Ask HN: What is still hard about system design with AI?
We use Claude code internally and it does a good job generating first-pass system designs when given templates and existing architecture. It often captures the obvious components and tradeoffs quickly.
Even so, system design still seems slower than expected. People spend days aligning, gathering context, and iterating on designs that feel like they could have started much closer to a workable draft.
For those who already use AI tools while designing systems:
What parts of system design remain difficult or slow?
Where do AI-generated designs tend to break down? The thing with system design is that all typical problems has been already solved, there are already battle tested patterns and practices for virtually any problem you can face until you're ~ at the scale of Google. You don't need AI for that. And if your problem is new or unique, AI isn't gonna help much. Preparing docs, requirements and diagrams isn't the time consuming part anyway. Talking to the right people, getting management approvals, changing other teams priorities etc is the time wasting part, the technical one is already solved. That's a people problem, not an AI problem. People spend so much time debating overcomplicating early system design (API v.s. event driven, etc.). AI is pretty good at generating what you want if you tell it your LOE and resources. Taking days to work through system design is a good idea. If you aren't going to take time for humans to understand the design why bother with design? AI makes lazy people more lazy. Most people, even if they are “smart af”, are lazy. Accountability