Tag
The author describes RelayOps, a prototype control plane for AI support agents that emphasizes a separation of concerns where the model proposes actions, a broker decides, and human approval is required for high-risk actions, seeking feedback on the architecture.
The author built RelayOps, an AI support agent prototype for telecom/subscription support, and shares results from a 50-ticket sample, seeking critique on handoff records, unsafe actions, audit fields, and usefulness for testing.