STPA-inspired questions tied a plain checklist in my coding agent. Their one win: Claude asking about timing. An experiment replaying three past code changes through an AI coding agent found that an STPA-inspired rule (62 words) tied a plain 35-word checklist at 6.1 real bugs found per plan out of 8, across 54 plans graded blind by two judges who agreed on 90% of calls. The STPA rule, adapted from MIT's safety method, beat the checklist only in case B, where Claude asked whether a timeout was too long (3 of 6 grades versus 0) and when to stop waiting (4 of 6 versus 0), while in case C STPA fell below no rule for Codex. The author retracted an earlier claim that STPA helped after two reviewers asked whether any "check what you might break" rule would do the same, and noted the test cannot separate STPA from a rule that merely mentions timing, since the STPA rule names "early/late" and "runs too long" and the checklist does not. STPA-inspired questions tied a plain checklist in my coding agent. Their one win: Claude asking about timing. A safety method from MIT, three replayed changes, 54 plans, two blind judges, and a headline I had to take back. STPA is a safety method from MIT that asks when an automatic action becomes unsafe. I put its questions into my AI coding agent's rules, then replayed three real past changes with no rule, with a plain "check what this could break" rule, and with STPA. On average STPA did no better than the plain rule. It won clearly in one case, where the risks were about timing. Only with STPA did Claude ask whether a timeout was too long 3 of 6 grades, against 0 or when to stop waiting 4 of 6, against 0 . The test My first version of this post said STPA helped. One question, whether a change breaks apps outside its target, had jumped from 1 in 6 to 5 in 6 in a single replay of case A. Two reviewers asked the obvious thing: would any rule that says "check what you might break" do the same? So I ran it properly. The two rules, word for word. The STPA rule 62 words : When a plan or design adds or changes something that acts automatically scaler, quarantine, drain, hook, mutating script , list each control action and ask: unsafe if missing, if wrong context, if early/late, if it stops too soon or runs too long. Name the feedback it acts on and what happens when that feedback is stale or empty. The plain checklist 35 words : Before shipping any change, check what it could affect beyond its intended target, how you would notice if it goes wrong in production, and how you would roll it back quickly. flowchart TB subgraph setup Same code, same prompt direction LR K "3 past changes" -- R "3 arms