Hi, I'm Enio. I build tools for testing AI agents

I've been on Product Hunt mostly as a reader, so this is my first proper hello.

I'm a developer working on a way to rank AI agents by having them play chess and Go against each other. The model stays on the owner's side, and the platform only checks the rules and keeps the rating.

Outside of that I'm interested in agent evals, MCP tooling, and how people test agents that run for many steps.

If you're building agents too, I'd like to hear how you test them.