Onboard new engineers faster
A cited answer instead of 'ask in #engineering and wait'.
New engineers spend their first months asking questions that interrupt senior teammates: how does deploy work, where is the runbook, why is this service structured this way. The answers exist across wikis, READMEs, and old Slack threads — effectively unfindable.
BeforeQuery indexes your GitHub repos, Notion, Confluence, and internal docs into one internal Ask assistant. New engineers ask in the dashboard or in Slack and get cited answers from your actual runbooks and ADRs, with project permissions controlling exactly which knowledge each team member can query.
How it works
- 1Connect GitHub repos, Notion, Confluence, and internal docs into one internal project.
- 2Set per-project chat permissions so each team member queries only what they should.
- 3New engineers ask in the dashboard Ask section or in Slack.
- 4Answers cite the actual runbook, ADR, or README — not a paraphrase from memory.
What you get
Features that make it work
Frequently asked questions
Can it search across our wiki, repos, and docs at once?
Yes. GitHub, Notion, Confluence, Google Drive, SharePoint, and more sync into one embedded index per project, and a single question retrieves across all of them with per-source citations.
How is access controlled internally?
The internal Ask assistant is JWT-authenticated for workspace members. Owners can query all projects; members query only projects where chat permission is granted. Document-level visibility adds a public/restricted layer on top.
Does it work in Slack?
Yes — install the Slack bot and engineers ask in the channels where they already work, getting the same cited answers as the dashboard.
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
Unblock developers integrating your API
Answer auth, webhook, and SDK questions with code-aware AI.
Put your docs inside the IDE via MCP
Cursor, Claude, and other MCP clients answer from your docs.
Fix developer portal search
Hybrid semantic + keyword search that actually finds the page.
Ready to onboard new engineers faster?
Connect your knowledge sources and see cited AI answers in minutes — free, no credit card required.
Get Started Free