Policies & Playbooks

AI answers for company policies

"Can I expense this?" answered from the actual policy, with a citation.

The pain

Your policies live in PDFs and wiki pages nobody opens: expense rules, travel policy, security requirements, code of conduct. Employees guess, ask a colleague who also guesses, or ping HR and legal for the hundredth time. Wrong guesses become compliance incidents.

How BeforeQuery solves it

BeforeQuery indexes your policy documents from Confluence, SharePoint, Google Drive, Notion, or direct PDF upload and answers policy questions in Slack or the internal Ask portal — always citing the exact policy section, so the answer is verifiable, not folklore. When policies change, the next sync updates every answer automatically.

How it works

1Connect the systems where policies live — Confluence, SharePoint, Google Drive, Notion — or upload policy PDFs directly.
2BeforeQuery normalizes each document to markdown, chunks it heading-aware, and embeds it into a governed knowledge base.
3Employees ask in Slack or the internal Ask portal: "can I expense a client dinner?" and get the answer with a citation to the exact policy section.
4Set document visibility and per-knowledge-base permissions so sensitive policies are only queryable by the right teams.
5When a policy changes, the next scheduled sync re-indexes it — every future answer reflects the current version.

What you get

Employees get policy answers in seconds instead of pinging HR, legal, or IT.

Every answer cites the policy source, so it is verifiable — not hallway folklore.

Policy updates propagate to answers automatically on the next sync.

Gap analytics reveal which policies are confusing enough to rewrite.

Features that make it work

File upload sources (PDF/MD)

Confluence / SharePoint / Drive sync

Slack bot

Citations to the policy source

Frequently asked questions

Can we restrict who can ask about which policies?

Yes. Documents can be marked restricted, and per-knowledge-base chat permissions control which workspace members can query each knowledge base — so manager-only compensation policies stay separate from the general employee handbook.

What if the AI misstates a policy?

Every answer carries citations to the policy section it was drawn from, and low-confidence questions fall back to your HR or legal contact instead of guessing. Conversation logs and LLM-judge evals let you audit answer quality over time.

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.

Does BeforeQuery work in languages other than English?

Yes. BeforeQuery answers in the language of the question while retrieving from your knowledge base, even if your docs are English-only, with citations back to the original pages. Workspace analytics break questions down by language so you can see which markets are asking what.