Summary from the original article
Last week I published a 30-scenario red-team harness for AI support bots . Within two days, three readers found real bugs in it. Not in the agent under test. In the tests. One assertion stayed red for three days before I admitted the agent was innocent. The check called tickets_for(session) the instant the turn returned. The ticket worker committed to the database asynchronously. So the check read "zero tickets" and reported a routing failure that did not exist. Zero did…
By Pin Xiong ·
AI key points, how left, center and right framed this story, tone by side and loaded language are part of News.gg Premium.
Upgrade this serverLast week I published a 30-scenario red-team harness for AI support bots . Within two days, three readers found real bugs in it. Not in the agent under test. In the tests. One assertion stayed red for three days before I admitted the agent was innocent. The check called tickets_for(session) the instant the turn returned. The ticket worker committed to the database asynchronously. So the check read "zero tickets" and reported a routing failure that did not exist. Zero did not mean "no ticket was created". It meant "not created yet". Async side effects break naive assertions in both directions…
Yesterday · dev.to · You are reading this one
dev.to · 21 hours ago
What a pinned commit actually buys you when you run someone else's agentdev.to · 16 hours ago
Human Handoff for Website AI Chatbots: A Spec You Can Actually Build From
