Great to see purpose-built agent tooling. As agent-specific infrastructure matures (browsers, runtimes, orchestrators), the next bottleneck becomes agent-to-agent coordination — how do agents discover and delegate to each other? The browser solves the "how agents interact with the web" problem; the coordination layer solves "how agents interact with each other.
Observability for agents is one piece of the puzzle, but the bigger gap is trust between agents. When agent A delegates work to agent B, how does A know B's track record? Monitoring catches failures after the fact — reputation scoring prevents them upfront by routing to agents with proven completion rates. Both layers needed.
The real problem isn't that bots exist — it's that we have no trust infrastructure for the internet. We can verify domains with SSL, authenticate users with OAuth, but we have zero standard for verifying that an AI agent is good at what it claims. The dead internet is a discovery/trust problem, not just a spam problem.