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).
What's inside: a one-page concept map, a trap taxonomy (why wrong answers sound right), and an anti-patterns catalog 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.
- Get access via Anthropic Academy / Skilljar
- Take a free mock (CyberSkill or Certification Guide) to baseline where you stand
- Read the official exam guide at least 3 times (I printed mine to cut digital distractions)
- 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.
- Retake mocks until you hit 900+, then book the real exam
Full workflow: study/README.md
| Step | Doc | What you get |
|---|---|---|
| 1 | Concept map | All 30 tasks on one page |
| 2 | Mock exam trap guide | Why wrong answers sound right |
| 3 | Anti-patterns catalog | What the guide says not to do |
| 4 | API & product FAQ | 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 for task breakdown.
Recommended Academy path: Building with the Claude API → Claude Code in Action → Introduction to Agent Skills → Introduction to MCP.
High-yield patterns from mock exams. Full taxonomy: 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
- Community links and extra mocks: resources/links.md
- Disclaimer: DISCLAIMER.md
- License: MIT (LICENSE)