Article

Why Harness & Loop Engineering Are the Missing Layer

by

Why Harness & Loop Engineering Are the Missing Layer The Agentic SDLC narrative has been getting louder lately — engineering teams pictured as a fleet of AI agents coordinating with each other, from requirement gathering all the way to production monitoring. But there’s one question that rarely gets a serious answer: If 12 different agents … Read more

Solving Electron SUID Sandbox Error on Linux (Ubuntu): A Quick Guide

by

Running Electron-based applications or custom IDEs on Linux can sometimes throw — including fixing Linux menu icons for portable Electron apps — a frustrating permission curveball right at launch. If you’ve encountered the infamous FATAL:setuid_sandbox_host.cc error, you are definitely not alone. Here is a quick breakdown of why this happens and how to fix it—including … Read more

I Tested 5 RAG Strategies. Only 2 Worked. Here's Why.

by
Susiloharjo

Stop Using Top-K Retrieval. Try This Instead.

Everyone talks about RAG like the hard part is the generation. It’s not. The hard part is getting the right chunks in front of the model in the first place. I’ve written before about why RAG retrieval is really a filtering problem, not a search problem, and this experiment confirmed it.

I learned this the hard way. After three weeks of testing five different retrieval strategies on 12,000 chunks of production data, I found out that the default approach — naive top-k similarity search — was giving engineers useless answers 40% of the time. They stopped trusting the bot.

Read more

Stop Building Agent Memory — Your Agent Doesn't Need It

by
Susiloharjo

Stop Building Agent Memory. Your Agent Doesn't Need It.

Last week I looked at my Redis dashboard and realized something: 4 out of 5 agent memory databases had zero queries in 7 days. I spent three weeks building them. They sit there, collecting dust, like unused gym memberships.

The agent uses exactly one memory type. The other four? Never queried. Never read from. Never written to.

This is not a post about how to build agent memory. This is a post about why I built the wrong thing, and what I learned when I stripped it all away. Earlier, I wrote about how my AI agent kept breaking — this memory experiment was part of that same journey.

Read more