Posts

Right now, there are many AI assistants available for coding. Claude Code, GitHub Copilot CLI, Codex CLI, and Gemini CLI are some of the most widely used options for terminal-based workflows. While it is difficult to determine feature parity, and probably not helpful, there are many common features supported by these assistants such as: custom agents, skills, MCP, hooks, and slash commands. In this post, I’ll explore sharing these capabilities across multiple assistants. ...

On my last post, I have discussed how Sharp Cred Manager now supports managing Azure Key Vault secrets in addition to certificates. Today, I released v2 beta6 version of Sharp Cred Manager which adds the ability to track App Registrations and their secrets and certificates. Originally, this was planned as a future feature, but the momentum on v2 was good and I decided to add it now. Similarly to the previous version, the general look and feel is preserved, with minor adjustments to display secrets in the dashboard and webhook notifications. Take a peek below: ...

I see it happening too often. A credential expires, goes unnoticed, and causes downtime. Granted, you should have DevOps processes in place to handle credential rotation, but if you don’t, the risk is significant. That’s why I created Sharp Cert Manager a few years ago as a simple tool to help monitor and notify about certificate expiration. It might not fix the problem for you, but it will nag you often enough that you will probably take action. ...

I’ve been delegating more coding than ever to AI in the last few months. Over time, I noticed some common patterns that work and common pitfalls. I’ve distilled what works for me when using AI for most of the heavy lifting. This isn’t about prompt engineering tricks—it’s about fundamentally rethinking your development workflow. If you’re an experienced engineer looking to delegate more coding to AI while maintaining quality and control, this guide will help you assess where you are and where you could be. ...

I heard about Ralph Wiggum as a Software Engineer a couple of months ago from Geoffrey Huntley’s article. The idea was intriguing and I wanted to build something real with it. At the same time, I’ve had a feature on the backlog of Sharp Cooking for about a year now. I knew it wasn’t an easy one and it was never a critical feature either. What a great opportunity! I highly recommend reading the original article as well as the snarktank/ralph implementation that was created since. The idea is simple yet powerful: create a detailed spec, set up the AI agent, let it run and learn in an autonomous loop until it completes the spec implementation. This post documents my experiment that became a production feature. ...