I Do Run AI Agents Overnight. Here's What Actually Matters.
Boundaries, supervision, evidence, and why unattended execution is not the same thing as unbounded autonomy.
Petie Clark — Applied AI Systems
Applied AI systems that survive contact with the business.
Field notes on agent orchestration, evaluation, authority boundaries, enterprise integration, deployment, and production operations.
Get new posts in your inbox
No spam. No marketing. Just the writing.
/start-here
How I think about governed systems
Why I Prefer One Clear Source of Truth
Why tools can multiply while authority, state, and accountability still need one dependable home.
Why I Write Down the Rollback Before the Change
A deployment is not ready merely because the forward path looks convincing.
The Case for a Smaller Blast Radius
Production systems become trustworthy through bounded change, not theatrical confidence.
The Case for Boring DNS Records
DNS rewards restraint. A short record can sit underneath browsers, certificates, service discovery, remote access, and every note that tells someone where to go. Because the syntax is compact, it's tempting to use records as a clever abstraction layer. Then a troubleshooting session becomes a tou...
4 min read
Read →
Why I Test From the Browser Backward
The browser is where all the private agreements in a web system become one public experience. A button carries the wrong label. A request leaves with the wrong shape. A response arrives correctly but never changes the screen. Each layer may look reasonable by itself, while the person using the pa...
3 min read
Read →
The Cost of One More Convenience Layer
Convenience layers are easiest to add when the underlying tool is almost pleasant. A desktop launcher can remember a model command. A web panel can turn flags into toggles. A helper script can choose ports, directories, and defaults so I don't have to. The first use gets shorter, which is real va...
4 min read
Read →
What Docker Labels Reveal About Hidden Architecture
Docker labels look like annotations until something starts making decisions from them. A reverse proxy discovers routes. An update tool selects eligible containers. A backup job identifies volumes by a naming convention. A monitoring process groups workloads into a view. Each consumer may read a ...
3 min read
Read →
The Backup Is the Easy Part
Making another copy feels responsible. Storage is cheap, schedules are obedient, and a successful backup job offers a tidy little moment of relief. I know the feeling well. I also know how easily it lets me postpone the harder question: what, exactly, am I promising myself I can recover?
3 min read
Read →
A Small Network Is Still a Production Network
A small network can be rebuilt badly with remarkable speed. There may be one router, one switch, a few access points, and a short list of local services. That looks simple enough to recreate from memory. Then the replacement comes up with a different address pool, half the names point at old dest...
4 min read
Read →
Why I Keep Configuration Close to the Service
Configuration gets harder to trust as the distance grows between a service and the facts required to run it. The distance isn't measured only in directories. It shows up in extra repositories, dashboard-only settings, shell history, copied environment files, and instructions that say “remember to...
4 min read
Read →
The Useful Difference Between Reachable and Ready
A listening port is a wonderfully low bar. It proves that something accepted responsibility for an address. In local model infrastructure, that can happen well before the system is capable of doing the job that brought a caller there.
4 min read
Read →
What Breaks First in a Homelab
The first thing to fail in a homelab usually isn't the newest service. It's the assumption that the service is standing on something simple.
4 min read
Read →
The AI Productivity Paradox Is Real - But You Are Measuring the Wrong Thing
CEOs say AI isn't moving the needle on productivity. I've been running AI in production for months. Here's why they're both right and wrong — and what the actual measurement problem is.
5 min read
Read →