A confidence score makes an automation rule look easy. My JEV email classification PoC showed why the score must first be tested against outcomes and weighed against the consequences of a wrong decision.
MCP does not require a rebuild of stable REST APIs. The architectural choice is how to expose each capability to agents through OpenAPI, vendor hosted MCP, or a shared custom MCP surface.
A manager’s PowerPoint template onboarding job reveals why an Agent Run cannot own the identity, state, and recovery of long running Enterprise AI work.
I built a JEV and n8n email classification PoC expecting to focus on model performance. The harder work was defining the active request, writing category boundaries, and deciding when a model judgment becomes a business decision.
OpenAI’s managed Codex harness can take over much of the work of running an agent. The harder question is which responsibilities still belong to the application, and how to make the runtime replaceable.