CCA-F start here · Mind maps
Scenarios × domains
The exam shows you 4 of 6 scenarios. Each scenario tests only some of the 5 domains. Green cells are tested, according to the official guide, and the link opens the mind map that covers that cell. Grey cells are not applicable: that scenario doesn't test that domain.
| Scenario | D1 Agentic architecture 27% | D2 Tools & MCP 18% | D3 Claude Code 20% | D4 Prompts & structured output 20% | D5 Context & reliability 15% |
|---|---|---|---|---|---|
| 1 Customer Support Agent | ✓Support maps 1–3 | ✓MCP maps 3–4 | N/A | N/A | ✓Support maps 4–6 |
| 2 Code Generation with Claude Code | N/A | N/A | ✓Claude Code maps 1–3 | N/A | ✓Claude Code map 5 |
| 3 Multi-Agent Research | ✓Multi-agent maps 1–3 | ✓Multi-agent map 4MCP map 4 | N/A | N/A | ✓Multi-agent maps 5–6 |
| 4 Developer Productivity | ✓Claude Code map 2 (Explore subagent) | ✓Claude Code map 6MCP maps 1–3 | ✓Claude Code maps 1, 2, 5 | N/A | N/A |
| 5 Claude Code for CI | N/A | N/A | ✓Claude Code map 4 | ✓Extraction maps 1, 4, 5 | N/A |
| 6 Structured Data Extraction | N/A | N/A | N/A | ✓Extraction maps 1–5 | ✓Extraction map 6 |
| Scenarios testing it | 3 (1, 3, 4) | 3 (1, 3, 4) | 3 (2, 4, 5) | 2 (5, 6) | 4 (1, 2, 3, 6) |
How to read it. Each scenario tests 2 or 3 domains, never all 5. Domain 4 sits in only two scenarios (5 and 6), and Domain 5 sits in four. Because you get 4 of the 6 scenarios, every domain has at least one of its scenarios on your paper, so study all five.
Source: exam guide §5, which lists the domains for each scenario: 1 (D1, D2, D5) · 2 (D3, D5) · 3 (D1, D2, D5) · 4 (D2, D3, D1) · 5 (D3, D4) · 6 (D4, D5).
The five mind-map pages
- Support agent: when the loop stops, prompt or hook, cleaning results, escalation, several matches, exact facts
- Multi-agent research: coverage gaps, subagent context, fixed or adaptive, tools per agent, failures, sources
- MCP: config home, tool or resource, wrong tool picked, failed tool returns
- Claude Code: instruction home, plan or do, iterating, CI, long sessions, built-in tools
- Structured extraction: JSON that parses, schemas that don't invent, retries, consistency, batch, human review