Having a good Time with DO Gradient AI

I thought I provide a quick “happy camper” status update. Even though this was only a side-activity, I had an exceptionally good day working with Digital Ocean Gradient and open source models. I am working on support Agents for the rsyslog ecosystem.

rsyslog site with DO Gradient-based AI Agent. Right now, we do not auto-expand it, but this might change.

Even the small openAI OS GPT works pretty well if you give it precise instructions and a good knowledge base. I love the setup, and switching models for testing works great. Currently working on integration components (like WinSyslog as client or Grafana as final destination).

I will later see how (hopefully easy) it is to add a routing agent in front of the specialized ones. I also need to find testbeds for all of them, so that we get exposure.

Hint: directly on rsyslog.com, there is the agent in the bottom right part – it’s the default “no work needs to be done” do applet.

Disclaimer: we got Sponsorship from Digital Ocean, which enables me to experiment freely with Gradient. While I am very grateful for this, it does not influence my view of the system. We approached them, because we thought Gradient sounds great. In fact, right now it looks like it is even greater than we thought.