Operations | Monitoring | ITSM | DevOps | Cloud

I recently heard a song that was written by a girl but sung and composed by AI. It left me confused— I'm not sure if I liked it. I was a bit prejudiced and automatically hated it because it was composed by AI. Similar to many works of AI, it had a rhythm, but it was too repetitive and lacked emotions. This made me think about all the other forms of art that might be created by AI, and it left me with a bitter feeling.

When we introduced the Low Code Plugin (LCP) framework in February, the premise was simple: if a system has an API, you should be able to build a plugin for it — quickly, with minimal code, and in a way you can share with the community. The "AI-ready" part was deliberate. The framework was designed to work naturally with AI assistants, so the path from idea to working integration would be as short as possible. That design decision is now paying off.

Anthropic, the company behind Claude, ran the most honest experiment in agentic AI: they gave a version of their own model $1,000, a small fridge in the office lunchroom, and one job. Run a shop. Make a profit. They named it Claudius. Claudius did not make a profit.

Most build-versus-buy debates assume you're choosing once, at the start, and living with it. Agentic engineering doesn't work that way. The decision shows up at every layer of the stack, and the teams getting it right aren't the ones who picked "build" or "buy" as a philosophy. They're the ones who know which layer is which.