CC
ERP / Finance / Accounting

Cin7 Core AI Integration

Connect Cin7 Core to BeforeQuery for grounded AI answers and agent actions across ERP / Finance / Accounting.

What is it?

About Cin7 Core

Cin7 Core is one of the ERP / Finance / Accounting 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 Cin7 Core

  1. Step 01

    In the BeforeQuery dashboard, go to Integrations → ERP / Finance / Accounting and select Cin7 Core.

  2. Step 02

    Sign in to Cin7 Core with an account that has permissions to grant BeforeQuery the ERP / Finance / Accounting scopes required.

  3. Step 03

    Confirm the connection. Cin7 Core is now available as a source and action target for every playbook in your workspace.

How BeforeQuery uses Cin7 Core

What the agent does with your Cin7 Core connection

  • 01

    Read Cin7 Core records — vendors, invoices, journal entries, cost centers — into the Context Graph.

  • 02

    Answer finance questions grounded in Cin7 Core data ("what's our AP aging?", "how much did we spend on X vendor?").

  • 03

    Trigger playbooks on Cin7 Core events — new PO approval, invoice matching, month-end close checklist.

  • 04

    Reconcile Cin7 Core data against other systems and flag anomalies for accounting review.

Use cases

What teams actually do with the Cin7 Core integration

AP invoice triage

New invoice hits Cin7 Core → BeforeQuery matches against the PO, verifies line items, checks vendor risk, and either routes for approval or auto-approves within the auto-approve threshold. Manual invoice-handling drops 70%+.

Month-end close checklist

Close kicks off → BeforeQuery generates the checklist per your close policy, tracks each step in Cin7 Core, chases owners on late items, and drafts the executive summary once close is done.

Cost-center + budget Q&A

Manager asks "how much has team X spent on cloud this quarter?" → BeforeQuery pulls Cin7 Core data, filters by cost-center + category, and answers with the specific number + trend vs. budget.

Answer questions grounded in Cin7 Core

Employees and customers ask Cin7 Core-related questions in Slack, Teams, or the widget — BeforeQuery answers with the exact Cin7 Core record shown alongside the response. No context switching, no "log into ERP / Finance / Accounting to check" round-trips.

Cin7 Core — Frequently Asked Questions

Common questions about connecting BeforeQuery to Cin7 Core.

Yes, with approver check-in. All journal writes require finance-owner approval; entries are reversible via reversing JEs; every write is audit-logged with the acting user + reason.
Standard OAuth 2.0 where Cin7 Core 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 Cin7 Core 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 Cin7 Core 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 Cin7 Core 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 Cin7 Core for real.

Ready to connect Cin7 Core?

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