https://t0ul.com/tags/operations/Recent content in Operations on t0ulHugoen-usTue, 04 Aug 2026 00:00:00 +0000https://t0ul.com/blog/admin-audit-and-one-click-rollback/Tue, 04 Aug 2026 00:00:00 +0000https://t0ul.com/blog/admin-audit-and-one-click-rollback/<p><em>Part of my <a href="https://t0ul.com/blog/the-plan/">AI Security Engineering</a> series, a local email-to-calendar agent I build, then attack, then harden. If you have not set up the lab yet, start with <a href="https://t0ul.com/blog/setting-up-the-lab/">Set up your lab</a>. The lessons are <a href="https://github.com/t0ul/ai-security-engineering">on GitHub</a>, and the agent itself lives at <a href="https://github.com/t0ul/emaildrop">t0ul/emaildrop</a>.</em></p> <h2 id="changes-go-wrong">Changes go wrong</h2> <p>The last post was about who may change the agent. This one is about what happens when a change they were allowed to make turns out to be bad: a prompt tweak that breaks the retrieval defense, a config that weakens a check. It will happen, because tuning an agent is a live, iterative thing, and the measure of an operation is not whether bad changes occur but how cleanly you can undo them.</p>