The Operating System

The stack behind the output.

My own operations run on an AI operating system I built: more than 100 scheduled jobs behind a control plane with spend caps and a kill switch, and typed approval before any agent-proposed change merges.

100+
Scheduled jobs
Typed
Approval before agent changes merge
Weekly
Operator scorecard
Replay
Gate on proposed rule changes

Control plane

More than 100 scheduled jobs. One control plane.

Scheduled jobs, scripts and AI agents run my operations. Every one of them is registered in a control plane with spend caps, a kill switch and typed approvals.

Approvals

Agent-proposed changes wait for my typed approval.

When an agent proposes a change, it arrives as a review card. It merges only after my typed approval, and it is measured afterwards.

Scorecard

A weekly scorecard audits my AI operator.

Since 28 September 2026, a weekly scorecard has audited my AI operator's replies: corrections per 100 replies by model, completion claims checked against evidence, golden questions, and missed replies.

Its first study tested the model-switch theory and found no cluster of corrections after a switch.

Self-improvement loop

The top correction type becomes one rule change.

Propose

The top correction type from the scorecard becomes one proposed rule change.

Replay

A replay gate tests the change on golden questions and past incidents.

Approve

The change merges only on my approval.

Built on 4 October 2026. The first card was wrongly denied by an absolute bar, so the gate now judges against the baseline.

More in The loop that rewrites my operator's rules.

Open to roles and client projects.

I work US hours and I am open to AI automation engineer roles and client projects with international teams.

Work with me Back to portfolio