This is my personal opinion and I’m going straight to the point, no intro.

AI assistants such as Claude Code, Cursor, OpenCode, OpenClaw, and others are so addictive for anyone who loves building things.

Software engineers are not going anywhere. Instead, we’re getting excavators and ditching our shovels.

I authored 192 commits this year (as of May 2026) without writing a single feature solely myself. I still edit files, but mostly out of convenience. If I need just one or two lines changed, it’s faster doing it myself than asking Claude.

I guess this was an intro 🤦

In the Fall of 2025 we’ve experimented with AI agents backporting upstream patches to CentOS Stream. For more info feel free to read:

For quite some time I’ve wanted to test how prone agentic tools are to prompt injection. Let’s go.

I’ll be using Claude Code 2.1.5, 4.5 Opus in various different sessions.

Ambient Code is a platform (not covered here) and a collection of AI coding agents and workflows designed to help with software development. I decided to give it a shot and see how well their agents can analyze and contribute to one of our projects in Packit org. The first tool we are going to use is called agentready. It checks how well a project is maintained and suited for AI-assisted development.…

One of the daily tasks we have when developing AI agents is to review their runs. We have to read dozens of decisions so we can evaluate if the agents did the right thing. If not, we have to adjust our user prompts, system prompts, and tools.

Let’s review how Sonnet 4.5 performs while backporting a complex patch (with multiple conflicts).

Over the last two weeks, we’ve spent time guiding our agents to perform more advanced workflows.

It was rough. For several days I was truly frustrated, because the results were atrocious.