Policies & Playbooks

Make SOPs and playbooks answerable

Operational procedures people follow because they can find them.

The pain

You wrote SOPs for onboarding customers, handling refunds, escalating outages, closing the books — and execution still varies by person, because reading a 20-page procedure to answer one question is unreasonable. The playbook exists; the behavior doesn't.

How BeforeQuery solves it

BeforeQuery turns your SOP library into an assistant: an operator asks "what's the refund process for annual plans?" mid-task and gets the exact steps with a citation to the SOP. Doc proposals flag recurring questions no SOP covers, so the playbook grows where the process actually breaks.

How it works

1Connect the tools holding your SOPs — Notion, Confluence, Google Drive, SharePoint — or upload them as files.
2BeforeQuery chunks each procedure heading-aware, so retrieval returns the relevant step, not the whole 20-page document.
3Operators ask mid-task — "what's the refund process for annual plans?" — in Slack or the internal Ask portal and get cited steps.
4Doc proposals scan recurring unanswered questions and draft new SOP content for your team to review.
5Scheduled syncs keep the index matched to the live procedures.

What you get

Procedures get followed because finding the right step takes seconds.

Execution stops varying by person — everyone retrieves the same approved SOP.

The playbook grows where the process actually breaks, driven by gap data.

New team members self-serve process questions from day one.

Features that make it work

Multi-source SOP indexing

Internal Ask assistant

Doc proposals from gaps

Scheduled syncs keep procedures current

Frequently asked questions

Our SOPs are long documents — will answers be precise?

Yes. Documents are chunked along their heading structure, so a question retrieves the specific procedure section rather than the whole document, and the citation links back to it for full context.

How do we find out which SOPs are missing?

Knowledge gap analytics log every question the assistant could not answer confidently, clustered and ranked by frequency — and doc proposals draft candidate SOP content from those gaps for your team to accept or dismiss.

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.