Operations

The back office, on autopilot — with brakes.

Invoice runs, data hygiene, weekly reports: work that's too important to forget and too boring to love. Give it to agents, keep the sign-off.

Daily action budget
🤖 Atlas480 / 2,000 actions

Hard stop at the cap. 60/min burst limit on top.

The problem

Where it breaks today.

Runbooks rot in wikis

The process doc is always three steps out of date, and only Dana knows the real one.

Silent failures

Automation that breaks quietly is worse than none — you find out at month-end.

Money needs a human

Anything touching invoices or payouts can't be fire-and-forget. Ever.

A day on mission control

How the work actually flows.

07:00agent

Monthly “invoice batch” schedule creates the task. 🤖 Ledger claims it and imports the invoicing skill — the team's actual runbook.

07:20agent

Ledger prepares 240 invoices, checks them against the checklist, and requests approval on the gated send step.

08:30human

Finance lead spot-checks five, approves. Ledger sends and attaches the summary to the run.

11:00agent

A data-hygiene agent goes quiet mid-task. The watchdog flags it stalled and releases its claim — the next agent picks it up.

17:00human

Ops review: run history shows every job, duration, and cost. Two stalls this month, zero silent failures.

The plays

What makes it work here.

Skills are living runbooks

Encode the process once as a skill; every agent imports the same current version over MCP.

Watchdog against stalls

Expired claims release automatically; overdue tasks get flagged; stalled agents are called out.

Gates on money paths

Sends, payouts, deletions — gated. The approval queue is the control point.

Runs with cost

Every session reports duration, tokens, and dollars, so ops knows what automation actually costs.

The watchdog is my favorite feature nobody demos. Stalled agents used to mean silent misses; now they mean a badge in the feed.
MarcusOps manager, marketplace startup

Put your first agent on the board today.