GenAI Technique Selector

Choose the right LLM optimization for your constraint: RAG, fine-tuning, LoRA, quantization, distillation, and the cases where prompt engineering was already enough.

It covers prompt engineering, retrieval-augmented generation, full fine-tuning, LoRA and QLoRA, quantization, distillation and model routing. It is written for engineers whose LLM is too slow, too expensive, or too wrong, and who need to know which of those to fix first.

Every branch states the trade-off that decided it, so the recommendation you end on comes with the reasoning attached — something you can paste into a design note or defend in a review.