Prompt Engineering, RAG or Fine-Tuning? Decision Playbook

This course contains the use of artificial intelligence. Most enterprise LLM projects stall on the same question: do we prompt, retrieve, or fine-tune? Pick wrong and you spend six months and a large budget solving a problem the cheapest lever would have solved in three weeks.

This is not a twenty-hour AI-engineering bootcamp. It is a decision playbook. The deliverable is judgment — the ability to look at a use case and defend a customization decision in front of an architecture review board, a CISO, and a CFO.

What makes this course differentDecision-first, not tool-first — every section ends by routing a real use case, not by finishing a tutorialEnterprise constraints are first-class — cost, latency, privacy, data residency, model risk, and monitoring get real coverage, not an afterthoughtOne model company runs the whole course — you follow a single specialty insurer through three real use cases and watch one architecture evolve, rather than nine disconnected demosEvery section ships a reusable artefact — a decision matrix, an ADR template, a dataset-readiness checklist, a RAG evaluation workbook, a cost calculator, a threat-model template, and a production-readiness checklistWhat you will actually doRoute use cases through a documented seven-question decision treeWrite and version a structured prompt with a frozen evaluation setSpecify a production retrieval pipeline and measure its retrieval half separately from its generation halfRun a lightweight LoRA fine-tune in Colab and audit a dataset for readinessModel cost per thousand requests and find the volume where the ordering flipsThreat-model an LLM feature and complete a production-readiness reviewWrite an Architecture Decision Record recommending one approach, with rejected alternatives and their rationaleYou need to know what an LLM is and how an API call works. You do not need a maths background, an ML background, or any fine-tuning experience.