CCDV-F Practice Exam 4 — 20 Questions

Question 1

A developer is building a document-review assistant that must extract every monetary figure from contracts and cite the page where each figure appears. The contracts average 40 pages. Early tests show Claude misses figures that appear in tables and occasionally cites the wrong page. The developer wants to improve recall and citation accuracy without changing the model. Which approach is most effective?

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Ask Claude to first list all candidate monetary figures with their page numbers, then verify each candidate against the source text before producing the final extraction.. Separating candidate generation from verification gives the model an explicit intermediate list it can check against the source, which catches table figures that a single extraction pass tends to skip. Verifying each page citation against the text before finalizing corrects misattributed page numbers, and the whole workflow stays within one model.

Answer

Instruct Claude to be thorough and to pay special attention to tables and page numbers in the contract.

Answer

Increase max_tokens so Claude has room to output more figures and longer citations.

Answer

Split each contract into 40 separate single-page prompts and merge the extracted figures afterward.

Question 2

A healthcare startup uses the Anthropic API to summarize patient intake forms. The security team requires that all protected health information (PHI) be redacted before the data leaves the application's trust boundary. A developer proposes using a custom regex to remove names and dates. Which approach best enforces the redaction requirement without exposing PHI to the model?

Accepted Answer

Apply a deterministic PHI-detection library (e.g., Presidio) to redact fields client-side, then send only the redacted payload to the Anthropic API.. The requirement is that PHI never leaves the application's trust boundary, so redaction must occur client-side before the API call. A vetted PHI-detection library provides deterministic, auditable removal of identifiers, unlike prompt instructions or hashing. This keeps the model input free of PHI while preserving enough clinical context for summarization, and it produces logs that satisfy compliance reviews.

Answer

Hash all input fields with SHA-256 before sending them to the Anthropic API.

Answer

Include a system prompt instructing Claude to ignore and not repeat any PHI in the input.

Answer

Send the raw text but request that Anthropic disable logging for the request via a custom header.

Question 3

A developer's MCP client launches a local stdio server that exposes a `query_metrics` tool. The server process writes diagnostic log lines to standard output while handling requests. Claude's tool calls intermittently fail with JSON parse errors on the client side. Which change best resolves this?

Accepted Answer

Configure the server to write all diagnostic logging to standard error instead of standard output.. The stdio transport dedicates standard output to JSON-RPC frames and standard error to diagnostics. When a server prints log lines to stdout, the client reads them as protocol data and fails to parse them, which matches the intermittent parse errors. Moving logging to stderr restores a clean protocol channel and lets the `query_metrics` tool calls complete normally without any transport redesign.

Answer

Wrap every log line in a JSON object so the client can skip non-protocol entries automatically.

Answer

Increase the client's request timeout so slow log writes do not corrupt the response stream.

Answer

Switch the server to HTTP with Server-Sent Events transport so logging no longer shares a channel with protocol data.

Question 4

A developer is building an agent that runs shell commands to inspect a repository. They want the agent to iterate autonomously but prevent destructive commands like deleting files outside the project directory. Which combination best enforces this boundary while preserving autonomy?

Accepted Answer

Route shell commands through a permission callback that inspects each command and denies those targeting paths outside the project directory.. Safety boundaries for autonomous agents must be enforced outside the model's discretion. A permission callback inspects every shell invocation before it runs and denies those reaching outside the project directory, which blocks destructive operations while still allowing the agent to iterate freely on permitted commands. Prompt guidance and token limits are advisory or orthogonal, and removing shell access discards needed capability.

Answer

Restrict the agent to read-only tools and remove shell execution entirely from its toolset.

Answer

Lower the model's max_tokens so it cannot compose long destructive command strings.

Answer

Rely on the system prompt instructing the model to never run destructive commands.

Question 5

A developer is using Claude to review pull requests. The prompt includes a 4,000-line diff followed by the question 'List any security issues.' Claude's answers are vague and sometimes reference the wrong file. The developer wants more precise, file-specific findings without switching models. Which change is most likely to improve precision?

Accepted Answer

Restructure the diff so each file is wrapped in its own labeled tag, and ask for findings in a per-file structured list.. Precision improves when the prompt gives the model clear boundaries and a specific output structure. Wrapping each file in labeled tags lets the model attribute findings to the correct file, and requesting a per-file structured list enforces specificity. Vague questions, broad essays, or extreme splitting lose the context and attribution needed for accurate, file-specific security findings.

Answer

Shorten the question to 'Any issues?' so the model has more room to reason about the diff.

