Post

Every time an agent explores your code base it builds up its own mental model of how the code works, and then throws that model away when the session ends. Code walkthroughs turn that model it into a step-by-step guide to bring you up to speed on any part of the system.

You can verify any task on the atelier.dev kanban board and it will automatically build a walkthrough of the acceptance criteria grounded in deep links back into the code that it wrote.

Rather than reading diffs line-by-line, you step through the agent's account of what it did and diff it against your own mental model. This is exactly the sort of high-level decision point which surfaces misunderstandings and gaps in the design. narphorium.com/blog/decisio...