Designet af AI-drevne applikationer indebærer at vælge den rette AI-tilgang, håndtere AI's unikke karakteristika (non-determinisme, omkostninger, latency, fejl) og designe for pålidelighed omkring iboende ufuldkomne AI. Det kombinerer software engineering med AI-specifikke overvejelser.
Valg af AI-tilgang
→ 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)
