Nikola Petrovic's profile on Product Hunt

About

Serial founder building the trust layer for AI agent governance. My ambition is to help AI do real work without companies giving up control and to build a globally relevant company from Europe. Obsessed with cutting-edge technology, startups and the entrepreneurial life. Strong believer in the just-f****-do-it mentality.

Badges

Tastemaker

Tastemaker 5

Gone streaking 10

Gone streaking

View all badges

Maker History

IsonapseControl what AI agents can do — before they do it.
Sep 2026

🎉

Joined Product HuntJuly 28th, 2026

Forums

•

4d ago

Isonapse - Control what AI agents can do — before they do it.

Isonapse is now in public beta for Claude Code. Let AI agents do real work, without giving up control. Isonapse sits between your AI agent and the systems it can touch — files, shell, web, and tools — and enforces your rules before every action happens. You stay in control, while Isonapse creates a verifiable audit trail of what the agent did.

p/murmell

•

1mo ago

Which agent should we add next: Hermes, OpenClaw, or something else ?

Hey Product Hunt.

Murmell already runs Claude Code, Codex, Kimi, and OpenCode on the same cloud canvas. More agents are coming, and I want to prioritize what you'd actually use.

•

1mo ago

How do you monitor AI agents once they're in production?

Shipping an AI agent is only the beginning. Once it's being used by real users, monitoring becomes just as important as development.

Traditional software monitoring focuses on uptime, latency, and errors, but AI agents introduce additional questions. Are they making good decisions? Are tool calls succeeding? Are they completing tasks efficiently? Are they getting stuck or behaving inconsistently?

Nikola Petrovic