benjhiggins

Hey - Really clean architecture on the outbound-only relay — solving the NAT problem that way is elegant.

Curious how you’re thinking about observability once agents are actually running. You can see which agent handled a message and where, but do you get any visibility into what happened inside the session — like reasoning steps, tool calls, token usage per convo?

The privacy routing layer is super compelling, but I’d imagine teams putting this into production would want that inner visibility too — especially for cloud agents where you’re effectively trusting a third party with execution.

How are you thinking about debugging when a cloud agent gives an unexpected response?

that's insane, love it. You've got a new subscriber.

Genius, literally the best thing I've found this week.

Everyones on the same journey of discovery I guess. Application and execution will be key , with a few failures along the way, will dertermine how AI can really support the Military in planning and executing operations. The same lessons will be learnt in the public sector as well, as more and more orgasnisations look to supplement with tooling to drive revenue and reduce overheads. Interesting times..