End changelog and version confusion
"Did this behavior change in v3?" answered instantly.
Users on older SDK versions hit behavior that changed two releases ago, and your changelog is a wall of entries nobody reads. Support spends real time reconstructing "what changed between v2.3 and v3.1" from git history and release notes.
Index your changelog, migration guides, and release notes alongside your docs, and BeforeQuery answers version questions with citations to the exact release entry. Use source groups to separate versioned doc sets so retrieval can be scoped to the version the user is actually on.
How it works
- 1Index your changelog, release notes, and migration guides alongside your docs.
- 2Organize versioned doc sets into source groups within the project.
- 3Scope retrieval with group_ids so answers come from the version the user is on.
- 4Version questions get cited answers pointing to the exact release entry.
What you get
Features that make it work
Frequently asked questions
How do I keep versions from cross-contaminating answers?
Source groups partition knowledge within a project, and chat/search requests scope retrieval with group_ids. Client keys can additionally pin allowed groups server-side, so a v2 docs surface can never retrieve v1 content.
Can it answer 'what changed between two versions'?
If your changelog and migration guides document the changes, yes — retrieval pulls the relevant release entries and the answer synthesizes them with citations to each entry.
Do release notes stay current automatically?
Yes. Changelog pages and GitHub-hosted release notes re-index via scheduled syncs and push webhooks, so a published release is answerable after the next sync.
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 end changelog and version confusion?
Connect your knowledge sources and see cited AI answers in minutes — free, no credit card required.
Get Started Free