The barriers to AI engineering are crumbling fast

The only remaining question being, why would you want to?

Funny enough, Helix doesn't know either! They put together a contest hoping that you'll figure it out: https://blog.helix.ml/p/llm-app-challenge-with-helix-10

You might say this is about Helix being small and trying to break into a crowded market, but OpenAI and Google offered similar contests / offers that asked users to submit ideas for LLM applications. Considering how many LLM sample apps are either totally useless ("Walter the Bavarian, a chatbot who gives trivia about Oktoberfest!") or could be better solved by classical programming ("a GPT that automatically converts currencies to USD!), it seems AI developers have struggled to find a single marketable use case of LLMs outside of codegen.

Codegen, contentgen, and driving existing products in human language (which you can largely bucket into interactive codegen)