My agent had two rules and obeyed neither

<p><a class="article-body-image-wrapper"

<p><em>The AWS Reliability Files, Part 1</em></p> <p>I told an AI a true fact about AWS. Then I had a second AI confidently insist it was wrong. Within one exchange, the first

<p><a href="https://john.onlee.io/en/blog/agent-memory-retrospective-1/" rel="noopener noreferrer">Part 1</a> was about falling in. <a

<p>A few weeks back I gave a coding agent one instruction: <em>"fix the failing import and ship it."</em></p> <p>CI went green. The agent, which I'd allowed to self-merge when

<p>Your AI system isn't going to crash. It's going to drift.</p> <p>A recommendation engine making 1.4 model calls instead of 1. A retrieval pipeline fetching 5 chunks instead of

<p>Four agents entered an infinite loop in November 2025. They ran for 11 days. The bill was $47,000. Nobody noticed until it was over.</p> <p>The team was running a market

<p>The agent generates 40 lines of code. You read the diff. You approve the change.</p> <p>What just happened there? You didn't write code. You didn't design a flow. You didn't

<p>"The Reasoning Trap." The line the authors won't quite say out loud is that the smarter your model gets at reasoning, the more likely it is to fabricate a tool that doesn't