Writing
Writing, in reading order.
Two tracks: systems that carry state over time, and agent workflows that can be verified end to end.
Systems With Continuity
Essays on memory, governed state, adaptation, and why useful software should compound over time.
- 013 min
Software Is Shifting From Tools to Systems
The real change is not that models can answer better. It is that useful software now needs loops for observation, correction, and carried state.
- 023 min
The Demo Works. The Fifth Run Doesn’t.
First-run output is the easiest benchmark. Repeated work is where weak continuity shows up.
- 033 min
Most AI Agents Don’t Improve Over Time
Repeated work should compound. Most agents still recompute.
- 043 min
Context Is Not Memory
Memory that affects behavior needs status, provenance, correction, contradiction handling, and revocation.
Reliable Agent Systems
Essays on coding agents, verification, orchestration, and the structure required to ship working software.
- 053 min
Why Most Coding Agents Still Don’t Ship Working Software
Plausible code is local success. Shipping software requires design, verification, runtime checks, and carry-forward knowledge.
- 063 min
Deterministic Gates Beat Prompt-Only Control
If a rule matters, move it out of the prompt and into the harness.
- 073 min
The Goal Is Not Multi-Agent. The Goal Is Reliable Software
Extra agents only earn their place when they isolate a recurring failure mode.
- 0810 min
Building a Coding Agent That Actually Ships
A Claude Code plugin for turning vague software ideas into reviewed, tested, committed code.
- 093 min
What Building This Taught Me About Diagnosis, Not Retries
Repeated failure usually means the system needs a different model of the problem, not another attempt.
- 104 min
Using coding-agent to Build a Local-First Knowledge Base
The repo tells two separate stories: a markdown-first knowledge base with one shared core, and a coding-agent workflow whose rules and artifacts stayed visible in the tree.