Skip to content
Gevurah

Field notes from the control plane

Build AI systems that can explain what happened.

Practical guides for operators who need durable context, visible execution, and publication gates that stay closed until a human approves the work.

2 approved articles currently visible

Choose a starting point

For a run that needs human approval, start with the approval walkthrough, then inspect the conceptual AgentRun lifecycle. The example uses a mock executor. Public API access is not available.

For context and execution records, choose a guide below. Context engineering explains what information may enter a run. Observability explains how to trace the decisions and the outcome.

The policy archive documents historical gate decisions. Its measurements belong to the dated archive; use the September evidence snapshot for the later published record.