Claude Models, Prompting & Context Engineering
5 build exercises to practise the concepts in this domain.
2.1 — Write a Model Selection Dossier
Intermediate
45 minutes
- How to characterise each pipeline stage by task shape, volume, latency tolerance, and quality bar
- How to assign the smallest model tier that clears each measured bar
- How to compute per-task unit economics for competing designs
- How to design an escalation rule with triggers and expected escalation rate
- How to write a lifecycle plan that keeps model changes eval-gated
2.2 — Redesign a One-Paragraph Prompt into a Layered Contract
Intermediate
45 minutes
- How to write an explicit role, scope, and rule-conflict contract
- How to design an output contract with a genuine escape hatch
- How to structure a template with XML tags separating static and per-request content
- How to place input-side and output-side guardrails around the model
- How to pair every refusal rule with a fallback route
2.3 — Build a Technique-to-Failure Decision Table
Intermediate
45 minutes
- How to classify production failures as format, boundary, reasoning, or rule-following
- How to select the cheapest fix on the ladder for each failure class
- How to design a diverse few-shot set with edge coverage
- How to write a CoT variant with parseable reasoning, and judge when built-in thinking replaces it
- How to price each technique at volume and decide what belongs in the cached prefix
2.4 — Write a Context Budget for a Long-Running Workflow
Advanced
45 minutes
- How to break real request context into its component costs using the usage field
- How to pre-flight requests with the token counting API
- How to compute the replay bill and find the dominant cost line
- How to match a management strategy to each context component
- How to set guardrails: ceilings, compaction triggers, and overflow alerts
2.5 — Design the Reuse Layer for a High-Volume Endpoint
Advanced
45 minutes
- How to order a prompt by stability and place the cache breakpoint
- How to compute cache economics for both TTLs at real volume
- How to refactor a prompt into shared modular sections
- How to identify what belongs in a Skill rather than the system prompt
- How to verify caching is active and alert on a collapsing hit rate