I've found that AI coding agents are good at building new projects from scratch. Even better if they're building a smallish project with features remixed from known projects, presumably in their training set.Where they've fallen apart for me is when working in existing, large, projects. When adding new features, or especially when fixing, non trivial, bugs.Could be skill issue with writing prompts on my part. But since I have the same prompting skills when starting new projects and fixing bugs, I feel like it's an issue within the choosing agents.