ARTICLES.
Notes from product, interface, and design-system work. The blog is structured as a practical field log: decisions, tradeoffs, and execution patterns that hold up in real projects.
01. FEATURED POST
// HIGHLIGHT
Full-Stack PMs Redesign the Operating Model
AI and no-code tools are collapsing the gap between strategy and execution. The Full-Stack Product Manager isn’t a trend — it’s a structural shift in how validation, learning and product leverage work.
Read FeatureFocus
Replacing manual discovery with continuous AI execution.
Audience
Product Leaders, Builders.
Format
Operating Model.
02. LATEST ARTICLES
// RECENT_NOTES
The Compounding Human
AI doesn't replace people who think — it compounds them. The gap opening up isn't between people who have AI and people who don't. It's between people building intuition now and people waiting to see how it shakes out.
Running agents locally is a different kind of control
After running OpenClaw on a VPS, I rebuilt the stack locally on a Mac Mini. The system works well now, but the real lessons came from operating it daily, architecture decisions, memory design, security boundaries, and the hidden cost of context.
The AI Moat Is Operational, Not Model-Based
Why your competitive advantage isn't about model size—it's about how reliably you ship
Shipping agents is easy. Running them is not.
What it actually takes to run agents in production: stability, memory, governance.
Shipping faster is easy. Governing systems is the hard part.
AI has democratised software creation. That’s the win. The risk is what happens next: brittle systems, quiet security gaps, and products that collapse under real usage. This is a practical take on “system governance” for builders who want speed and staying power.
Streamline your QA & E2E testing today!
QA doesn’t have to be a bottleneck. With Playwright MCP and BrowserMCP, you can turn testing into a programmable, repeatable system that scales with your product.
Why AI demands a new playbook
AI does not behave like traditional software. Not deterministic outputs, but probabilistic systems. This post explains why roadmaps must shift from feature delivery to learning, and how Product Managers can plan, measure, and communicate in non-deterministic development.
Rethink how we build with AI
Adding AI to existing products is not transformation. It is augmentation. This piece explores why bolt-on AI underperforms, why generative systems demand first-principles design, and why the real shift is architectural, not incremental.
The age of the agent orchestrator
AI agents are moving from novelty to infrastructure. As organisations deploy more autonomous systems, the scarce skill is no longer execution. It is orchestration.
Vibe coding tools for Product Managers
A practical look at Cursor, Windsurf, Lovable and Bolt, what they’re good for, where they bite, and how Product Managers can use them without pretending they’re senior engineers.
A comprehensive guide to creating better prompts
Prompting is not clever wording. It is specification. This guide shows Product Managers how to write prompts that produce reliable outputs, plus reusable templates you can lift straight into your workflow.
The End of Apps
Apps were built for navigation. AI agents are built for outcomes. This piece explores why software is shifting from static interfaces to dynamic, conversational systems.
Why Product Managers will thrive with AI
AI does not replace Product Managers. It rewards the ones who think in systems, write clearly, and measure outcomes. Here’s how to use it without turning your workflow into fluff.
How the Product Manager role keeps evolving
Product Management has never been a fixed job. It has shifted with markets, software, and now AI. This is the structural story of how the role evolved, and what it is becoming next.
So, you want to be a Product Manager?
Product Management looks tidy from the outside. In reality it is influence without authority, decisions without perfect data, and constant context switching. Here is what the job actually feels like, and why people still choose it.
Let’s talk about prioritisation
Prioritisation is not choosing the best idea. It is choosing the next trade-off. These frameworks help teams make the trade-offs explicit, and stop “loudest voice wins” becoming your roadmap.
Building AI products that people trust
AI is now normal software. The winners will not be the cleverest models. They will be the teams that design for trust, control, and real user outcomes.
03. SUBSCRIBE
One concise update each month: what shipped, what changed, and what I learned while building products and systems.