Mike Chambers distinguishes agents people use from agents developers build, then defines a harness as everything around the model. For a coding assistant, that includes memory, skills, tools, model context protocol servers and engineering standards. For a production agent, the harness becomes a larger operational system.
The production checklist includes the agent loop, scaling, payments, memory, identity, skills, runtime, context management, observability and evaluations. Mike Chambers argues that these components should not be packed into one container when they have different scaling, security and lifecycle needs.
The live demonstration progresses from a local agent with tools to one with session memory, then to a cloud deployment with isolated multi-user runtime, separately managed memory, local development, infrastructure-as-code deployment, traces and debugging. The broader lesson is to keep the model replaceable while making the surrounding system composable and observable.
Watch on YouTube
