Your question is Fine-Tuning vs Prompting. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
Describe the trade-offs between fine-tuning a model versus using advanced prompt engineering and embeddings.
Compare the approaches for a production LLM feature, without assuming a specific company, domain, or model. Discuss how you would choose between them based on task stability, data availability, quality requirements, latency, inference and training cost, update frequency, privacy, and operational complexity. Include how you would evaluate both approaches before deployment, and address hallucination, prompt injection, and knowledge freshness. Your answer should recommend a decision framework rather than claiming that one approach is always superior.