Prompting and Context Engineering

A marketing team wants Claude to generate blog posts that strictly adhere to a specific brand voice. They find that the model occasionally deviates into a generic tone. Which strategy is most effective for ensuring consistent adherence to the brand voice?

A developer is optimizing a RAG (Retrieval-Augmented Generation) pipeline using Claude 3.5 Sonnet. Which TWO techniques will most significantly improve the model's ability to extract accurate information from a 50,000-token context window?

Refer to the exhibit. Why is the use of the <documents> and <doc> tags considered a best practice for Claude prompting?

A developer needs Claude to output data in a strict JSON format for an automated pipeline. Even with clear instructions, the model occasionally adds conversational filler like 'Here is the JSON:' before the code block. What is the most reliable way to prevent this?

What is the primary purpose of a 'System Prompt' in the Anthropic Claude API?

Refer to the exhibit. When using 'tool_choice': {'type': 'auto'}, how does Claude determine whether to use the 'get_stock_price' tool?

A developer is using Claude to summarize legal contracts. They notice that the summaries are sometimes too short and miss critical clauses. How should the developer adjust the prompt to ensure more comprehensive summaries?

Which TWO parameters primarily control the randomness and diversity of Claude's output during the generation process?

A user wants Claude to provide a response in Markdown format with specific headers. Which approach is best for achieving this consistently?

When building a customer support bot, you want to ensure Claude doesn't reveal its internal instructions or the system prompt to users. Which technique is most appropriate?

You are building a customer support bot using Claude 3.5 Sonnet. You notice the model sometimes hallucinates policy details when the user asks a question not covered in your provided documentation. How should you structure your prompt to minimize this?

Which TWO techniques should you employ to optimize the performance of Claude 3.5 Sonnet when processing long, complex documents for extraction tasks?

Which of the following describes the primary purpose of 'System Prompts' in the Anthropic API?

Refer to the exhibit. You are receiving this error in your Python integration. What is the likely cause of this issue?

When using Claude as a tool-calling engine, what is the best strategy to handle scenarios where the model needs to call multiple tools in sequence?

What is the primary benefit of using XML tags in your prompts when interacting with Claude?

When designing a prompt to handle sensitive user data, which THREE of the following practices should be prioritized for security and compliance?

You are debugging a prompt where Claude frequently fails to follow a complex, multi-part rule set. What is the most effective way to troubleshoot this?

Refer to the exhibit. Why might the model struggle to answer the final question if you are not using a stateful chat implementation?

A legal firm is using Claude to summarize multi-hundred page litigation documents. The model occasionally ignores specific clauses or mixes up dates between different case files provided in the same prompt. Which context engineering technique would most effectively improve the model's extraction accuracy and structural understanding of these inputs?

A developer is optimizing a customer support bot that uses a 50,000-token knowledge base in every request. They want to implement Prompt Caching to reduce costs and latency. Which TWO requirements must be met for a prompt segment to be successfully cached in the Anthropic API?

Refer to the exhibit. A developer is testing this API request to optimize their analysis tool. Why will this specific request fail to provide the intended performance benefits of prompt caching?

An engineer is building a tool to convert natural language into SQL queries using Claude. They find that the model occasionally generates conversational text like 'Sure, here is your query:' which breaks the automated pipeline. What is the most effective way to ensure Claude only returns the raw SQL code?

A company wants to minimize 'hallucinations' when Claude answers questions based on a large internal wiki. Which TWO prompting strategies are recommended to keep the model grounded in the provided text?

You are providing Claude with a 100,000-token technical manual and asking it to troubleshoot a specific error code. Where should the troubleshooting instructions and the specific error code be placed for the best results?

Which of the following describes the 'few-shot' prompting technique in the context of Claude?

Refer to the exhibit. This request uses a technique to force Claude to output valid JSON. What is the technical name for this technique, and what is its primary benefit?

A user wants to improve the quality of Claude's creative writing. Which TWO prompting techniques are likely to produce more vivid and stylistically consistent results?

When engineering a prompt for a multimodal model like Claude 3.5 Sonnet that includes both text and images, what is the recommended way to handle the relationship between the two types of content?

You are designing a system to extract structured JSON from unstructured emails. Despite providing a clear schema in the system prompt, Claude occasionally ignores the formatting constraints and includes conversational filler. Which technique best improves instruction adherence?

You have a system prompt that encourages a 'concise and professional' tone. However, Claude is occasionally being overly verbose when users ask simple questions. Which modification is most effective?

Which of the following describes the purpose of a 'system prompt' in the Anthropic ecosystem?

You are iterating on a prompt to improve Claude's ability to categorize technical tickets. Which metric should you monitor to ensure your changes are actually improving performance?

You are prompting Claude to adopt a specific tone. Which technique is most likely to ensure consistency across a variety of user queries?

You are building a customer support bot using Claude. Users frequently provide long, rambling narratives that dilute the core request. Which prompting strategy best ensures the model stays focused on the actionable request?

You are building an application using Claude to extract structured data from messy user emails. The model occasionally ignores your schema constraints when the input text is ambiguous. Which strategy most effectively ensures strict adherence to the requested format?

