Automation

Automate what you can describe

Write a workflow in plain English — or import a PDF SOP — and BeforeQuery executes it across your systems, with approval where it matters and an audit trail on every step.

Book a demo Explore product

Live now

Capability 01

Trigger on anything

Chat message, submitted form, cron schedule, inbound webhook, monitoring alert, HRIS event, ticket event — every playbook can fire on any of them. The trigger and the workflow are configured separately, so you can run the same playbook on demand and on a schedule.

grounded answer · sources

answer

Priya’s Okta lockout can be cleared via self-serve MFA challenge — no IT intervention required. If MFA fails, escalate to IT on-call.

cited from

IT · Okta account lockout policy

runbook · updated 4d ago

HR · Emergency access procedure

policy · updated 2w ago

Ticket #48211 · priya · resolved

past ticket · similar match

Capability 02

A unified authoring experience

Describe the workflow in plain English and BeforeQuery drafts the nodes, tool bindings, and approval points. Or drop in an existing SOP PDF and watch it turn into a playbook you can review and enable. No visual builder to learn — but a graph view is one toggle away.

approvals · pending 4

unlock okta account

priya.sharma · self-serve · read-only

denyapprove

refund $128.40

stripe · ord_A4b2c · manager approval

denyapprove

revoke prod IAM role

aws · role/analyst · step-up MFA

denyapprove

reset zoom SSO

kiran.mehta · self-serve

denyapprove

Capability 03

135 pre-built playbooks

HR onboarding, IT service desk, security triage, finance approvals, sales handoff, legal contract intake, RevOps hygiene — every module ships with 15+ playbooks you can install in a click.

context · priya.sharma

Capability 04

Approval where it matters

Approval chains with escalation, deadlines, delegates when the reviewer is out, and step-up MFA on destructive actions. Configure once as an Approval Policy; reference from any playbook.

reports · this week

Auto-resolved

78.4%

+4.1 pt

Avg. loop time

11.4s

-2.1s

Approvals pending

-3

Coverage

94%

+1.2 pt

monsun

Capability 05

Draft → staging → production

Rehearse a playbook against a past ticket in simulation mode. Promote to staging with a subset of traffic. Roll back if it does not perform. Every run is versioned; every version is reversible.

grounded answer · sources

answer

Priya’s Okta lockout can be cleared via self-serve MFA challenge — no IT intervention required. If MFA fails, escalate to IT on-call.

cited from

IT · Okta account lockout policy

runbook · updated 4d ago

HR · Emergency access procedure

policy · updated 2w ago

Ticket #48211 · priya · resolved

past ticket · similar match

Capability 06

Every run traceable

Each executed playbook writes to the immutable audit log: what fired it, what data it read, what actions it took, who approved which step. Ready for SOC 2 evidence collection or the after-incident postmortem.

approvals · pending 4

unlock okta account

priya.sharma · self-serve · read-only

denyapprove

refund $128.40

stripe · ord_A4b2c · manager approval

denyapprove

revoke prod IAM role

aws · role/analyst · step-up MFA

denyapprove

reset zoom SSO

kiran.mehta · self-serve

denyapprove

The BeforeQuery method

Visibility. Reasoning. Action.

Every playbook, every action, every answer follows the same three-beat rhythm — one that keeps every write behind evidence and every decision behind policy.

Visibility

Read the full context — who is asking, what they own, what they can access, what breaks if we touch it. Nothing acts on incomplete signal.

Reasoning

Match the request to a grounded answer or a playbook. Cite the source paragraph, weigh the risk tier, and route to the correct approver where policy demands it.

Action

Execute the write on your systems with an audit-log id, an entity list, and a rollback path. Confirm the outcome with the requester in the same thread.

How every request flows

From ask to resolution in one loop

Six stages every request travels. What changes is how many stages policy lets the agent execute without waiting on a human.

Request

In Slack, email, widget, MCP, or the helpdesk. Same voice, same context.

Slack · Teams · Zendesk · Widget · MCP

Retrieve

Grounded lookup against your knowledge with source paragraphs held aside.

Knowledge Studio

Reason

Read the Context Graph — who, what they own, what breaks if we touch it.

Context Graph

Approve

Route to the correct approver per policy. Reversible writes gated, destructive step-up.

Approval matrix

Execute

Act on Okta, Stripe, Workday, GitHub, or your own systems. Logged and attributable.

Actions runtime

Verify

Confirm the outcome with the requester. Feed the result back into future decisions.

Feedback loop

Request

In Slack, email, widget, MCP, or the helpdesk. Same voice, same context.

Slack · Teams · Zendesk · Widget · MCP

Retrieve

Grounded lookup against your knowledge with source paragraphs held aside.

Knowledge Studio

Reason

Read the Context Graph — who, what they own, what breaks if we touch it.

Context Graph

Approve

Route to the correct approver per policy. Reversible writes gated, destructive step-up.

Approval matrix

Execute

Act on Okta, Stripe, Workday, GitHub, or your own systems. Logged and attributable.

Actions runtime

Verify

Confirm the outcome with the requester. Feed the result back into future decisions.

Feedback loop

Enterprise-grade by default

The controls your security team is going to ask about

SOC 2 Type II

audited annually

GDPR

EU data residency

HIPAA-ready

BAA available

SSO / SAML

Okta · Entra · Google

SCIM 2.0

auto-provision

Audit log

every write, traceable

Bring your key

AES-256-GCM at rest

Bring your model

Anthropic · OpenAI · self-host

Zero training

your data stays yours

Rollback

every write reversible

TLS 1.3

in transit

99.9% uptime

SLA on Enterprise

Explore the stack

Works together with

Agentic Support

The most common home for playbooks.

BeforeQuery Assistant

The conversational surface.

AI Service Desk

Where playbooks meet the ticket queue.

Knowledge Studio

The knowledge every action is grounded in.

Frequently asked questions

Common questions about Proactive Playbooks

Open Playbook Studio, pick a module, and describe the workflow: what triggers it, what systems it touches, what it should do at each step, and where a human should approve. BeforeQuery drafts the nodes and the tool bindings; you review, tweak, and enable. Most first playbooks are live in under an hour.

Yes. Drop in a PDF, Word doc, or Confluence page and the AOP-style import parses the steps, matches each to a tool call, and asks you to confirm the tricky spots. Great for teams migrating from ServiceNow, Jira Service Management, or a hand-run runbook.

Full list at /playbooks — 22 for HR, 20 for IT, 23 for Finance, 26 for Security, 25 for RevOps, 19 for Legal. Each ships with its systems required, trigger, approval defaults, and success metric. Install, connect, and go.

Every executed action is logged with the entity IDs it touched. Rolling back replays the reverse action against those IDs — e.g. re-provisioning an account we deprovisioned, cancelling a refund we issued. Some external systems don't support true rollback (e.g. sent emails); those actions are marked non-reversible before the write.

Yes. Environments (draft, staging, production) work per-playbook. You can pin production traffic to v3 while running v4 against 10% of a specific queue in staging.

Run automation on BeforeQuery

Book a demo and see what Proactive Playbooks does on your own data — usually within 45 days.

Book a demo Start Free