C
Payroll

Check AI Integration

Connect Check to BeforeQuery for grounded AI answers and agent actions across Payroll.

Connect Check
What is it?

About Check

Check is one of the Payroll platforms BeforeQuery connects to. Once linked, the platform's data becomes a first-class source for grounded AI answers and a target for policy-gated agent actions — the same identity, approval, and audit-log guarantees every other integration ships with.

Setup

How to connect Check

  1. Step 01

    In the BeforeQuery dashboard, go to Integrations → Payroll and select Check.

  2. Step 02

    Sign in to Check with an account that has permissions to grant BeforeQuery the Payroll scopes required.

  3. Step 03

    Confirm the connection. Check is now available as a source and action target for every playbook in your workspace.

Explore

Related integrations

G
Gusto

Gusto is one of BeforeQuery's Payroll integrations. Connect it once and every agent in your workspace can read, reason over, and act on Gusto data with your policies + audit trail.

P
Paychex

Paychex is one of BeforeQuery's Payroll integrations. Connect it once and every agent in your workspace can read, reason over, and act on Paychex data with your policies + audit trail.

RP
RUN Powered by ADP

RUN Powered by ADP is one of BeforeQuery's Payroll integrations. Connect it once and every agent in your workspace can read, reason over, and act on RUN Powered by ADP data with your policies + audit trail.

How BeforeQuery uses Check

What the agent does with your Check connection

  • 01

    Read Check pay history + upcoming runs to answer employee questions in Slack ("when's my next check?").

  • 02

    Trigger downstream updates when Check data changes — banking, tax jurisdiction, deductions.

  • 03

    Draft communications for pay-cycle events, holiday shifts, or off-cycle bonuses grounded in your comp policy.

  • 04

    Reconcile Check exports against ledger entries and flag anomalies for the accounting team.

Use cases

What teams actually do with the Check integration

Employee pay-history Q&A

Employees ask "when's my next paycheck?" or "how much was my last bonus?" — BeforeQuery pulls their Check record, checks the pay calendar, and answers with the specific number and date. No HR ticket required.

Off-cycle bonus workflow

Manager submits an off-cycle bonus in the request form → BeforeQuery drafts the Check adjustment, routes to CFO approval, executes the payroll write, and sends the employee a heads-up with the amount and pay-date.

Payroll-ledger reconciliation

After each Check run, BeforeQuery pulls the export and reconciles against the GL entries in NetSuite / QuickBooks. Anomalies (unexpected line items, out-of-band amounts) get flagged for accounting review with a linked drill-down.

Answer questions grounded in Check

Employees and customers ask Check-related questions in Slack, Teams, or the widget — BeforeQuery answers with the exact Check record shown alongside the response. No context switching, no "log into Payroll to check" round-trips.

Check — Frequently Asked Questions

Common questions about connecting BeforeQuery to Check.

Only if a playbook needs it. Comp data is treated as high-sensitivity: the connection can be scoped to exclude comp fields entirely, and any playbook that reads comp requires an approver on the workspace level. Nothing about compensation appears in default answers.
No. Full payroll runs stay with your payroll administrator inside Check. BeforeQuery reads, drafts adjustments, and orchestrates the surrounding workflow (approvals, communications, reconciliation) — but the "process payroll" action stays with a human.
Standard OAuth 2.0 where Check supports it, otherwise API-key or bearer-token auth. Credentials are stored encrypted at rest (AES-256-GCM) per workspace, never shared across customers, and rotated on request. The connection is scoped to the least-privilege set of scopes each playbook needs — you approve the scope list on install.
No. Your Check data feeds only your workspace's own agents and answers. Nothing is used to train a shared model, and nothing crosses workspace boundaries. Bring-your-own-model is available on Enterprise if you want to pin inference to your own OpenAI / Anthropic / self-hosted deployment.
Yes. Every Check integration is scoped at install time — you pick which resources, users, or record types are visible. You can further restrict per-playbook: a single playbook only touches the specific Check objects it needs. Scope changes take effect on the next sync.
Every write is logged with the acting user, the playbook that fired it, the exact operation, the target entity IDs, and the timestamp — all in the immutable audit log. Writes are rehearsable in simulation mode against a copy of live data before they touch Check for real.

Ready to connect Check?

Start free. No credit card required. Connect your first integration in under 5 minutes.

Get started free