Because they want it to be executed quickly and cheaply without blocking the workflow? Doesn’t seem very weird to me at all.

what you are suggesting would be like a truck company using trucks to move things within the truck

More like a car company transporting their shipments by truck. It's more efficient

Well, regex doesn't hallucinate....right?

Because they actually want it to work 100% of the time and cost nothing.

Good to have more than a hammer in your toolbox!

because impact of WTF might be lost in the result of the analysis if you solely rely on LLM.

parsing WTF with regex also signifies the impact and reduces the noise in metrics

"determinism > non-determinism" when you are analysing the sentiment, why not make some things more deterministic.

Cool thing about this solution, is that you can evaluate LLM sentiment accuracy against regex based approach and analyse discrepancies

I used regexes in a similar way but my implementation was vibecoded, hmmm, using your analysis Claude Code writes code by hand.

They had the problem of sentiment analysis. They use regexes.

You know the drill.

Using regex with LLMs isn't uncommon at all.

hmm not a terrible idea (I think).

You have a semi expensive process. But you want to keep particular known context out. So a quick and dirty search just in front of the expensive process. So instead of 'figure sentiment (20seconds)'. You have 'quick check sentiment (<1sec)' then do the 'figure sentiment v2 (5seconds)'. Now if it is just pure regex then your analogy would hold up just fine.

I could see me totally making a design choice like that.

They're searching for multiple substrings in a single pass, regexes are the optimal solution for that.