Human-AI partnerships are for alignment, not capability

Sean Goedecke, a software engineer, argues that engineers working with coding agents now add most value by aligning the output with their company's technical values.

Sean Goedecke, a software engineer and essayist, notes that many people compare AI-assisted programming to human and computer partnerships in chess. He says coding agents already make fewer mistakes than he does and work far faster. Left alone, however, their output is hard to maintain and trades away real requirements for invented ones.

• Goedecke lists habits he sees in AI models, such as long comments above functions, hundreds of useless unit tests and extra text added across websites.
• He argues that each company's technical values differ, so an engineer who changes companies has to learn them again.
• He expects an aligned AI model would need to adapt to a wide range of company values on the fly.
• His practical advice is to describe high-level values to the agent explicitly.

Teams may need to write down their technical values so that agents and new staff can read them; this is an inference and is not the author's claim. The essay is one engineer's opinion, not a team report.

Derived by Working Surface from the article; more in the Playbook. Source line: In other words, my primary value is not that I help the AI write better code, it’s that I align the AI with the values of my organization.

3 October 2026: the written material that steers AI agents has become a maintained product that needs an owner, and setups without one decay into tangles that only the AI can navigate.