Skip to content
CCAF Preparation

The six exam scenarios

The CCAR-F exam does not ask isolated questions. Every item sits inside one of six published scenarios — a realistic production context that frames a whole group of questions — and 4 of the 6 are drawn at random for any given sitting.

That is unusually generous: the exam tells you in advance what situations it will put you in. Knowing them well enough to recognise which one you are in, and which domains it leans on, is worth real marks. Each page below has the official framing, what the scenario actually tests, the mistakes it is built to catch, and the lessons that cover it.

  1. 1Customer Support Resolution AgentBuilding a customer support resolution agent with the Claude Agent SDK. It handles high-ambiguity requests — returns, billing disputes, account issues — through custom MCP tools (get_customer, lookup_order, process_refund, escalate_to_human), targeting 80%+ first-contact resolution while still knowing when to hand off to a human.Primary domains: Agentic Architecture & Orchestration · Tool Design & MCP Integration · Context Management & Reliability
  2. 2Code Generation with Claude CodeUsing Claude Code to accelerate development — generation, refactoring, debugging and documentation — integrated into a team's workflow through custom slash commands, CLAUDE.md configuration, and judgement about when plan mode beats direct execution.Primary domains: Claude Code Configuration & Workflows · Context Management & Reliability
  3. 3Multi-Agent Research SystemBuilding a multi-agent research system with the Claude Agent SDK: a coordinator delegates to specialised subagents — web search, document analysis, synthesis, report generation — to produce comprehensive, cited reports.Primary domains: Agentic Architecture & Orchestration · Tool Design & MCP Integration · Context Management & Reliability
  4. 4Developer Productivity with ClaudeBuilding developer productivity tools with the Claude Agent SDK: helping engineers explore unfamiliar codebases, understand legacy systems, generate boilerplate and automate repetitive work — using the built-in tools (Read, Write, Bash, Grep, Glob) and MCP server integrations.Primary domains: Tool Design & MCP Integration · Claude Code Configuration & Workflows · Agentic Architecture & Orchestration
  5. 5Claude Code for Continuous IntegrationIntegrating Claude Code into a CI/CD pipeline for automated code review, test-case generation and pull-request feedback — designing prompts that produce actionable feedback and keep false positives down.Primary domains: Claude Code Configuration & Workflows · Prompt Engineering & Structured Output
  6. 6Structured Data ExtractionBuilding a structured data extraction system: pulling information out of unstructured documents, validating output against JSON schemas, holding accuracy high, handling edge cases gracefully, and integrating with downstream systems.Primary domains: Prompt Engineering & Structured Output · Context Management & Reliability