2.1Beginner35 minutes
2.1 — Select model tiers for a high-volume FAQ deflector
What you will learn
- Write accuracy floor and latency/cost SLAs
- Map traffic mix to relative model tiers
- Price unit cost at expected volume and define revisit triggers
← Build Exercises
Domain 2
Claude Models, Prompting & Context Engineering
5 build exercises to practice the concepts in this domain.
2.2Intermediate40 minutes
2.2 — Design system prompt, template, and guardrail split for a support agent
What you will learn
- Write explicit criteria, formats, and boundaries
- Template a multi-step support flow
- Separate soft prompt guidance from hard tool-path controls
2.3Intermediate35 minutes
2.3 — Choose PE techniques for a latency-sensitive ticket classifier
What you will learn
- Name the failure mode before picking a technique
- Prove zero-shot or few-shot before CoT
- Justify CoT only with measured gain vs latency
2.4Advanced40 minutes
2.4 — Budget and trim context for a tool-using support agent
What you will learn
- Allocate a per-layer context budget
- Protect verbatim IDs outside narrative summaries
- Trim tool results with structured retention
2.5Advanced40 minutes
2.5 — Refactor a review agent for caching, modules, and Skills
What you will learn
- Split stable prefixes from volatile turn content
- Apply caching and shared modules
- Isolate a verbose playbook as a Skill