More from Practitioner's Corner

Monday, August 10

ISSUE #41

Practitioner's Corner

We kept getting stuck on one number. An agent scored 100% on correctness and 58% on safety in the same run. It completed the job and leaked credentials it had no business touching. Both scores are accurate. That's the whole problem: the metric you naturally reach for can be orthogonal to the property that actually matters. Builders sense this already. The ones who could run agents longer keep choosing shorter loops, because the receiving organization can't verify what happened fast enough. This issue is us working through what that gap means for people who have to ship.

Monday, August 10

ISSUE #41

Practitioner's Corner

Past Articles

August — Issue #41

Builder Profile

Melissa Pan Changed Instruments Twice, and What She Could See Changed With Them

Database recovery, then agent traces, then practitioners: three instruments, and what each one was structurally incapable of hearing.

Deliberate Constraint

Nobody Ever Blamed the Rate Limiter

Ten-step agent loops are backpressure. The consumer downstream is a human who has to defend the output — and that's where the real ceiling sits.

August — Issue #40

The Two Clocks

A Queue Is Not a Shelf

Queues are not shelves. Two clocks, one in support and one in code review, show how waiting work mutates, and why capacity means attention delivered before that change.