Scenario practice

The real CCAR-F exam doesn't ask questions in isolation. It presents four scenarios, picked at random from a published set of six, and each frames a run of questions about the same system. Practice one scenario with instant feedback, or sit four at random with answers held until the end.

Exam-style set

Four scenarios at random, every question for each, no feedback until you finish. Results by scenario and by domain, then a full review.

The six scenarios

Scenario 1

Customer Support Resolution Agent

You're building a support agent with the Claude Agent SDK that resolves ambiguous customer requests such as returns, billing disputes, and account problems. It reaches your backend through custom MCP tools: get_customer, lookup_order, process_refund, and escalate_to_human. The goal is to resolve at least 80% of contacts on first touch while recognizing the cases a human should take over.

Agentic Architecture & Orchestration · Tool Design & MCP Integration · Context Management & Reliability

Scenario 2

Code Generation with Claude Code

Your engineering team relies on Claude Code to generate, refactor, debug, and document code. You're responsible for fitting it into the team's workflow: custom slash commands and skills, a sensible CLAUDE.md setup, and knowing when a task calls for plan mode and when direct execution is enough.

Claude Code Configuration & Workflows · Context Management & Reliability

Scenario 3

Multi-Agent Research System

You're building a research system on the Claude Agent SDK in which a coordinator agent delegates work to specialized subagents: one searches the web, one analyzes documents, one synthesizes findings, and one generates reports. Given a topic, the system produces a thorough report with citations.

Agentic Architecture & Orchestration · Tool Design & MCP Integration · Context Management & Reliability

Scenario 4

Developer Productivity with Claude

Your team is building internal developer tools on the Claude Agent SDK. The agent helps engineers find their way around unfamiliar or legacy codebases, generates boilerplate, and automates repetitive chores. It works through the built-in Read, Write, Bash, Grep, and Glob tools, plus connections to Model Context Protocol (MCP) servers.

Tool Design & MCP Integration · Claude Code Configuration & Workflows · Agentic Architecture & Orchestration

Scenario 5

Claude Code for Continuous Integration

Claude Code runs inside your CI/CD pipeline. It reviews pull requests automatically, proposes test cases, and posts feedback on the PR. The central challenge is writing prompts and configuration that produce actionable findings while keeping false positives low enough that developers keep trusting the output.

Claude Code Configuration & Workflows · Prompt Engineering & Structured Output

Scenario 6

Structured Data Extraction

You run a system that uses Claude to turn unstructured documents into structured records, validates every result against JSON schemas, and passes the output to downstream systems. Accuracy has to stay high across messy and unusual documents, and edge cases must be handled cleanly rather than with plausible-looking guesses.

Prompt Engineering & Structured Output · Context Management & Reliability

Scenario names and the systems they describe follow section 5 of Anthropic's CCAR-F exam guide v1.0. The questions are original to this site.

Browse all 60 questions

Each question has its own page with the answer and a full explanation.

Scenario 1: Customer Support Resolution Agent 10

Scenario 2: Code Generation with Claude Code 10

Scenario 3: Multi-Agent Research System 10

Scenario 4: Developer Productivity with Claude 10

Scenario 5: Claude Code for Continuous Integration 10

Scenario 6: Structured Data Extraction 10