Policies & Playbooks

Turn runbooks into an incident copilot

At 2am, the on-call asks and gets the runbook step — not a wiki search.

The pain

During an incident, the on-call engineer knows a runbook exists but not where, and wiki search returns three stale versions. Minutes of outage are spent finding the document instead of following it, and the engineer who wrote it is asleep.

How BeforeQuery solves it

Index your runbooks, postmortems, and architecture docs from GitHub, Notion, and Confluence, and the on-call asks the Slack bot in the incident channel: "how do I fail over the payments DB?" The answer comes back in seconds with steps and a citation to the canonical runbook — and gap analytics show which incidents had no runbook at all.

How it works

1Index runbooks, postmortems, and architecture docs from GitHub, Notion, and Confluence into one knowledge base.
2Install the Slack bot and invite it to your incident channels.
3During an incident, the on-call asks in-channel — "how do I fail over the payments DB?" — and gets the runbook steps with a citation in seconds.
4Questions with no runbook behind them are logged as knowledge gaps, becoming your runbook backlog.
5GitHub webhook syncs re-index runbooks on every push, so answers always match the latest revision.

What you get

On-call engineers get the runbook step, not a wiki search, at 2am.

Answers cite the canonical runbook, eliminating stale-version confusion.

Every incident with a missing runbook surfaces in gap analytics.

Runbook edits propagate to answers automatically via webhook syncs.

Features that make it work

GitHub / Notion / Confluence sources

Slack bot in incident channels

Citations to canonical runbooks

Knowledge gap analytics

Frequently asked questions

How current are the runbook answers?

GitHub and GitLab sources can re-index via webhooks on every push, and other sources sync on a fixed schedule. Answers always retrieve from the latest indexed revision, with a citation so the engineer can open the full runbook.

Can this run inside our existing incident channel?

Yes. The Slack bot answers on @-mention in any channel it is invited to, including ad-hoc incident channels, and threads its answer under the question so the incident timeline stays readable.

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.