Answer

Split the diff into 4,000 separate single-line prompts and merge the answers afterward.

Answer

Ask Claude to produce a long free-form essay about the overall code quality before listing issues.

Question 6

A developer registers a tool named get_order_status with an input_schema that declares order_id as a string. During testing, Claude repeatedly emits tool_use blocks where order_id is the numeric value 10482 instead of a string. The downstream API rejects numeric IDs. Which change most reliably fixes this at the tool-definition layer?

Accepted Answer

Add a description to the order_id property stating it must be a string, and include a format or pattern hint in the schema.. Tool argument types are steered by the tool definition itself, so the durable fix is to make the expected type explicit through property descriptions and schema constraints. Describing order_id as a quoted string with a numeric pattern gives Claude the signal it needs, and validating the payload before calling the downstream API provides defense in depth.

Answer

Set the tool_choice parameter to force get_order_status on every turn.

Answer

Raise max_tokens so Claude has more room to format the argument correctly.

Answer

Change input_schema to declare order_id as an integer so the numeric output becomes valid.

Question 7

A developer is building a Python application that streams responses from the Anthropic Messages API. They notice that when they set stream=True, the response object is an iterator of server-sent events. They want to extract only the incremental text chunks as they arrive, without waiting for the full message. Which event type should they filter for to get the text deltas?

Accepted Answer

content_block_delta. When streaming with the Messages API, the server sends a series of events. The content_block_delta event is specifically designed to carry incremental text deltas as Claude generates the response. By listening for this event type, the developer can process text as it arrives, enabling real-time user experiences. Other events like message_start, message_delta, and ping serve different purposes such as initialization, final metadata, or keep-alive.

Answer

message_delta

Answer

message_start

Answer

ping

Question 8

A developer is working in a large monorepo and wants Claude Code to automatically run `npm run lint` and `npm run test` after every file edit it makes, without needing to ask each time. Which Claude Code feature should the developer configure to achieve this?

Accepted Answer

Configure a PostToolUse hook in `.claude/settings.json` that matches the Edit and Write tools and runs the lint and test commands.. Hooks are the deterministic automation mechanism in Claude Code. A PostToolUse hook bound to the Edit and Write tools executes a configured shell command every time those tools complete, which guarantees `npm run lint` and `npm run test` run after each change without any prompt. Documentation files, slash commands, and permission flags influence behavior or require manual action but cannot enforce automatic post-edit execution.

Answer

Add a CLAUDE.md file at the repository root that documents the lint and test commands.

Answer

Enable the `--auto-approve` flag in the project's `.claude/settings.json` so Claude Code can decide when to run the commands.

Answer

Create a custom slash command named `/lint-test` in `.claude/commands` that runs both commands.

Question 9

A developer is using Claude Code to debug a complex issue. After several exchanges, Claude Code suggests a solution that involves modifying a configuration file outside the project directory. The developer is concerned about unintended side effects. What is the most appropriate way to handle this?

Accepted Answer

Reject the suggestion and ask Claude Code to propose a solution that stays within the project directory.. Rejecting the suggestion and asking for a solution confined to the project directory is the safest approach. It avoids potential side effects on other projects or the system. Claude Code can often provide alternatives that use project-local configuration, which are easier to manage and revert.

Answer

Accept the suggestion but create a backup of the configuration file first.

Answer

Use the `/undo` command to revert the suggestion and then manually edit the configuration file.

Answer

Allow the modification because Claude Code has context about the system.

Question 10

A developer writes an agent loop that handles Claude's tool_use blocks by executing each tool and appending a user message containing the tool_result blocks. In production, a request occasionally triggers a 400 error stating that the tool_use ids were not found. Reviewing the code, the developer sees the loop builds each new request by sending only the latest user message and the newest tool_result message, discarding earlier turns to save tokens. Which action resolves the error while preserving the agent's behavior?

Accepted Answer

Send the complete conversation history on every request, including the assistant turn containing the tool_use blocks that the tool_result messages reference.. Because the Messages API holds no server-side session, every request must include the prior assistant turn that emitted the tool_use blocks alongside the tool_result messages that cite those ids. Trimming history to save tokens removed the referenced blocks, so the API rejected the orphaned results. Sending the complete history, or a window that retains each referenced tool_use turn, restores valid correlation.

Answer

Generate a new UUID for each tool_result block and set the tool_use_id field to that fresh value so the results appear unique to the API.

Answer

Switch the loop to the Batches API so that multi-turn tool exchanges are processed together and prior messages are retained on the server.

