Exam format
The CCA-F is a proctored, closed-book exam delivered by Pearson VUE, online or at a test center. You get 120 minutes to answer 60 multiple-choice questions, each with one correct answer and three distractors. There is no AI assistance during the exam. Your result is a scaled score out of 1000, and 720 is the pass line.
The five domains and their weights
Questions are distributed across five domains, weighted by importance. The Claude Prep mock exam samples questions in the same proportions, so a mock feels like the real distribution.
The agentic loop, when to choose a workflow over an agent, multi-agent orchestration, task decomposition, session state, and guardrails.
The CLAUDE.md memory hierarchy, settings and permissions, hooks, slash commands, subagents, and CI/CD automation.
Prompt structure, XML tags, few-shot examples, chain of thought, prefilling, structured JSON output, and batch processing.
Tool descriptions and schemas, the tool-use loop, MCP servers and clients, transports, and integration security.
Context window management, prompt caching, long conversations, error handling, rate limits, and production reliability.
The six scenario contexts
Rather than abstract trivia, most questions are grounded in production scenarios. The exam draws from a published set of six contexts, so practicing against realistic situations pays off:
- Customer support resolution agent
- Code generation with Claude Code
- Multi-agent research system
- Developer productivity tools
- Claude Code in CI/CD
- Structured data extraction
Scoring and retakes
The 1000-point scaled score means the 720 pass line is normalized, not a raw percentage. If you do not pass, you can attempt the exam up to four times in a rolling 12-month window, with waits of 14, 30, and 90 days after successive fails. That makes efficient prep worthwhile: you want to pass on the first or second try.
Sample questions
Here are a few original questions in the exam’s style. Reveal each answer to see the explanation.
Which type of task benefits MOST from being split across parallel subagents?
- AA tightly sequential task where each step depends on the output of the previous step
- BA task where every agent must continuously see the other agents' evolving intermediate state
- CA quick, targeted edit to a single known file where response latency matters most
- DRead-heavy research where independent sources can be explored simultaneously and each subagent returns a condensed summary
▸Show answer & explanation
Answer: D. Read-heavy research where independent sources can be explored simultaneously and each subagent returns a condensed summary
Parallel subagents shine on parallelizable, self-contained, read-heavy work: each worker explores independently in its own context and returns compressed findings. Sequential dependencies eliminate the parallelism benefit, tasks requiring continuously shared state incur heavy coordination overhead, and quick targeted edits are better done in the main conversation because subagents start fresh and add latency.
Read the docs →What happens when a PreToolUse hook script in Claude Code exits with code 2?
- AThe tool call is blocked, and the hook's stderr output is fed back to Claude as an error message
- BThe tool call proceeds, but a warning banner is shown to the user in the transcript
- CThe tool call is blocked, and the hook's stdout JSON is parsed for a permissionDecision value
- DThe hook is retried once before Claude Code falls back to the normal permission prompt
▸Show answer & explanation
Answer: A. The tool call is blocked, and the hook's stderr output is fed back to Claude as an error message
Exit code 2 from a PreToolUse hook is a blocking error: the tool call is prevented and the stderr text is returned to Claude so it understands why the action was rejected. Stdout, including any JSON, is ignored on exit code 2; JSON decisions like permissionDecision are only processed when the hook exits with code 0. There is no automatic retry behavior for hooks.
Read the docs →Which sequence correctly describes the core loop Anthropic uses to describe how agents operate?
- AClassify the input, route it to a specialized prompt, then aggregate the responses.
- BPlan the full task upfront, execute every step, then summarize and terminate.
- CGenerate a draft, have a second model evaluate it, then return the first draft unchanged.
- DGather context, take action, verify work, then repeat.
▸Show answer & explanation
Answer: D. Gather context, take action, verify work, then repeat.
Anthropic describes the agent loop as gathering context, taking action, verifying work, and repeating until the task is done. Classify-and-route describes the routing workflow, not the agent loop, and generate-then-evaluate describes evaluator-optimizer. Planning everything upfront and terminating contradicts the iterative, feedback-driven nature of agents.
Read the docs →Which two variations of the parallelization workflow does Anthropic describe in 'Building effective agents'?
- ARouting, which classifies inputs, and gating, which validates intermediate outputs between steps.
- BSharding, which splits large documents across context windows, and batching, which groups API requests to reduce cost.
- CMapping, which transforms each input item independently, and reducing, which merges partial results into one summary.
- DSectioning, which breaks a task into independent subtasks run in parallel, and voting, which runs the same task multiple times to get diverse outputs.
▸Show answer & explanation
Answer: D. Sectioning, which breaks a task into independent subtasks run in parallel, and voting, which runs the same task multiple times to get diverse outputs.
Anthropic names exactly two parallelization variants: sectioning (independent subtasks in parallel) and voting (the same task run multiple times for diverse outputs). Routing is a separate workflow pattern and gates belong to prompt chaining, not parallelization. Sharding, batching, and map-reduce are general distributed computing terms that Anthropic does not use for this pattern.
Read the docs →Practice like it’s exam day
Claude Prep gives you 1,000 exam-style questions and full 120-minute mock exams scored on the 1000-point scale, so nothing on exam day is a surprise.