Compliance-safe AI answers
PII masking, access controls, and audit trails built in.
Legal blocked your AI rollout: customer PII could leak into prompts, there is no audit trail of what the AI said, and access control is all-or-nothing. Shadow AI happens anyway — employees paste sensitive content into public chatbots.
BeforeQuery is built for governed deployment: PII masking before content reaches the LLM, document-level visibility (public vs. restricted), per-project chat permissions, OIDC/SAML SSO, and workspace audit logs. Full conversation traces mean every answer is reviewable — an approved tool beats a shadow one.
How it works
- 1PII masking scrubs sensitive data before content reaches the LLM.
- 2Document visibility (public vs. restricted) and per-project permissions control access.
- 3OIDC and SAML SSO gate who can use internal surfaces at all.
- 4Workspace audit logs and full conversation traces make every answer reviewable.
What you get
Features that make it work
Frequently asked questions
How does PII masking work?
Sensitive data is masked before content is sent to the LLM, so personal information in your indexed sources or user questions is not exposed to the model provider.
Is there an audit trail?
Yes — workspace audit logs record administrative activity, and conversations plus traces record what was asked, what was retrieved, and what was answered, making the system reviewable end to end.
How granular is access control?
Three layers: SSO (OIDC/SAML) controls who signs in, per-project chat permissions control which knowledge each member can query, and document-level visibility controls which docs are retrievable on which surfaces.
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
Internal helpdesk for IT and HR
"How do I get a laptop repaired?" answered without a ticket.
Separate knowledge across products and versions
Source groups keep Product A answers out of Product B chats.
Stop losing knowledge when people leave
Institutional memory that survives offboarding.
Ready to compliance-safe AI answers?
Connect your knowledge sources and see cited AI answers in minutes — free, no credit card required.
Get Started Free