Blog

Thoughts & Stories

Sharing my experiences, learnings, and adventures in tech and beyond.

Browse by Topic

DevOps & Cloud Infrastructure (138)AI & LLMs (102)Web Development (81)ERP Systems (72)Backend & APIs (60)Software Development (52)Security (28)Career Reflections (27)Cloud (15)Product & SaaS (12)AI / Machine Learning (5)University (1)Hackathons (1)

August 20268 min read

Claude Code vs Codex: Agentic Coding Compared

A fair, current comparison of Claude Code and OpenAI's Codex CLI, two agentic coding tools that live in your terminal.

August 20267 min read

DeepSeek V4 Flash: Building a Spider-Man Cafe Tracker

I recreated the Spider-Man: Brand New Day Spidey Tracker as a live cafe map for BSD and Gading Serpong, built with DeepSeek V4 Flash 0731.

August 20268 min read

How Claude Code Works: Agentic Coding Explained

A developer-level walkthrough of how Claude Code works as an agent: the tools it uses, its plan-act-observe loop, its permission model, and how it extends.

August 20268 min read

Human-in-the-Loop Design for AI Agents

Practical design patterns that keep a human in control of an autonomous AI agent before it takes costly or irreversible actions.

August 20268 min read

MCP OAuth: Why Authentication for AI Agents Is Hard

Remote MCP servers demand a full OAuth 2.1 stack, and every piece of it fights back.

August 20268 min read

MCP vs Function Calling: How AI Agents Use Tools

Function calling and MCP both let an LLM use tools, but at different layers, and you usually want both.

Showing 169–174 of 594 posts

Explore More

Projects

See the projects I've built

Experience

My professional career

Certifications

Professional certifications