CCARF

CCARF Practice Paper

Paper 1

Full practice exam · 60 questions. Use flashcard mode for instant feedback or exam mode to simulate the real test.

Start Paper 1 in the app

Questions in Paper 1

Q1D3 Claude Code Configuration & Workflows — A documentation team wants to archive the full conversation transcript to a log file every time Claude Code runs /compact, so that context l… Q2D2 Tool Design & MCP Integration — A developer productivity platform has a tool called analyze_content with the description 'Analyses content from various sources.' Logs show … Q3D5 Context Management & Reliability — Claude Code is auditing API documentation coverage across a large codebase. After exploring 15 modules, the agent produces vague references … Q4D1 Agentic Architecture & Orchestration — A customer support agent needs to escalate a complex billing dispute to a human agent. The AI agent compiles a handoff that includes the con… Q5D2 Tool Design & MCP Integration — An agent has two tools: `analyze_content` ('Analyses content') and `extract_web_results` ('Extracts data from web pages'). After a system pr… Q6D5 Context Management & Reliability — A data extraction pipeline extracts financial figures from annual reports. The pipeline cites sources using inline text references like 'Acc… Q7D5 Context Management & Reliability — A docs team processes a 500,000-line codebase by having Claude Code read files and generate docs, instructing it to 'summarise each module a… Q8D1 Agentic Architecture & Orchestration — Production data shows that in 8% of cases, a customer support agent processes refunds without verifying account ownership, occasionally lead… Q9D5 Context Management & Reliability — A customer asks a support agent to match a lower price advertised by a competitor. The agent's policy documents cover price adjustments for … Q10D3 Claude Code Configuration & Workflows — A developer working on a React Native project notices that Claude Code applies web-specific React conventions (e.g., using div elements) whe… Q11D1 Agentic Architecture & Orchestration — A customer support agent handles account deletion requests. The company policy requires explicit human approval before any account is perman… Q12D1 Agentic Architecture & Orchestration — A developer-tool agent writes code and runs shell commands. A system prompt instruction ('Do not run destructive commands or access files ou… Q13D3 Claude Code Configuration & Workflows — A CI pipeline validates that generated API docs match the codebase. It runs `claude -p 'Verify that all public API endpoints in src/api/ hav… Q14D4 Prompt Engineering & Structured Output — A validation-retry loop still fails on the same documents after three attempts each. In which situations will further retries not help? (Sel… Q15D1 Agentic Architecture & Orchestration — A coordinator agent should spawn specialist subagents for billing disputes and technical issues. Its system prompt describes the delegation … Q16D5 Context Management & Reliability — A legal document extraction pipeline has been running for three months with calibrated confidence thresholds. Extractions above 90% confiden… Q17D4 Prompt Engineering & Structured Output — Your data extraction pipeline uses tool_use with tool_choice set to 'auto'. You need guaranteed structured output for every request, but som… Q18D4 Prompt Engineering & Structured Output — Your extraction pipeline validates that line item amounts sum to the stated total. For Document A, the sum is £450 but the stated total is £… Q19D1 Agentic Architecture & Orchestration — An architect is designing a customer support system using the Claude Agent SDK. The system needs a coordinator agent that can delegate to a … Q20D2 Tool Design & MCP Integration — A support agent has `process_refund` and `adjust_billing` tools with clearly differentiated descriptions, yet still occasionally calls `adju… Q21D2 Tool Design & MCP Integration — A developer needs to rename a variable from 'userData' to 'customerData' in a specific file. The variable appears 12 times throughout the fi… Q22D3 Claude Code Configuration & Workflows — A developer is iterating on a data transformation function with Claude Code and has identified three issues: (1) date parsing mishandles tim… Q23D2 Tool Design & MCP Integration — A customer support team configures an MCP server for their internal CRM system. The agent frequently ignores the CRM MCP tool and instead us… Q24D5 Context Management & Reliability — A documentation team working across a 500,000-line codebase notices that Claude Code's responses become less specific after extensive file e… Q25D4 Prompt Engineering & Structured Output — The pipeline validates each tool_use extraction against a Pydantic model with model_validate(). Validation succeeds and every field has the … Q26D4 Prompt Engineering & Structured Output — An extraction pipeline uses `tool_use` with a 15-required-field schema. For some document types, only 8 of those fields ever appear in the s… Q27D2 Tool Design & MCP Integration — A developer productivity platform has a code review agent equipped with 18 tools covering code analysis, documentation lookup, test generati… Q28D4 Prompt Engineering & Structured Output — An extraction pipeline processes 50-page legal contracts in a single API call. It captures parties and dates from the first few pages but mi… Q29D5 Context Management & Reliability — A documentation generation pipeline uses Claude Code to produce docs from three sources: source code comments, existing wiki pages, and API … Q30D4 Prompt Engineering & Structured Output — Your extraction pipeline correctly identifies data in