Inspection Agent
Photographs every part, calls the ones that look wrong, and hands an inspector a decision instead of a shift of scanning. Written for a precision manufacturer making machined components for aerospace and medical device customers, where the constraint was never how hard anyone was trying. A Sandia study of 82 inspectors on precision parts measured an 85% hit rate on defective items and a 35% false-alarm rate on good ones, and detection starts falling inside the first 30 minutes on task. Six stations, run as a loop: what station 6 learns from the overrides and the escapes is what station 2 calls on.
{{ g.n }}
{{ g.name }} · {{ g.sub }}
{{ g.desc }}
Subagents ({{ g.acount }})
{{ a.name }}{{ a.code }}{{ a.name }}{{ a.auto }}{{ tk }}
The workbench · subagents send notes, you make the human calls
SUBAGENT NOTES
{{ nt.ini }}{{ nt.who }} {{ nt.text }}
YOUR TASKS · HUMAN IN THE LOOP
{{ g.t1 }}
{{ g.t2 }}
{{ g.tnote }}
{{ g.btn }}
{{ g.wait }}
YOUR TASKS · NONE AT THIS STEP
{{ g.was }}
{{ g.ev1L }}{{ g.ev1V }}
{{ g.ev2L }}{{ g.ev2V }}
{{ g.ev3L }}{{ g.ev3V }}
✓
Cleared for full autonomy{{ g.sign }}
Put a person back on this step
How to read this map
{{ lg.code }}{{ lg.text }}
A person is in the loop wherever a part's fate or the standard itself is decided. Four of the six stations refuse to proceed on their own, Flag Reviewing, Lot Deciding, Sample Checking and Model Retraining, and those are the four a person carries. Everywhere else the subagents run at volume and reach you only when they cannot settle something.
The loop closes
Station 6 does not end the quarter. A retraining accepted after reading the overrides is what station 2 calls on, which is why the same escape stops happening.