub repo, Notion workspace, or a file upload — and BeforeQuery crawls, normalizes, chunks, and embeds the content automatically. The website widget is a single script tag, and the Slack/Discord bots install in a few clicks. There is no model to fine-tune and no infrastructure to run.
Are answers backed by citations?
Yes. Every answer includes a structured citations list with the URL, title, and excerpt of each source used, and the answer text cites sources inline. Users can click through to verify any claim against the original document — which is what makes the answers trustworthy enough for support, sales, and internal use.
Is my content used to train AI models?
No. Your indexed content, embeddings, and conversations are isolated to your workspace and are only used to answer your own questions. Content is never shared across customers, and data is encrypted at rest and in transit. Enterprise plans add OIDC/SAML SSO, audit logs, and data-residency options.
Which knowledge sources can I connect?
18+ source types: websites, GitHub, GitLab, Notion, Confluence, Google Drive, SharePoint, Shopify, Zendesk, Jira, Linear, Salesforce, Slack, Discourse, Stack Overflow, YouTube, OpenAPI specs, and direct file uploads (PDF, Markdown, TXT, HTML). Sources sync on a schedule, and GitHub/GitLab can re-index automatically via webhooks on every push.
What happens when the AI is not confident in an answer?
Answers are confidence-scored. When retrieval confidence falls below your threshold, BeforeQuery returns a transparent, configurable fallback — typically pointing users to your support channel — instead of guessing. Those unanswered questions are logged in knowledge gap analytics so you can close the gap in your docs.
Related use cases
Discover what your docs are missing
Every unanswered question becomes a prioritized docs backlog.
Detect and fix stale documentation
AI-drafted doc updates from real user questions.
Measure documentation ROI
Show which docs answer questions and deflect tickets.
Ready to make docs nobody reads actually useful?
Connect your knowledge sources and see cited AI answers in minutes — free, no credit card required.
Get Started Free