ccaf-study-guide

# CCAF Study Guide (910/1000): Your Last Cheat Sheet Unofficial prep for **Claude Certified Architect - Foundations (CCAF)**. I scored **910/1000** on the exam and open-sourced the notes I used as my last cheat sheet. The CCAF exam is scenario-heavy: you pick the right architecture when an agent forgets context, a generic tool keeps misfiring, or a customer escalation lands mid-process. The official guide covers all of it, but it's dense. This repo distills **30 exam tasks** across 5 domains into two complementary views: **what to do** (patterns and traps) and **what not to do** ([anti-patterns catalog](study/03-anti-patterns-catalog.md)). **What's inside:** a one-page concept map, a trap taxonomy (why wrong answers sound right), and an **[anti-patterns catalog](study/03-anti-patterns-catalog.md)** that maps every "avoid / do not / instead of" warning from the official guide. If a distractor sounds plausible, check the traps first; if it sounds like a shortcut the guide rejects, check the anti-patterns. Use this as your **last cheat sheet**, not your textbook. Take a mock first to see where you stand, then study the official guide and use this repo to close the gaps. ## Start here 1. Get access via [Anthropic Academy / Skilljar](https://anthropic.skilljar.com/claude-certified-architect-foundations-access-request) 2. Take a free mock ([CyberSkill](https://ccaf.cyberskill.world/) or [Certification Guide](https://claudecertificationguide.com/)) to baseline where you stand 3. Read the **official exam guide** at least **3 times** (I printed mine to cut digital distractions) 4. **Practice on a real project** alongside study: build an agent loop, wire up MCP tools, or configure Claude Code. Scenarios stick better when you've lived them. 5. Retake mocks until you hit **900+**, then book the real exam Full workflow: [study/README.md](study/README.md) ## Study path | Step | Doc | What you get | | ---- | ---------------------------------------------------------- | ----------------------------- | | 1 | [Concept map](study/00-concept-map.md) | All 30 tasks on one page | | 2 | [Mock exam trap guide](study/02-mock-exam-trap-guide.md) | Why wrong answers sound right | | 3 | [Anti-patterns catalog](study/03-anti-patterns-catalog.md) | What the guide says not to do | | 4 | [API & product FAQ](study/04-api-and-product-faq.md) | Exam vs production gotchas | **Domain weights:** Agentic Architecture (27%) · Tool Design & MCP (18%) · Claude Code Config (20%) · Prompt & Structured Output (20%) · Context & Reliability (15%). See the [concept map](study/00-concept-map.md) for task breakdown. **Recommended Academy path:** Building with the Claude API → Claude Code in Action → Introduction to Agent Skills → Introduction to MCP. ## Trap cheat sheet High-yield patterns from mock exams. Full taxonomy: [02-mock-exam-trap-guide.md](study/02-mock-exam-trap-guide.md). ``` Context filling up (multi-issue) → 5.1 Summarize resolved; active thread full Generic tool, inconsistent output → 2.1 Split typed tools Messy source formats → 4.3 Schema + normalization in prompt Function behind wrappers → 2.5 List aliases → grep each Agent forgets mid-conversation → 5.1 Pass full messages array Unknown bug path → 1.6 Adaptive investigation Long code exploration (30+ min) → 5.4 Scratchpad file Mid-process escalation → 1.4 Structured handoff brief Angry + no context → 5.2 Acknowledge + one question Identity multi-match → 5.2 Ask identifiers, never guess ``` ## More - Community links and extra mocks: [resources/links.md](resources/links.md) - Disclaimer: [DISCLAIMER.md](DISCLAIMER.md) - License: MIT ([LICENSE](LICENSE))