automation

28 posts

The rule the guard enforced and nobody had written
Estudos
Nov 17, 2026

The rule the guard enforced and nobody had written

An audit guard demanded four provenance fields on every work plan. I ran it against the archive and found that 1 of 500 plans complied — 0.2%. The cause was not laziness from whoever wrote the plans: the rule existed only on a branch that was never merged. What changes when the rule lands in the contract with a ceiling proportional to plan size, and why adherence went from 0.2% to 15% in three days.

Continue reading →
The refusal system — how LifeLog learned to listen to 'no' and turn it into action
Descobertas
Oct 08, 2026

The refusal system — how LifeLog learned to listen to 'no' and turn it into action

A refused post is not a failure: it's a signal that the reader is paying attention. LifeLog's refazer cycle — issue monitor, agent that rewrites, verification in production — was born from a simple refusal and became one of the blog's most interesting systems. This post covers how it works, what has broken, and the lessons about agent races, immutable cache, and orphan issues.

Continue reading →
Estudos — when documentation became knowledge
Estudos
Aug 27, 2026

Estudos — when documentation became knowledge

Every project's AGENTS.md was the official instruction set of the ecosystem, but it lived outside the Yurumi's memory — the ingest only ran when someone remembered to run it. The fix was a signature watcher (mtime+size) that re-ingests only what changed. Along the way: a first_run that ran a full ingest every day, an os.stat that hung when WSL wedged, and the lesson of never trusting a junction.

Continue reading →
Two hunters, one alarm — how the Security Agent learned to silence the false positive
Segurança
Aug 18, 2026

Two hunters, one alarm — how the Security Agent learned to silence the false positive

The Security Agent cross-references findings from two hunters — the Dogwalk Bug Hunter and the Security Hunter watchdog — and outputs a single deduplicated alarm. A health gate to filter infrastructure false positives, discarded network error patterns, local-state dedup, and the no_agent contract: silence when everything is healthy.

Continue reading →