Sign in Subscribe

Topic

Automation

A collection of 23 issues

A fix applied to the live page is not a fix: locking rebuilt pages against the generator that re-creates the error

A correction made in June was live-wrong again in October, because the build engine that renders the page was never updated. The fix was a server-side lock that refuses writes to the rebuilt pages.

"The draft is ready" is not a status: what an agentic routine owes you when it reports on its own work

A daily scheduled routine carried its own claim that two replies were drafted. Neither draft existed. Why an agent must verify the assertions it holds in state - and the API trap that nearly confirmed the bug.

Claude Code mods vs skills: a skill is a suggestion, a mod is a guarantee — and what I would hard-block first

Mods run inside the Claude Code harness and can refuse a tool call outright, where a skill can only advise. The scoping rule that follows, the four I would actually build, and the security posture they demand.

File timestamps can't see staleness that comes from outside the folder: what an agentic housekeeping routine needs that mtime doesn't give it

My weekly routine rebuilds stale project summaries by comparing file modification times. It ran clean — and missed a summary made wrong by a decision taken in a different folder. Local change detection is not correctness.

The daily automation that never calls a model: local scheduled jobs, a receipt printer, and designing for the device being offline

Claude Code built it; nothing in the running loop calls a model. The useful lesson was not the printer - it was that the output device is the flakiest link, and coupling the email to the print cost me both.

Price governance in ecommerce: how a promotion died silently on four country shops for a month

A home and living brand advertised a fifty-euro saving while checkout charged full price on four markets for a month. The cause was the price guard itself - and the fix was declaring the price once and auditing the whole chain daily.

I tested my new Claude skill against an agent that didn't have it — and the control group found the saving my skill missed

The skill was 35% faster and used 12% fewer tokens. The baseline agent, with no instructions at all, found €10.51 the skill walked straight past. Why the no-skill run is a second opinion, not just a scoreboard.

I replaced my Loom subscription with a single app I build myself: what Claude Code builds in an afternoon moves the buy-versus-build line

Screen capture, a camera bubble, live transcript, YouTube upload with real subtitles and chapters - all browser APIs, one local file, built with Claude Code. The constraint that looked like a bug became the best feature.

Nineteen days of ad spend with no measurement: the Google Tag Manager snippet was gone from the page, not broken in the console

A purchase conversion sat at zero for nineteen days. The container was fine - the snippet had been removed by a deploy. How to pin the hour without backend access, why you must tell Smart Bidding its data is wrong, and the fourteen-day cap that makes fast detection worth money.

My scheduled Claude Code routine failed three weeks running: what agentic workflows need that a written lesson doesn't give them

An AI automation that couldn't unblock itself, scheduled in a context where the one thing it needed was impossible. Why agents must know what their execution environment can do — and why a well-written lesson with no owner changes nothing.

Work with me →×