Shipping is the foundation

Software engineer Sean Goedecke argues that AI tools have not made shipping easy, because shipping needs context about systems and people that AI models lack.

Sean Goedecke, a software engineer who writes about working at large technology companies, argues that shipping changes is the skill every other senior skill depends on. Engineers who cannot ship give bloated estimates and turn small requests into large projects. He says AI tools help with shipping but cannot run it from start to finish.

• Goedecke compares every alternative, such as writing a ticket or delegating a task, against the default of making the change oneself.
• Managers give senior engineers many small requests, and those requests are meant to avoid slow formal resourcing.
• In his account, shipping includes finding the shortest practical path, solving small problems on the way and keeping managers informed.
• He writes that even frontier AI models cannot be left to change a codebase unsupervised, and that engineers still need to read the code.

Engineering managers who choose leads for work done with AI agents may want people who can still make and judge changes themselves. This is an inference and is not the author's claim. The piece is a personal essay and offers no data.

Derived by Working Surface from the article; more in the Playbook. Source line: LLMs can help with that process, but they cannot run it end-to-end.

5 October 2026: when AI agents produce the output, the remaining work is judging it: knowing the way to done and making each change visible to the person who must accept it.