Should you read the code, is RAG dead, and did Skills kill MCP?

A GitHub developer advocate argues that people must still review code written by AI, with effort matched to the risk, until they can explain and own the result.

GPS, a developer experience advocate at GitHub, recapped an episode of the GitHub Podcast that tested five popular claims about AI. The first claim is that nobody needs to read code written by AI. Her answer is that developers are still responsible for the code, but not every line deserves the same attention.

• A rewrite of the sign-in code of a live product deserves a different review from an experiment with a page's styles.
• Her rule is to "review until you can explain and own the outcome."
• Sometimes the review starts before the agent writes anything, with reading the existing code and planning. Sometimes the generated code itself needs most of the attention, such as its error handling, permissions and tests.

A team can match the depth of review to the risk of each AI-written change and stop when the reviewer can explain it. This is GitHub's advice to developers, and its use by reviewers outside engineering is an inference.

Derived by Working Surface from the article. Source line: review until you can explain and own the outcome.

21 September 2026: when AI agents build quickly, people keep the review, the responsibility and the promises an interface makes.