Agentic Engineering Anti Patterns
simonwillison.netThe biggest version of this I see is when people batch-submit PRs to popular open source repos with agent-generated code. The maintainer gets flooded with well-formatted but shallow contributions that take more time to review than they save.
What helps is treating agent output as a first draft. My workflow: let the agent generate, then spend equal time reviewing as if a junior dev wrote it. If I cannot explain every line in the diff, it does not ship.
The culture shift matters too. Teams should normalize asking "did you review this yourself?" without it feeling accusatory. A simple PR template checkbox like "I have personally tested these changes" sets the right expectation.
Great topic, and great start. Another anti-pattern I see is: "Do not file PRs on code that you hasn't been reviewed for accessibility to a human".
At first glance, this could seem to be redundant (downstream) of the suggested anti-pattern. But reviewing code doesn't necessarily mean reading all of it. A reviewer might want to unpack a function you already know well, because you specified it and saw it work (but never read).
am I dumb or does this article just have one anti-pattern making it not plural
I haven't thought of any more yet. It's a work in progress.