structured tables but returns empty fields when the same information appears in narrat… Q31D5 Context Management & Reliability — A structured data extraction system processes invoices, purchase orders, and contracts. The monitoring dashboard shows 97% overall extractio… Q32D1 Agentic Architecture & Orchestration — A customer support agent's loop terminates when cumulative token usage exceeds a budget. During a complex billing investigation the budget i… Q33D2 Tool Design & MCP Integration — A platform has `search_knowledge_base` ('Searches help articles') and `process_action` ('Handles customer actions like refunds and plan chan… Q34D4 Prompt Engineering & Structured Output — Your extraction pipeline retries failed documents, but the retry simply resends the original document with the same prompt. Success rates on… Q35D1 Agentic Architecture & Orchestration — A customer-support agent runs an agentic loop. Each turn it inspects `stop_reason`; when the value is `"tool_use"` it executes the requested… Q36D2 Tool Design & MCP Integration — A team needs to integrate with Jira for issue tracking in their Claude Code workflow. A developer proposes building a custom MCP server. Wha… Q37D1 Agentic Architecture & Orchestration — A coordinator using the Claude Agent SDK delegates a refactoring task to a code reviewer, a test generator, and a documentation writer in pa… Q38D3 Claude Code Configuration & Workflows — A documentation team needs to simultaneously update API reference docs for three independent microservices after a breaking change. Each upd… Q39D1 Agentic Architecture & Orchestration — A customer support agent runs to its `max_iterations=10` cap on every request, even simple ones. Logs show stop_reason returns 'end_turn' af… Q40D5 Context Management & Reliability — A customer support agent achieves only 55% first-contact resolution, well below the 80% target. Logs show it escalates straightforward damag… Q41D2 Tool Design & MCP Integration — A team's agent must generate a weekly report on the first turn of each conversation by calling `generate_report`. With `tool_choice: 'auto'`… Q42D3 Claude Code Configuration & Workflows — A developer's Claude Code applies the team's API conventions correctly in some sessions but not others, on the same project. They suspect th… Q43D3 Claude Code Configuration & Workflows — A platform engineering team creates a /security-audit skill that scans the codebase for vulnerabilities. The skill should be available to ev… Q44D4 Prompt Engineering & Structured Output — Your extraction pipeline uses tool_use with a JSON schema, so outputs always parse. Finance still reports invoices where line items do not s… Q45D3 Claude Code Configuration & Workflows — A consultancy works across 12 client projects simultaneously. Each developer has personal preferences (editor keybindings, alias shortcuts) … Q46D1 Agentic Architecture & Orchestration — A customer support agent integrates with three different backend systems via MCP tools. One system returns dates as Unix timestamps, another… Q47D3 Claude Code Configuration & Workflows — A developer is new to a healthcare compliance domain and needs to build an audit logging system. They understand the technical implementatio… Q48D4 Prompt Engineering & Structured Output — An invoice-extraction pipeline mislabels fields on documents where the correct interpretation is ambiguous. Which few-shot practices should … Q49D5 Context Management & Reliability — Claude Code is synthesising release notes from commit messages, PR descriptions, and changelog entries. During a 200+ commit session, summar… Q50D2 Tool Design & MCP Integration — A customer support agent has two tools: get_customer_profile (returns name, email, preferences) and get_customer_orders (returns order histo… Q51D4 Prompt Engineering & Structured Output — Your document processing pipeline chains three steps: (1) extract raw text, (2) classify document type, (3) extract structured fields based … Q52D1 Agentic Architecture & Orchestration — A developer's customer support agent sometimes terminates prematurely because they check if response.content[0].type == 'text' to determine … Q53D1 Agentic Architecture & Orchestration — A customer support agent must redact credit card numbers from its responses before they reach the customer. The current system prompt instru… Q54D3 Claude Code Configuration & Workflows — A documentation team creates a /generate-api-docs skill that reads source code files and produces Markdown API reference pages. The skill ge… Q55D5 Context Management & Reliability — Your extraction pipeline reports 97% aggregate accuracy, and you want to automate high- confidence extractions. Which safeguards should be i… Q56D1 Agentic Architecture & Orchestration — A financial services company's customer support agent receives a request: 'I was charged twice for my subscription, and I also need to updat… Q57D3 Claude Code Configuration & Workflows — A docs team maintains three content types in `docs/api/`, `docs/architecture/`, and `docs/runbooks/`, each with distinct formatting, termino… Q58D3 Claude Code Configuration & Workflows — A team is debugging a complex distributed system issue. The lead developer wants to use Claude Code to explore logs, trace request flows, an… Q59D2 Tool Design & MCP Integration — An engineering team needs to update all references to a renamed API endpoint across their 500,000-line codebase. They know the old endpoint … Q60D4 Prompt Engineering & Structured Output — Your extraction pipeline has a validation step that checks extracted financial data. When validation fails, the system retries by sending ju…