Answer

Reduce the number of tools passed in the tools parameter so that fewer tool_use blocks are generated and fewer ids need to be matched.

Question 11

A developer is streaming a long Claude response using the Messages API with stream: true. Their client code reads Server-Sent Events and appends text to the UI. Mid-stream, the connection drops and the client reconnects by re-issuing the same request from scratch. Users complain that the answer restarts from the beginning. What is the most accurate explanation of what is happening?

Accepted Answer

Streaming responses are stateless; a dropped connection cannot be resumed, so re-issuing the request starts a brand new generation and the partial text already shown is discarded.. Streaming responses from the Messages API are not resumable: each HTTP request produces an independent generation delivered as Server-Sent Events. When the transport fails, the client cannot ask the server to continue from the last token it saw. The correct mitigation is to persist partial output locally, avoid blindly restarting the UI, and design retries that tolerate duplicate or truncated content.

Answer

The client must call the count_tokens endpoint before reconnecting so the server can splice the new stream onto the previous tokens.

Answer

The Messages API supports resuming a stream from the last received event, so the client should have sent the last event ID back on reconnect.

Answer

Setting a higher max_tokens on the reconnect lets the API detect the earlier partial output and continue from where it stopped.

Question 12

A developer is building a customer-support agent on the Claude Messages API. The agent receives a long conversation history plus a retrieved knowledge-base article, and the developer wants Claude to answer only from the retrieved article while still seeing the full chat for tone. The developer wants the retrieved article treated as the most authoritative source, even if earlier turns contain outdated policy statements. Where should the retrieved article be placed, and how should it be marked?

Accepted Answer

Place the retrieved article inside the system prompt, wrapped in tags, and instruct Claude that content overrides any conflicting statements in the conversation.. The system prompt is the operator-controlled channel and carries more weight than user or assistant turns, making it the right place to establish that the retrieved article is authoritative. Tagging the article with XML-style delimiters gives Claude an unambiguous boundary for the trusted content, so outdated policy in earlier conversation turns does not win.

Answer

Insert the retrieved article into a tool_result block from a search tool and instruct Claude to prefer tool results over all other content.

Answer

Place the retrieved article as the first user turn, followed by the conversation history, and rely on Claude's recency bias to prefer the article.

Answer

Append the retrieved article as the final assistant turn so Claude treats it as its own prior statement and repeats it verbatim.

Question 13

A developer is integrating the Anthropic API into a healthcare application that processes protected health information (PHI). The compliance team requires that data is encrypted in transit and that the application authenticates to the API without embedding secrets in client-side code. Which combination of practices should the developer implement?

Accepted Answer

Use HTTPS with TLS 1.2 or higher for all API calls and store the Anthropic API key in a server-side secret manager, retrieving it at runtime.. The correct practices are HTTPS with TLS 1.2+ for encryption in transit and a server-side secret manager for the API key. This ensures PHI is protected during transmission and the API key is not exposed in client code, satisfying both compliance requirements.

Answer

Use HTTPS for API calls and store the API key in a client-side configuration file that is bundled with the application.

Answer

Use a VPN for all traffic and hardcode the API key in the server application's environment variables.

Answer

Use HTTP for internal network calls and embed the API key in the mobile app's source code for simplicity.

Question 14

A developer is using the Messages API and wants Claude to reply in strict JSON matching a schema their downstream service expects. They have already written a clear instruction in the system prompt describing the schema. Which additional API feature most directly enforces that the output conforms to the schema?

Accepted Answer

Defining a tool whose input_schema describes the desired fields, then instructing Claude to call that tool for its response.. Tool definitions carry a JSON Schema in input_schema, and when Claude invokes a tool, the API returns arguments that conform to that schema. Routing the model's answer through a tool call therefore gives the strongest structural guarantee in the Messages API. Prompt instructions help guide behavior but do not enforce shape, so pairing them with a tool schema is the reliable pattern for strict JSON.

Answer

Setting temperature to 0 to eliminate all variation in the response format.

Answer

Increasing max_tokens so the model has room to complete the full JSON object without truncation.

Answer

Adding a stop_sequence equal to the closing brace so the API halts generation exactly at the end of the JSON.

Question 15

A developer is integrating Claude into a customer-facing portal where users can paste arbitrary text that is inserted into prompts. The security team wants to reduce the risk of prompt injection leading to unauthorized actions. Which TWO controls are most effective? (Choose two.)

Accepted Answer

Delimit and clearly label untrusted user content within the prompt, instructing Claude to treat it as data rather than instructions.. Prompt injection defense requires both reducing the model's tendency to follow injected instructions and ensuring that no unauthorized action succeeds regardless of model output. Delimiting untrusted content addresses the first layer, while server-side authorization enforcement addresses the second and is the control that actually prevents harm when injection attempts succeed.

