Would like to revive this thread now that Hamilton has an API for the ML_Prep, a low code solution that pivoted 180 degrees to having a fully programable API.
I think this shows how a low code interfaces isn’t always the best. Especially now with AI; I can feed the API JSON and ask Claude to make me a normalization protocol. Yes, it might not 1 shot it, but to be fair these are small scripts compared to what others are doing with LLM’s (with 1M token context windows most of our scripts probably use .1-1% of that). I think it’d probably work right away (don’t have a ML_Prep to test with).
I see a future where low code interfaces are gone due to LLM’s… I think all companies should be focusing on making their robots to integrate with LLM’s by using API’s (or pylabrobot 
). The company that endorses a fully standardized language that actually works with LLM’s and Git will easily take over the entire market, just my two cents. Everyone has had similar hardware for a decade now… the market leader will be ease of use to code. This would allow anyone to program a protocol, what they wanted with GUI interfaces to begin with. Yes you will still need an engineer to validate and tweak for liquid classes, niche assays, and labware but you can 1 shot 90% of the code.