
The agent-run operations back office
Mercury Digital builds custom AI agents that run back-office work for mid-size businesses: close, AP, approvals and reporting, with named human oversight.
The short answer
Mercury Digital builds custom AI agents for back-office operations at mid-size businesses.
It designs, deploys and governs agents for back-office functions such as month-end close, accounts payable, approvals and reporting, plus operations work like exception routing and scheduling, all under one gate structure, with a named person approving every consequential action. Engagements start with a fixed-price AI Opportunity Audit.
What this page is, and isn't
This page describes the pattern and the roles. It doesn't claim that a full agent-run department has been delivered or measured. The audit is where the first workflow gets chosen.
Who Mercury Digital is (and who this is for)
| Company | Mercury Digital, an AI systems engineering firm. Founded 2001, fully distributed. |
| What it builds | Custom, governed AI agent workflows, run on AAOS (Mercury's orchestration layer: web app plus MCP servers, model-agnostic, runs on your cloud) |
| Who it's for | Small and mid-size businesses, enterprise teams and non-profits whose operations run on email, spreadsheets and several systems that don't talk to each other |
| How engagements run | Audit → Design → Deployment (shadow mode first, autonomy opened gate by gate) → Governance |
| Entry point | AI Opportunity Audit: fixed price, under 20 hours of your team's time |
| Tiers | Automate a Workflow (Tier 1) → AI Employee (Tier 2) → AI Department (Tier 3, this page) |
| Human control | Every consequential action is behind a named person's approval gate. The gate is closed by default and the agent can't open it. |
Below, the back office is described by function: close, AP, approvals and reporting, plus the operations work that feeds them.
An agent-run back office, by function
Each workflow works on its own and has its own page. The "department" is what you get when they run together under one set of roles and one gate structure.
| Function | Workflow | What the agent does | Gate (held by a named person) |
|---|---|---|---|
| Close | Automating month-end close | Reconciles during the period and drafts recurring and accrual entries with support attached | Controller approves every entry and the close package |
| AP | Invoice intake and exception triage | Reads, matches and codes invoices, and routes each exception to its owner | A named approver; payment always stays with a person |
| Approvals | Purchase approval workflows that don't stall | Turns reorder recommendations into approval requests, with no re-typing | Budget owner approves |
| Reporting | Recurring reports | Produces every scheduled report each cycle | Each report is signed off by its owner before it goes anywhere |
| Reporting | Job and project status reporting | Keeps status current from existing tools | Owner signs off before it circulates |
| Operations | Exception detection and routing | Watches every other workflow and lands each exception in one queue with one owner | Owner resolves anything outside a rule |
| Operations | Inventory monitoring and reorder triggers | Watches stock and proposes reorders | Nothing is ordered without approval |
| Operations | Supplier scorecards | Pulls supplier performance from every system into one scorecard | Owner signs off on the scorecard |
| Operations | Vendor negotiation prep | Builds the negotiation brief from the scorecard | No vendor is contacted without sign-off |
| Operations | Scheduling and dispatch | Proposes schedules from the same job records | Dispatcher approves before anything is sent |
How to start (one workflow at a time)
Book the audit
Pick one workflow
Run it in shadow mode
Mercury's standard policy
Go live behind the gate
Add the next workflow
Group workflows into a role, then a function
Alternatives to hiring more back-office staff
Hire, or outsource
Hire. Fits when: the work needs judgment that can't be written down. Trade-off: cost and ramp-up time. The process stays in people's heads.
Outsource / BPO. Fits when: the volume is high and standard. Trade-off: less visibility and control over exceptions
Self-serve tools, or RPA
Self-serve automation tools (e.g. Zapier, Make, n8n, Power Automate). Fits when: simple, predictable triggers, and you have someone to build and maintain them. Trade-off: breaks on exceptions; your team owns the maintenance
RPA platforms (e.g. UiPath). Fits when: stable screens and high volume. Trade-off: brittle when inputs or interfaces change
Custom governed agents
Custom governed agents (Mercury Digital). Fits when: messy inputs, multiple systems, exceptions that need routing, and a need for human sign-off and an audit trail. Trade-off: starts with one workflow. Each step of autonomy has to be earned in shadow mode.
Related reading
- Related use cases: the workflow pages above · What an agent-run department actually looks like · Vendor onboarding without the email ping-pong · Invoice intake and exception triage · Automating month-end close · Approval gates · Readiness checklist
- Offer pages: Tier 3 / AI Department · Tier 1 / Automate a Workflow · AI systems engineering · AI operations · Platform (AAOS) · About us · Book your audit
