Random thoughts, tutorials, and things I learn along the way.
I keep these intentionally short to deliver the point — I dislike long posts. ¯\_(ツ)_/¯
Note: Some of this content was written with AI assistance, but the thoughts, experiences, and insights shared here are genuinely mine. My goal is simply to share what I've learned along the way.
AI can build almost anything you describe now. The bottleneck moved to the part it can't do — imagining the right thing, and telling its story clearly enough to build. Thinking, imagination, and writing are the new core skills.
AI can find the bug. It can't notice that you just rebuilt last week's helper. PR review's real job is the team alignment it forces — and the bot doesn't get that one yet.
The discipline that compounds in zero-to-one product work isn't a better process. It's a sharper set of principles for the moments the process doesn't cover.
Opening a Claude session with your request looks faster. It isn't. The minutes you spend on exploration before instructing are the cheapest of the day.
AI didn't take the job. It made it obvious that writing code was the smallest, most replaceable part of what I was actually hired to do.
AI is brilliant inside a single file or feature. Pull back to the system level and it drifts. Architecture is still a job that needs a human eye.
I started tagging every button and card with data-* so Claude and Playwright agents could navigate my UI. Turns out they read the accessibility tree — and semantic HTML was the right answer the whole time.
The first solution that feels right is rarely the best one. One deliberate pause before committing changes what you build and how fast you undo it.
AI agents and conversational interfaces are reshaping frontend. A reflection on where UI attention shifts as interfaces move from starting point to byproduct of intent.
When pushing harder stops working, stepping away clears mental overload. Learn how breaks create idle time for background processing and why quiet thoughts often hold the solution.
Standups don't break loudly. They drift in familiar ways—expanding into planning, hosting wrong people, losing focus. A note on keeping daily alignment simple and intentional.
Projects slow down when ownership is unclear. Learn how single-responsibility leadership eliminates the grey zone that kills team momentum and delays.
Reflections on how lasting change mirrors software versioning — humble patches, patient iterations, and the steady maintenance of self.
A reflection on how AI tools changed my coding rhythm — boosting output but fragmenting focus — and how I’m learning to use them efficiently without burning mental energy.
Why learning agentic design patterns is the smartest, most future-proof way to prepare for the next era of AI.
A practical look at orchestrating multi-agent conversations to design and build products — from role-based reasoning to human-in-the-loop curation.
A practical look at using ChatGPT, Claude, and Cursor as a multi-agent reflection loop — and when to actually use it.
Exploring the privacy benefits and technical tradeoffs of running AI models locally on user devices instead of in the cloud.
How I built a DIY MCP server to let ChatGPT remotely orchestrate Claude-Code sessions — enabling real coding work while away from my desk.
A reflection on how staying inside the reasoning loop — instead of passively waiting for results — makes AI coding more efficient for big changes and critical fixes.
Why product teams should design for failure, not just the happy path—lessons from agent loops and a frustrating Uber Eats experience.
How I used the Custom GPT builder itself to refine, test, and critique a new GPT — while keeping myself in the loop where it mattered.
How I use self-simulated user testing to make custom GPTs smoother, faster, and more fun to use.
For fast-moving GenAI teams, structure matters. Here's how to separate iteration from engineering — and ship smarter.
How AI tools can actually make our memory worse, and the personal strategies I use to stay cognitively engaged while coding.
Hard-earned lessons from building and shipping fast in the world of AI assistants and chatflows.
Learn how working memory, stress, and distractions impact productivity, and discover strategies to improve focus and reduce workplace stress for better performance.
Learn practical strategies for managing workplace stress and building effective coping mechanisms based on a decade of experience in the software industry.
Why systems beat goals, and the one book that survived my productivity purge.
Learn a practical way to manage deployments beyond Vercel's free tier limitations using GitHub Actions.
Learn how to avoid over-engineering your code review processes and build contextual review systems that match your team's actual needs rather than following FAANG company practices.
Learn how to build a control room system for client-side rendered applications using WebSockets to manage app state, maintenance windows, and version updates in real-time.
Learn how to build editable HTML components in React using contentEditable, with a generic solution for inline editing across your application.
Learn how to build a custom React hook that enables state synchronization across multiple browser tabs using localStorage and the storage event API.