The harness can improve without touching the model
An outside model found a real bug in my agent's harness, wrote a fix, and proved it helped; every safety property in that sentence had to be built by hand.
July 2026No. 06A working coding agent is about 2,500 lines of harness
Fifteen chapters after the empty file, the model's weights hadn't changed once; everything that reads as agentic came from code we wrote around one API call.
July 2026No. 05Context management decides what the model sees this turn
Forty turns into a real bug the agent started contradicting itself; the model never changed, the window did.
July 2026No. 04Agent skills are procedures the harness can load
Your strongest reviewer cannot sit inside every pull request; a skill captures the repeatable part of their procedure so the agent stops rediscovering the job.
July 2026No. 03Agent sandboxing is a blast radius decision
The word sandbox covers five very different mechanisms, from a V8 isolate to a microVM, and the right one depends on the failure you need to contain.
July 2026No. 02Agent memory is context assembly over time
The model forgets everything at the session boundary; whatever feels like memory is the harness deciding what to keep, recall, update, and forget.
July 2026No. 01Harness engineering is the system around the model
When an agent fails, the model takes the blame; the more useful questions are about the ten layers wrapped around it.