I build the agent, then I keep it alive.

In my current role, four of my agents run in enterprise production: incident triage on the ticket queue, an observability copilot over a multi-application Kubernetes estate, and a knowledge agent serving the whole business through Confluence. As a freelancer, I built a three-agent delivery pipeline that let a single engineer run a production computer vision service end to end.

That combination is the thing worth knowing about me: I have built agents inside enterprise constraints, and I have been the only engineer responsible for one. Both teach the same lesson from different directions. The interesting engineering is not making the agent capable, it is making it trustworthy.

Start from what the system must never be allowed to do. Then give it everything else.

Before I specialised in operations agents, I shipped the layers underneath them: RAG systems, multimodal extraction pipelines, forecasting models, computer vision and transformer fine-tuning. Eleven production systems in total. That history is why I am comfortable saying when an agent is the wrong answer.

I work in the open too. I write about production agent engineering on LinkedIn most days, using a content pipeline that is itself one of the case studies on this site.