Articles

After three days of back-and-forth, an AI agent and I had a pipeline that does the boring first edit of my videos. But it lived inside one chat, and a fresh session wouldn't remember any of it. Here's the last fix, and how I turned the whole thing into a reusable skill with checks it can't skip and gates that wait for my approval.

I wanted an AI agent to clean my videos' audio as well as Final Cut Pro does, using free tools. Two attempts sounded "not quite" right, and I couldn't explain why, which meant I couldn't fix it. Here's how a robot listener, trusted only after it passed a test I already knew the answer to, named the problem and got me to audio I can't tell apart from Final Cut's.

Every video I make starts with the same chore: deleting silences, one pause at a time. Plenty of tools promise to cut them for you, but most hand back a finished file where one bad cut is permanent, and the defaults chopped my quiet words into confetti. Here's how I got AI to cut every pause into a timeline I can still fix, why measuring my own recording beat trusting the defaults, and the half of the chore it couldn't touch yet.

An Idea Brief gives an AI agent direction. A PRD gives it boundaries. That distinction matters because an agent does not leave an unanswered product question blank. It fills the gap with an assumption

This is a companion article that will contains explanatory notes, prompts, links to GitHub Repositories with the aim of improving the learning the experience complementing the AI Agentic Android Development series on CodeTutor YouTube channel. This will be a evolving document. As more videos under the series get published, you should see content getting updated in this article

Most engineers think a harness manages tool calls. But it also decides what the model sees, what stays outside its working memory, how work is delegated, and what must be verified before action. This article turns early RLM research into a practical way to redesign long-running coding agents.

Your AI agent needs to read emails, webpages, GitHub issues, and documents to get useful work done. The problem begins when material it was supposed to examine starts influencing what it does next. This article shows where that risk appears in everyday agent workflows and how to keep permissions outside the model.

An AI art company, Midjorney, just walked into medical imaging. The real lesson isn't about the scanner — it's about where disruption now comes from, and whether the incumbents are ready for it.

AI can speed up coding without improving delivery. Learn how teams can find where work waits, measure real gains, and fix the next bottleneck. Here is a practical guide for engineering leaders, Scrum Masters, project managers, and delivery teams separating faster coding from real productivity gains.

Most first agent demos do not fail because the model forgot something; they fail because the system cannot tell current workflow progress from reusable memory. The bug appears when a user corrects the agent, a tool fails, or an old preference conflicts with the current source of truth. This article gives developers a first-principles boundary for building agents that can recover from corrections without corrupting future runs.

Karpathy’s Anthropic move is a career lesson hiding in plain sight: the badge is visible, but the work compounds. This article explores why title inflation, dry promotions, and status-heavy designations can mislead professionals — and how to judge roles by autonomy, scope, authority, and leverage instead. The punchline: don’t chase the loudest title; chase the biggest room to grow.

Android teams are using LLMs to do codebase health checks — reviewing dependency hygiene, catching security misconfigurations, flagging deprecated APIs, checking Play policy compliance. The results are disappointing. The findings feel shallow, vary run to run, and miss issues a senior engineer would catch in minutes. The model is not the problem. The project is not LLM-friendly — and making it LLM-friendly is the new engineering discipline that most teams have not yet tackled.