Momcilo Savic

I've noticed that most founders spend a lot of time asking whether an AI agent works and much less time asking what happens after people start relying on it.

Before launching, I'd want clear answers to five questions:

1. What can the agent access?

Data access tends to expand over time. It's worth knowing exactly which systems, documents, and information sources are within reach.

Running into a wall I haven't seen written about clearly.

Single agent in production is fine. Logs, traces, normal observability.

Let me know if this sounds familiar:

Me: Implement issue ABC and satisfy every acceptance criterion in the spec.