Build LogVoice Design
#26
2026-06-105 min read

Both voice iterations failed the Cash ISA test. I shipped the original.

Two iterations of the uk-calculator-voice skill (analytical v2.0.0 and warmth-corrected v2.1.0) both failed the same blind A/B on Cash ISA drafts. The original v1.0.0 won both rounds. The ship was v1.1.0: a reset to the passing baseline with the recovery path formalised, not a third iteration attempt.

Read post→
Build LogAgentic AI
#27
2026-06-096 min read

Archon was burning quota. The fix was a hook, not a scheduler.

Three Archon runs in flight simultaneously, two of them fired without a deliberate decision. The instinct was to build a smarter scheduler. What worked was a global PreToolUse hook that intercepts archon workflow run and forces a pause before anything spawns.

Read post→
Build LogPython
#28
2026-05-318 min read

The classifier is the product: how four branches replaced an inbox

Inbox Hub is five SQLite tables, twelve route handlers, four Shadow DOM components, and a launchd cron. Strip those away and what remains is a four-branch decision tree that runs on every message. Everything else is plumbing around that core.

Read post→
Build LogAI Tools
#29
2026-05-287 min read

Ten AI-prose tells, one shell script, no more guessing

The em-dash density in my own published articles was running at four times the normal rate for edited prose. That was a measurable problem. So I made it measurable: codified ten AI-prose tells into STYLE-GUIDE.md and a pre-publish shell audit that catches them mechanically.

Read post→
Build LogDevOps
#30
2026-05-286 min read

Two assumptions the pipeline held until it shipped

B8b's first end-to-end Telegram ship-tap exposed two bugs that had been invisible in every prior test. Neither was logic. Both were assumptions the pipeline had been making silently since the day the code was written.

Read post→