Answer

Increase the max_tokens setting so Claude has more room to reason about whether input is malicious.

Answer

Cache responses for identical user inputs to reduce the number of times Claude processes potentially malicious text.

Answer

Lower the temperature to zero so Claude becomes deterministic and cannot be manipulated.

Question 16

A developer is building a customer-support assistant that must answer only from a provided knowledge base article and must refuse to answer when the article does not contain the information. The assistant currently invents plausible answers. Which prompt change best enforces the refusal behavior?

Accepted Answer

Instruct the model to answer only using information found in the article and to respond with a fixed phrase such as 'I don't have that information' when the article is insufficient.. Grounding requires two explicit constraints: define the permitted source and define what to do when that source is inadequate. Naming the article as the only allowed source, plus a fixed refusal phrase for missing information, gives the model an unambiguous rule and produces a consistent, detectable abstention. Tone, token limits, and document placement do not establish either constraint.

Answer

Increase the max_tokens parameter so the model has more room to explain its reasoning.

Answer

Move the knowledge base article to the end of the prompt so it is the last thing the model reads.

Answer

Add an instruction to answer in a polite and professional tone at all times.

Question 17

A developer is writing an MCP client that must stay responsive while a server performs a slow operation during a tool call. The client should allow the user to cancel the request without terminating the whole session, and the server should be able to stream incremental output before finishing. Which two MCP features should the developer implement? (Choose two.)

Accepted Answer

Request cancellation using the notifications/cancelled notification with the in-flight request ID.. Long-running MCP operations are handled with progress notifications tied to a client-supplied progress token and with out-of-band cancellation via notifications/cancelled. Together they let a server report partial progress and let a client abort one request without disturbing the session, which is precisely the behavior the scenario demands.

Answer

Polling tools/list repeatedly to detect when the tool has finished executing.

Answer

Closing the transport and reinitializing the session to interrupt the operation.

Answer

Setting a long client-side timeout and retrying the same request until it succeeds.

Question 18

A developer is using the Anthropic API to build a customer support chatbot. The chatbot must access a backend CRM to retrieve customer details. The security team requires that the chatbot only accesses records for the authenticated customer and that the CRM credentials are never exposed to the model. Which approach best satisfies these requirements?

Accepted Answer

Implement a backend service that authenticates the user, retrieves the customer ID, and calls the CRM with its own credentials, then returns only the necessary data to Claude.. The best approach is a backend service that authenticates the user, retrieves the customer ID, and calls the CRM with its own credentials, returning only necessary data to Claude. This keeps credentials server-side and enforces that the chatbot only accesses records for the authenticated customer.

Answer

Pass the CRM API key to Claude in the system prompt so it can include the key when calling the CRM tool.

Answer

Store the CRM credentials in the model's fine-tuning data so it can learn to call the CRM securely.

Answer

Have Claude generate CRM API calls and execute them directly from the client-side application using the customer's browser session.

Question 19

A developer is building a real-time chat application where users expect responses in under two seconds. The prompts are short (under 200 tokens) and the responses are typically one or two sentences. Which Claude model should the developer choose to optimize for latency and cost?

Accepted Answer

Claude 3 Haiku. For a real-time chat application with short prompts and simple responses, latency and cost are critical. Claude 3 Haiku is specifically designed to be the fastest and most affordable model in the Claude 3 family, making it ideal for this use case. More powerful models like Opus or Sonnet would add unnecessary cost and latency without providing meaningful benefits for such straightforward interactions.

Answer

Claude 3.5 Sonnet

Answer

Claude 3 Opus

Answer

Claude 2.1

Question 20

A developer's MCP client sends a tools/call request for a tool that performs a database write. The tool result comes back with is_error set to true and a message about a unique-constraint violation. What is the most appropriate way for the client to handle this result?

Accepted Answer

Surface the error content to Claude as the tool result so it can reason about the failure and adjust its next action.. Tool errors are delivered in-band as a tool result with is_error set to true, and the accompanying content is meant to inform the next reasoning step. Returning that result to Claude preserves the conversation loop and lets the model adapt, which is the correct handling for a recoverable data-level failure such as a constraint violation.

Answer

Convert the tool result into a plain assistant text message and end the turn without invoking Claude again.

Answer

Terminate the MCP session and reconnect before retrying the tool call.

Answer

Discard the result and silently retry the identical tool call up to three times.