11 min readarchitecture
The Arc Since the Six Were Caught
After fixing six agent failure modes, the system graduated from outcome checking to path checking. A field report on trajectory evals and generalization.
index / writing
Writing on agent reliability and LLM cost
How I think about making agents trustworthy and affordable in production — the same methods behind the audits and teardowns.
10 min readarchitecture
The Calibration Ledger: 58 Runs, 93% Pass, n Is Small
58 runs, ~93% autonomous pass, and why that number is honest evidence — not a reliability proof. A field report on agent evals at solo scale.
12 min readarchitecture
False Greens: Three Structural Observations
How fail-closed design, headless execution seams, and converting incidents to fixtures stop AI agents lying about success. A field report from a solo dev-loop.
10 min readarchitecture
One-Sided Contracts Break Agent Pipelines
A strict contract enforced on only one side produces false rejections as reliably as a loose one produces false acceptances. A field report from my fleet.
9 min readarchitecture
QA Is Only as Honest as Its Coverage
A PR merged over a red CI job while dev-loop QA said green. Here's the root cause, the fix, and why partial greens are the most dangerous lies in agent systems.
10 min readarchitecture
Permissive Parsing Is a False-Green Factory
How a silent None from an AI agent registered as a pass — and the fail-closed contract that fixed it. A field report from a production agent fleet.
16 min readarchitecture
Six False-Greens in a Self-Auditing Agent Pipeline
Six ways my autonomous dev-loop reported success when nothing had landed — and the fail-closed gates that caught each one before they corrupted the ledger.