Phase 6 · Modern LLM engineering · Adapting models
Prompting vs RAG vs fine-tuning
Pick the cheapest approach that works.
Open this lesson Create a free account
Why it matters
"Should we fine-tune?" is one of the most common questions teams ask about LLMs, and the answer is usually "not yet". Fine-tuning is powerful, but it's slower to iterate on, ties you to one model version, and is often used to solve problems it's bad at, like teaching facts. Knowing the order to try things in saves months and money.
What you'll be able to do
- Match the problem to the tool: prompting for instructions, retrieval for knowledge, fine-tuning for behavior and cost
- Estimate monthly cost for prompting, prompting with caching, and a fine-tuned small model
- Work out when a fine-tune pays for itself
- Plan an evaluation-first approach before choosing
Before this lesson
Next in this phase: LoRA