[lgiordano_notte]

LLM-based coding only really works when wrapped in structured prompts, constrained outputs, external checks etc. The systems that work well aren’t just 'LLM take the wheel' architecture, they’re carefully engineered pipelines. Most success stories are more about that scaffolding than the model itself.

[CivBase]

Does anyone provide a good breakdown of how much time/cost goes into the scaffolding vs how much is saved from not writing the code itself?

[lgiordano_notte]

A breakdown would be interesting. I can’t give you hard numbers, but in our case scaffolding was most of the work. Getting the model to act reliably meant building structured abstractions, retries, output validation, context tracking, etc. Once that’s in place you start saving time per task, but there’s a cost up front.