Monday, August 24, 2026

    Model Selection and Optimization

    16.8% of the exam · about 8.9 of 53 items

    Model Selection and Optimization

    16.8% of the published blueprint, which works out at about 8.9 items on a 53-item form. These are expected values across forms, not a promise about the form you sit.

    4 published sub-domains, each separately weighted

    • Technical Fundamentals

      6.1% · 3.2 items2+ items

      Foundational technical concepts supporting AI application development, including basic engineering practices (integrating with SDKs that wrap REST APIs, websockets).

    • LLM Fundamentals

      5.2% · 2.8 items2+ items

      Basic understanding of LLMs (tokens, context windows, sampling, non-determinism, next-token generation), model options (fast mode, extended thinking, adaptive thinking, effort levels), and fundamental prompting techniques (zero-shot, single-shot, multi-shot).

    • Cost and Token Management

      2.8% · 1.5 items1–2 items

      Token budgeting and cost management techniques for Claude applications, including token usage tracking, cost modeling, and caching techniques (prompt caching, cache check-pointing) for cost optimization.

    • Model Selection and Tradeoffs

      2.7% · 1.4 items1–2 items

      Claude model capabilities (Opus vs. Sonnet vs. Haiku use cases, adaptive thinking support), tradeoffs across quality/latency/cost parameters, and breaking behavior changes across model releases when selecting models for tasks.

    6 concept cards — tap one for the example, the instinct and the trap

    Primary sources for this domain

    The guide’s “How to Prepare” section says to review official Anthropic documentation for the Claude API, models, prompt engineering, Claude Code, Skills and MCP. These are those pages, taken from each site’s own llms.txt manifest rather than from a search.

    Working the whole blueprint? The study guide carries the eligibility rules, the exam logistics and the full sub-domain allocation table.