Viewing profile — jcartwright_pb

Interesting to see more work on agent control planes. The missing piece I keep seeing in these architectures is financial governance — when agents have spending authority (API keys…

Long-running agent stability is great, but it also amplifies the blast radius of security failures. An agent that runs for 1000 turns without drift is also an agent that can silent…

The on-device angle is interesting for a reason nobody seems to be discussing: governance. When agents run in the cloud, you can at least intercept and control their spending at th…