03PublishedJudgment
Jev: The New Judge in Town
Why I think decision models are a brilliant idea—and how OpenSidebar is using Jev to judge completion.
Read the essay
OpenSidebar Ideas
Ideas for agents
Ideas for agents
that deserve trust.
Essays on reliability, human agency, evaluation, and the systems that turn capable models into dependable software.
03 published
00 in progress
Writing
The essays
Long-form arguments, grounded in the product and its code. Newest first.
02
Published
Trust
The Sandbox Needs Two Rooms
A public place to try an agent must be safe enough to control—and ordinary enough that the agent cannot see the controls.
Read the essay
01
Published
Reliability
Done Means Verified
An agent is not finished because it acted. It is finished when it has evidence that the user’s objective was achieved.
Read the essay
The reliability loop
01
ActChange the world
02
ObserveRead the new state
03
VerifyEarn the verdict
Editorial lens
What we examine
Not model capability in isolation, but the system around it.
What makes a result believable?
Verification, read-backs, traces, and the difference between an action taken and an outcome achieved.
Where should autonomy end?
Mandates, reversibility, approval boundaries, and preserving the consequential decisions for people.
What turns a model into a product?
Harnesses, tools, recovery, evaluation, and the architecture required for dependable work on the web.