Built with Agentic Engineering -- The New Way Software Gets Made
Forget vibe coding. This is a real workflow: plan with agents, verify with QA, review as human, ship to production. Here is what it actually looks like in practice.
#agentic engineering
5 posts
Plan Mode or Bust -- Why Agents Must Think Before They Code
Every AI coding session that skips planning costs 3x more in debugging. Here is how plan mode works in Claude Code, real rejection logs, and why the QA agent rejects most first drafts.
From Agent to Production -- The Pipeline That Lets You Sleep
The full CI/CD pipeline for agentic code: spec to deploy in one workflow. Real examples from luonghongthuan.com and CubLearn. How to build the system that runs while you sleep.
Evidence-Based Debugging -- Giving Your Agent Eyes
An agent that guesses burns credits and ships bugs. An agent with Chrome DevTools, Docker logs, and semantic code understanding measures and fixes. The difference is not the model -- it is the tools.
The QA Agent -- Automated Code Verification That Actually Works
I built a QA agent that runs 10x slower than code generation and rejects plans 4-5 times before approving them. Here is the methodology, the real rejection logs, and why it changed everything.
Stay in the loop
Get notified when I publish new posts on AI, .NET, cloud architecture and more.