This course compares cost, quality, and effort so you can pick the right approach for your product.
Includes practical lessons, exercises, and a clear next step after you enroll.
About this course
Curriculum
Lessons are listed in order. Each one has a goal, a walkthrough, practice, and a short check before you continue.
- 01Two ways to change behaviorPrompts and examples now; weights later if you must.
- 02When prompting is enoughFormat, tone, and tool use with evals.
- 03When retrieval beats bothFacts that change should not live in weights.
- 04When fine-tuning earns its keepStyle at volume, structured output, or a domain dialect evals cannot get from prompts.
- 05Costs of owning a fine-tuneData pipelines, retraining, and model drift.
- 06A choice recordDocument what you tried: prompt, RAG, then FT last.
- 07Workshop: a complete pass on a real taskCombine the earlier lessons into one working example you can keep.
- 08Quality bar, common mistakes, and a 30-day planLock in a checklist so the skill survives after the course ends.
- 09Measure results so you know the work is actually betterAdd a simple evaluation so quality and cost are not guesswork.
- 10Ship it: handoff, monitoring, and the next projectPut the workflow where other people can use it without you in the room.