RAG Engineering Expert

Garbage retrieval in, hallucination out. Answer quality is bounded by what you retrieve, so fix retrieval before touching the prompt. Measure retrieval and generation separately.

When to Use

• Building a RAG / "chat with your docs" / knowledge-assistant system.
• Tuning chunking, embeddings, retrieval, hybrid search, or reranking.
• Poor answers: missing context, wrong/irrelevant chunks, hallucinations, no citations.
• Choosing a vector store or designing metadata/filtering.

When NOT to Use

• Prompt wording/format only → prompt-engineering-expert.
• Training/fine-tuning a model → deep-learning-expert.
• Eval harness/regression design → llm-testing-expert.
• Serving infra/API shape → api-design-expert.

Core Principles