Who may make a change, approve it and carry it out: policy, human review and audit for AI agents and automated systems.
An agent is asked to rewrite one section of someone’s document, and the owner approves its draft. Follow that one edit to the moment it is written, and see what the grant, the approval and the component that performs the write each have to check, and what slips through when an approval names a section instead of a version.
Graph engineering and orchestration: what an arrow means, which work can overlap, why a ready task still waits, what survives an interruption, and who decides a finished result can be used.
A dependency graph can expose eligible work, but it cannot schedule a worker, define material completion or grant human authority. Here is how to separate the DAG, node contracts, runtime and revision lifecycle.
We run several independently branded automated accounts on one shared engine. They are separate on purpose: separate voices, separate subject matter, separate audiences. Separateness is the product.
We already know the shape of an accurate report that nobody acts on. This is not that. Here the monitoring is not failing.
In March 2026 we wrote a draft about agent damage and did not publish it. The number in that draft was thirteen.
An operator console that combines current system health with durable work state, so exceptions can be investigated without switching between separate service consoles.
A recoverable orchestration system for multi-step production work, using dependency state, material evidence and human review to decide what can proceed.
A governance control plane that keeps operational evidence durable and routes sensitive transitions through policy and human review.