Blog

With GPT and Claude, any PM or designer can build something that technically works in half a day. It is addictive, and it lies. 'Technically works' (in isolation, on happy-path data, on my machine) is a different universe from 'works well inside the current system, at scale.' That second thing is the real engineering, and AI quietly lets you skip all of it. This post is about the prototype trap, the naivety of confusing a working demo with a production-ready feature, and the reframe that makes non-engineers actually useful with AI: run the loop to evaluate options and build conviction, spark the team instead of pretending the hack is done, and treat innovation as selection rather than invention.

A builder's argument for why neither product teams nor everyday users are ready for fully autonomous AI agents: verification is the expensive part and most of us can't afford it, and unverified AI output compounds like debt. Includes the snowball failure modes I hit running an agent-heavy personal knowledge system, and the practices I stole from gbrain and gstack to contain them: memory gates, provenance, supersede-not-append, periodic reindex, fresh-context isolation, and poisoning defenses.

Claude Code shipped workflows. So I wrote one that takes any testing task — a vague Slack message, a Jira story, a 'just check the checkout' — and runs it end to end on Katalon True Platform. Manual, automated, and Playwright. One skill. Three lanes. Here's the whole thing.

How we build software in the AI era. A complete ways-of-working model for AI-native teams — why agile and Scrum rituals (sprints, story-point estimation, velocity, the daily standup) were a tax on slow building, why Kanban and continuous flow fit human-and-AI-agent collaboration, and the markdown files you can drop into a repo to run it tomorrow.

How Claude Code records every interaction as a replayable, auditable event stream — and why the design choices are worth stealing.

What agentic QA actually is (and isn't), the 25% automation ceiling, trust as a loop, the harness vs. the model, and the one experiment every QA leader should run this week.

Kai is the orchestrator agent at the heart of Katalon's True Platform — a repositioning from automation company to AI-native quality platform. A short note on what shipped and why it matters.

Understanding when to fix the bottom and when to empower the top - a practical guide to team leveling that every leader needs

From daily briefs to project management - how Claude Code and a Light Agent system transformed my workflow into a terminal-first lifestyle

How Scout bridges the gap between high-velocity AI-assisted development and quality assurance, bringing autonomous testing to the era of vibe coding.

The PM job has never been simultaneously easier and harder than it is right now. With just one prompt, I can transform ideas into prototypes and concepts into mockups—but like the massive IBM computer in 'Hidden Figures,' these tools are only valuable when you truly understand what lies beneath them.

The operating pattern I use to take new ideas from sketch to scalable system without losing momentum.

High-quality execution comes from deliberate practice loops, not from reading more playbooks.

How to anchor product decisions in the realities of the people you serve—without turning discovery into a stage play.