Dizajniranje AI-pogonskih aplikacija uključuje izbor правog AI pristupa, rukovanje jedinstvenim karakteristikama AI-ja (nedeterminizam, cijena, latencija, greške) i dizajniranje za pouzdanost oko inherentno nesavršenog AI-ja. Kombinira softversko inženjerstvo s AI-specifičnim razmatranjima.
Izbor AI pristupa
→ PROMPTING (LLM APIs) → for most LLM tasks (simplest); good prompts go far
→ RAG → to ground answers in your own/current DATA (reduce hallucination)
→ FINE-TUNING → for specific behavior/style prompting can't achieve
→ TRADITIONAL ML → for structured prediction/classification with data
→ PRE-BUILT services → vision, speech, etc. (don't reinvent)
→ match the approach to the problem (often: prompting + RAG for LLM apps)
