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.
Technical Debt Is Sometimes Just Unmade Decisions
Decision memo: remove competing service routes by choosing one authoritative path and making the fallback prove its limits.
4 min read
Read →
Model Evaluation Is Mostly About Choosing Better Failure
My model notes became useful after I stopped looking for one winner and started recording which mistakes each workflow could survive.
4 min read
Read →
The Best Internal Tools Reduce Questions, Not Clicks
The fleet index became useful when it stopped pretending that discovery was somebody else's problem.
4 min read
Read →
A Workbench Beats a Platform More Often Than Vendors Admit
A useful internal surface can unify a job without trying to own every system behind it.
4 min read
Read →
From Months to Days: How Agentic LIMS Delivery Compresses the Work
How validation maps, parallel delivery lanes, native-workflow fit, production-like clone proof, and explicit human authority compressed LIMS delivery from months to days.
4 min read
Read →
The Interface Between Humans and Automation Is an Authority Model
Automation becomes predictable when permission is part of the interface, not an assumption hidden behind it.
3 min read
Read →
Small Tools Win When the Workflow Is Already Good
The right small tool began by leaving a mature spreadsheet workflow alone.
4 min read
Read →
What Restore Testing Teaches You About Every Other System
The backup report said the archives were valid. The restore diary began because valid archives weren't the claim I needed to prove.
4 min read
Read →
The Useful Part of Observability Starts After the Alert
An alert earns its keep when it shortens the path from a symptom to a safe decision.
4 min read
Read →
I Stopped Counting Activity and Started Counting Accepted Work
The useful measure of automated work begins after output exists: was it verified, accepted, and produced with less steering?
4 min read
Read →