I have been building software and web systems since 1995. This site documents what changes when experienced engineering process is used to plan, direct, review, and ship work through AI agents.
Why Symfony, a project-specific skill, and a bounded pre-commit review hook sit underneath the AI-assisted delivery lifecycle.
Read article →How framework governance, project conventions, and a bounded commit hook keep AI-assisted Symfony work from drifting across slices.
Read articleHow hidden delivery work and review-environment pressure forced the planning method to become an inspectable lifecycle: plan, design, specify, scaffold, implement, and verify.
Read articleHow review/ worktrees, disposable containers, and isolated databases keep parallel agent work reviewable without turning one staging site into a hidden dependency.
What the first implementation slice exposed: the visible feature estimate was useful, but it missed import, framework, security, review infrastructure, seed data, and remediation work.
Read articleExtending the docs-in-Git pattern to scope boundaries, slice plans, review notes, status files, and next-action decisions in an AI-assisted delivery workflow.
Read articleBreaking the 2,800-hour work breakdown into multiplier bands: high-compression implementation, client-dependent coordination, controllable setup work, discovered build work, and parallel-slice risk.
Read articleHow a two-hour client walkthrough became a structured work breakdown using AWS Transcribe, Claude-written extraction scripts, screenshots, product comparisons, and engineering review.
Read articleWhere the 8x number held, what conditions made it possible, and where the claim stops: production-grade, narrow-scope CRUD/business web apps, not all software.
Read articleOversized, interdependent slices run in parallel can slow the project down, even when each individual agent is moving quickly.
Writing topicUsing commit history, churn, fix-like work, and feature clustering to measure where slices were too large and how to split them next time.
Writing topicI am Jochen Daum, a software engineer based in Tauranga, New Zealand. I have been building software and web systems since 1995, across custom applications, WordPress, hosting, AWS, and production support.
This site is for practical notes on software delivery with AI agents: planning, slicing, review, deployment, hidden requirements, and the difference between coding faster and engineering better.
More about me →