Use Cases/Internal Knowledge

Separate knowledge across products and versions

Source groups keep Product A answers out of Product B chats.

The pain

You run multiple products (or versions, or regions) with overlapping terminology, and a naive AI mixes them up — citing Product A's config syntax in a Product B answer. Cross-contaminated answers are worse than no answers.

How BeforeQuery solves it

BeforeQuery's source groups partition knowledge within a project, and chat, search, and widget requests scope retrieval with group_ids. Client keys can pin allowed groups server-side — a key embedded in Product B's help center can never retrieve Product A content, no matter what the request asks for.

How it works

  1. 1Organize each product, version, or region's content into source groups.
  2. 2Scope chat, search, and widget requests with group_ids.
  3. 3Pin allowed groups on client keys server-side — scoping the request can narrow but never widen.
  4. 4Use multi-project portal chat internally when you do want cross-product answers.

What you get

Keep Product A's config syntax out of Product B's answers.
Enforce isolation at the key level, not just the request level.
Serve multiple products, versions, or regions from one workspace.
Choose scoped or cross-product retrieval per surface.

Features that make it work

Source groups
group_ids scoped retrieval
Client-key allowed_groups enforcement
Multi-project portal chat

Frequently asked questions

What stops a request from accessing another product's content?

Client keys carry allowed_groups enforced server-side: request-level group_ids are intersected with the key's allowed groups, so a key embedded in Product B's help center can never retrieve Product A content regardless of what the request asks for.

Should I use separate projects or source groups?

Separate projects give full isolation (own keys, permissions, analytics); source groups partition within a project while allowing selective cross-group retrieval. Many teams use projects per product and groups per version.

Can internal users still search across everything?

Yes — the internal portal chat accepts multiple project_ids and group_ids, so workspace members with permission can ask across products even while public surfaces stay strictly scoped.

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 separate knowledge across products and versions?

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

Get Started Free