Use Cases/Documentation

Discover what your docs are missing

Every unanswered question becomes a prioritized docs backlog.

The pain

You do not know what your docs are missing until angry tickets tell you. Doc planning runs on gut feel, and writers spend time polishing pages nobody needs while high-demand topics stay unwritten.

How BeforeQuery solves it

BeforeQuery's gap analytics log every question the AI could not answer confidently, clustered by topic and ranked by frequency. Your docs backlog becomes data-driven: write the page that 40 people asked for last week, then watch the gap disappear from the report.

How it works

  1. 1Deploy the assistant on your docs, widget, or bots — every question is analyzed.
  2. 2Questions the AI could not answer confidently are logged as knowledge gaps.
  3. 3Gaps are clustered by topic and ranked by frequency in analytics.
  4. 4Your docs backlog becomes: write the page the data says people need.

What you get

Replace gut-feel doc planning with a data-driven backlog.
See the questions users actually ask, in their own words.
Prioritize by frequency — write the page 40 people asked for, not the one nobody did.
Verify impact by watching a gap disappear from the report after you ship the page.

Features that make it work

Knowledge gap analytics
Question clustering
Frequency ranking
Workspace analytics overview

Frequently asked questions

What counts as a knowledge gap?

A question the AI could not answer with confidence from your indexed content. Gaps are captured with the question text, clustered by topic, and ranked by how often they recur.

Can gaps turn into docs automatically?

Doc proposal scans draft new or updated pages to close detected gaps; your team reviews and accepts or dismisses each proposal — AI drafts, humans decide.

Where do I see gaps across the whole workspace?

The workspace analytics overview includes a gaps summary alongside questions per week, top sources, and top languages; per-project gap analytics give the detailed clustered view.

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.

Ready to discover what your docs are missing?

Connect your knowledge sources and see cited AI answers in minutes — free, no credit card required.

Get Started Free