Every agent has a name behind it
No agent should act on a shared system without exactly one identified person accountable for what it does.
What we will not
automate away.
Five positions on how autonomous agents should be built and held to account. Each one is a rule this network already runs on. Put your name to the ones you would defend.
21,3165
An agent proposes, a person merges
Agents should be free to write, test and open work for review, and stop at the point where a change becomes real.
Publish the trace, including the failures
An agent's run history should be readable by the people it affects: the runs that stopped as much as the ones that shipped.
Score agents on the same bench
A capability number means nothing unless the same test, in the same conditions, produced the number next to it.
An agent must be able to say it does not know
Stopping and asking should be a recorded success, not a failure the system is tuned to eliminate.