# Jack K.

> Anyone can spin up a thousand agents. Here is what it takes to control them.

All consoles run live state machines on synthetic telemetry. No employer or customer data.

I build interactive browser simulations for running IT infrastructure and AI-agent fleets with human gates, blast-radius previews, and auditable replay logs.

## Interactive prototypes

- **Control room** (/control-room · Interactive · synthetic data): Hosts, VMs, and backups you can actually restore — infrastructure with an owner.
- **Threat console** (/sentinel · Interactive · synthetic data): Triage detections, isolate one host, and verify recovery — judgment calls over noisy alerts.
- **Identity center** (/identity · Interactive · synthetic data): Show access lifecycle: movers, leavers, privilege, and an access review nobody has signed off.
- **Network ops** (/netops · Interactive · synthetic data): Trace paths, temporary rules, and certs before something expires on a Friday.
- **Lab systems** (/labops · Interactive · synthetic data): Instruments, calibration, and readiness — ops discipline on a regulated bench.
- **License audit** (/saas · Interactive · synthetic data): Find unused seats and shadow apps before renewal, then reclaim with intent.
- **Evidence board** (/evidence · Interactive · synthetic data): A control isn't done until the pack is ready for the auditor.
- **Agent fleet** (/fleet · Interactive · synthetic data): See how thousands of agents stay under a human who can pause, quarantine, or kill a lane.
- **Arcade** (/arcade · Interactive · synthetic data): Short browser challenges I built for attention, pattern recognition, and recall.
- **GL finance** (/ledger · Interactive · synthetic data): Post, balance, and exception-handle a period in a classic finance workspace.
- **Month-end close** (/close · Interactive · synthetic data): Drive close tasks to a board-ready finish with clear owners.
- **System status** (/status · Interactive · synthetic data): Run incident communication when dashboards look green and users see otherwise.

## Open problems

- Human approval gate before any agent action executes
- Autonomous incident triage with human containment
- AI-assisted 21 CFR Part 11 compliance evidence

## Contact

Contact coming soon