Claude Models, Prompting & Context Engineering

Select models, engineer context and prompts for production, and manage long-horizon tasks.

1. 2.1The Claude Model Family and Selection CriteriaHow the Claude model tiers differ, which selection criteria matter in production, and how to make model choice an evidence-based, reversible decision rather than a guess.9 min
2. 2.2Context Engineering PrinciplesHow to treat the context window as a scarce resource, decide what enters it and when, and structure it so that attention, caching and cost all work in your favour.10 min
3. 2.3Advanced Prompting for ProductionThe prompting techniques that survive contact with production traffic, how to structure a system prompt that can be maintained for years, and the patterns to retire as models change.10 min
4. 2.4Extended Thinking and Effort ControlHow Claude's reasoning features work, how configuration has moved from fixed budgets to adaptive thinking and effort levels, and how to decide where thinking earns its cost and latency.9 min
5. 2.5Prompt Caching Strategy at ScaleThe mechanics of prompt caching, how to design request assembly so that a fleet of services shares cache hits, and how to diagnose the silent invalidators that make hit rates collapse.10 min