Venkata Krishna Reddy Atchi 3 4 (October-December) A common safeguard for autonomous agents is to have a person approve their actions But people tire and a tired reviewer misses more This paper asks how many actions should be sent to a human and which ones when the reviewers catch probability falls as the recent workload rises We model a reviewer whose catch probability declines with recent busy time and a risk scorer that ranks actions We prove that when the scorers ranking is well behaved the share of bad actions caught is a concave function of the review rate so there is a single best rate and that for a Gaussian scorer reviewing everything is never the best choice once fatigue is present At the optimum an action is worth sending to the reviewer only if its probability of being bad exceeds a threshold that depends on the fatigue strength and on how much is already being reviewed In a minutebyminute simulation of an eighthour shift 1000 runs per setting sending every action to the reviewer missed 173 of about 30 bad actions because the mean catch probability fell to 043 Sending only the riskiest 36 of actions missed 112 a reduction of 35 with 67 fewer reviews A threshold computed from the theory with no tuning matched the best tuned threshold A controller that simply holds the reviewers load near a target did not beat a welltuned fixed threshold and learning the fatigue strength from audits worked only when about 30 of reviewed bad actions were audited Whether scheduled breaks help depends on the fatigue model they did nothing when fatigue followed recent load alone and cut misses by 17 to 23 when a slow cumulative component was added All results are from simulation with assumed parameters Copyright (c) International Journal of Computer Science, Engineering and Artificial Intelligence. All rights reserved 2026