Start with the essays

Agentic Software Development

A curated stream of hands-on tips and lessons learned from tuning coding agents in practice. Skim the summaries, pick a post, and dive in.

  1. Tightening the Frontend Feedback Loop With Browser Aware Agents

    My initial frontend workflow was functional but tedious. I’d discuss frontend design in ChatGPT, take screenshots, send them back, then hand things off to an agent to implement. It worked, but every iteration felt slower than it should have been. At some point I stopped and thought: what if the agent could actually see the browser? That question led me to chrome-devtools-mcp. Once the agent had visibility into the live …

    Read post
  2. Skills Drift Problem

    A quick lesson from sharing skills across coding agents When you work across multiple projects, your skills decay faster than your code. I kept copy-pasting the same skills across repos and agent-specific directories. Each project slowly drifted. Small tweaks here, forgotten updates there. I never knew which version was the real one. The problem showed up quickly, so I fixed it at the root. The solution I landed on was …

    Read post
  3. Why Some Coding Agents Just Work

    Over the last few weeks, I’ve been working with coding agents for my development workflows, mainly Kilo Code and Codex. I came into Codex after spending significant time with Kilo, so the contrast was immediately noticeable. Kilo felt smooth out of the box. Codex felt more erratic. My first instinct was to judge the agents. Looking closer, the difference wasn’t model capability. It was defaults. Kilo ships Distinct modes for …

    Read post
rasyid hakim

Rasyid Hakim

I’m a systems-minded engineer who turns fuzzy ideas into reliable products.

I do Software Engineering, Mentoring, Data Engineering, Research As Hobby