White-labeled help for agency clients
Run branded AI assistants for every client from one workspace.
Your agency maintains docs and support for a dozen client sites, and every client wants 'that AI assistant thing' — branded as theirs, isolated from other clients' data, without you running a dozen separate vendors.
BeforeQuery's multi-tenant workspaces let you run one project per client with fully isolated knowledge and per-project client keys. The widget is themable per site, enterprise plans allow hiding BeforeQuery branding, and workspace analytics give you per-client usage reporting to include in retainers.
How it works
- 1Create one project per client in your workspace — knowledge is fully isolated per project.
- 2Issue per-project client keys, so each client's widget only reaches their own content.
- 3Theme the widget per site; enterprise plans allow hiding BeforeQuery branding.
- 4Use per-project analytics for usage reporting in client retainers.
What you get
Features that make it work
Frequently asked questions
Is client data really isolated?
Yes. Each project has its own sources, index, and client keys — a key issued for one client's project cannot retrieve another client's content, and analytics are reported per project.
Can the widget look like the client's brand?
The widget is themable per site, and hiding BeforeQuery branding is available on the enterprise plan — so the assistant presents as the client's own.
How do I report value to clients?
Per-project analytics cover question volume, deflection, top sources, and knowledge gaps — a ready-made monthly report showing what the assistant handled for each client.
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
Answer repeated questions in Slack and Discord
The bot answers the 50th 'how do I install this?' so you don't.
Reduce community moderation load
First-line answers so moderators handle only real discussions.
Mine forum and Stack Overflow answers
Years of community answers become part of the AI's knowledge.
Ready to white-labeled help for agency clients?
Connect your knowledge sources and see cited AI answers in minutes — free, no credit card required.
Get Started Free