I'd counter that n8n (or most other workflow tools) can handle as much ambiguity as OpenClaw - it has a LLM call node. Stuff the ambiguous parts in there, but don't burn a rainforests worth of compute figuring out how to call the weather API each and every time.
Also, in the olden days of pre-AI, if our weather workflow did not notify us because conditions juuust failed to be met, we adjusted the thresholds. Uphill, both ways.
Don't get me wrong, I use a bunch of LLMs for automations. By prompting the model "here is what I want to achieve, here are the tools I have, figure out how to stitch them together". Actual workflows run (mostly) deterministically, with a sprinkling of "classify this image" or "summarize this text" nodes thrown in for a good measure.
Like if you want bad weather alerts, you need to specifically define every situation of "bad weather" by givin exact weather / wind / rain limits.
What happens if it's cold, windy and rainy, but every value is juust 0.1 over the threshold of notifying you? It's still objectively shit weather.
Or can n8n go through your emails and check for promo codes or sales you're looking for - in ad mails that are 90% images with text?