Blog

Practical notes on AI agents, Laravel/Vue systems, DevOps, developer tools, and software decisions that need to survive maintenance.

tutorial · July 4, 2026 · 12 min read

The Agent Edit Contract I Use Before a Coding Agent Touches a Repo

A practical contract for giving coding agents repository context, edit boundaries, verification steps, and rollback paths before they touch code.

ai · Jul 3 · 12 min

Your Coding Agent Needs a Map, Not a Bigger Context Window

Why coding agents need compact repository maps, ownership boundaries, and verification paths more than bigger context windows.

devtools · Jul 2 · 13 min

Before You Adopt a Beta Library, Prove the Exit Path

A practical test for adopting beta libraries: prove the rollback path, migration cost, and ownership model before they enter production.

frontend · Jul 1 · 14 min

Code That Renders Is Not Code You Can Trust

A field note on why rendered UI is not enough, and how to verify AI-generated interfaces against behavior, accessibility, and maintenance risk.

tutorial · Jun 30 · 13 min

Your Cron Job Is Not Healthy Until the Artifact Proves It

A production checklist for cron jobs that proves useful artifacts exist, are fresh, and can be consumed downstream after the process exits.

market · Jun 29 · 12 min

Open Weights Just Ate the API Margin — What a Pragmatic Dev Actually Does on Monday

GLM-5.2's MIT-licensed open weights at one-sixth the cost of GPT-5.5 isn't a benchmark story — it's a cost-structure story. Here's what it means for your architecture decisions this week.

devops · Jun 28 · 14 min

The 5 Cron Patterns That Lie to You — Exit 0 Doesn't Mean Success

Five cron patterns that look healthy while silently failing, with checks for stale files, empty outputs, partial JSON, and missing delivery.

frontend · Jun 27 · 15 min

The JavaScript I Deleted With CSS: A 2026 Survival Guide

A 2026 frontend survival guide for replacing unnecessary JavaScript with modern CSS features while keeping behavior accessible and maintainable.

ai · Jun 26 · 10 min

Why AI Cron Jobs Lie to You: The Exit 0 With Empty Output Pattern

Why a green cron exit can still mean failed work, and how to verify agent jobs by checking useful output instead of process status.

ai · Jun 25 · 11 min

I Swapped My LLM Backend — The API Call Worked on the First Try

A field report on changing an LLM backend cleanly: where provider abstraction helps, where costs shift, and what still needs verification.