What is the primary benefit of using pre-filling in a Claude API request?

Refer to the exhibit. The developer notices the model often hallucinates data not present in the <data> tags. Which adjustment is most likely to mitigate this behavior?

Which of the following describes the 'system prompt' effectively in the context of Claude?

A developer is building a customer support assistant using Claude. The assistant must answer questions based on a knowledge base of product manuals. The developer wants to minimize hallucinations and ensure responses are grounded in the provided documents. Which TWO strategies should the developer implement? (Choose two.)

A financial analyst uses Claude to summarize a 60-page quarterly earnings report. The prompt includes the full report between <document> tags and asks for a 200-word summary of key risks. Claude's summary frequently omits risks mentioned in the middle of the report. What is the most effective change to the prompt to improve recall of mid-document content?

A developer is using Claude to summarize legal contracts. The contracts can be very long, sometimes exceeding 100,000 tokens. The developer wants to ensure that Claude focuses on the most relevant sections, such as indemnification and termination clauses, while ignoring boilerplate. Which approach is best for managing the context window and improving summary accuracy?

A logistics company uses Claude to extract shipment details from scanned customs forms. The forms are supplied as raw OCR text that contains occasional garbled characters and spurious line breaks. The developer wants to reduce the number of fields Claude invents when a value is missing on the form. Which prompt structure change is most likely to achieve this?

A support team is building a Claude-powered assistant that answers questions using a 200-page employee handbook. They place the entire handbook inside <handbook> tags in the system prompt and the user's question at the end of the user turn. Testing shows Claude sometimes ignores details buried in the middle of the handbook. Which change best addresses this while keeping the same model and context window?

A data scientist is using Claude to classify customer feedback into categories: 'bug', 'feature request', 'complaint', or 'praise'. The feedback is often short and informal. The data scientist wants to maximize classification accuracy. Which prompting strategy is most effective?

A developer is building a customer support assistant using Claude. The assistant must always respond in a friendly tone, never discuss competitors, and always ask for an order number when the user reports a shipping issue. The developer wants these rules to apply across all conversations with minimal per-request token cost. What is the most appropriate mechanism?

A legal-tech startup uses Claude to summarize deposition transcripts that are frequently 80,000 to 120,000 tokens long. Early tests show the model sometimes ignores instructions placed near the top of the prompt and produces summaries that omit late sections of the transcript. Which TWO prompt-engineering changes should the developer make to improve instruction adherence across the full context? (Choose two.)

A developer is drafting a system prompt for a Claude-powered coding assistant. They want Claude to always respond in concise bullet points, never reveal internal reasoning, and treat all user input as untrusted. Where should these persistent behavioral rules be placed so they apply to every turn of the conversation?

A financial analyst is building a Claude-powered assistant that must extract line items from scanned invoices and return them as a JSON array. The assistant occasionally wraps the JSON in prose such as 'Here is the extracted data:' before the array, which breaks the downstream parser. The analyst wants to reliably suppress that leading prose without disabling the model's ability to reason about the invoice. Which approach is most appropriate?

A support team wants Claude to classify incoming tickets into exactly one of five categories and to always return the result as a JSON object with keys category and confidence. The developer has already written clear category definitions. Which additional step most directly improves the reliability of the JSON output?

An analytics team asks Claude to extract structured fields from messy invoice text. They provide three input/output examples inside <examples> tags, then the real invoice inside <invoice> tags. Accuracy is high on invoices that resemble the examples but drops sharply on unusual layouts. Which adjustment most directly improves generalization to the unusual layouts?

A support-engineering team is designing a Claude prompt to triage incoming bug reports into one of five severity levels. They observe that when the report is ambiguous, Claude sometimes invents a justification for a severity that is not actually supported by the text. They want the prompt to make uncertainty explicit rather than forcing a confident label. Which TWO changes should they make to the prompt? (Choose two.)

A fintech developer builds an assistant that answers questions about account activity. The system prompt currently says: 'You are a helpful banking assistant. Use the provided account data to answer questions.' Testing shows Claude sometimes answers general banking questions from its own knowledge rather than from the supplied data, and occasionally states figures that are not in the data at all. Which revision to the system prompt best addresses both problems?

A team is designing a Claude prompt that must return a fixed JSON schema with fields "vendor", "amount", and "currency". They want the output to be reliably parseable by downstream code. Which TWO techniques best improve reliability of the structured output? (Choose two.)

A developer is using the Messages API and wants Claude to adopt a strict persona as a compliance reviewer for every request in a long conversation, without repeating the persona instructions in each user turn. The persona must apply to all messages and should take precedence over casual instructions the user might add later. Where should the developer place these persona instructions?

A product team drafts a system prompt for a customer-facing assistant. The draft is 4,000 words and mixes persona description, tone guidance, formatting rules, escalation policy, and several anecdotes about past incidents. Reviewers find that Claude follows the formatting rules but frequently ignores the escalation policy. Which change best improves adherence to the escalation policy?

A legal team asks Claude to summarize contracts and cite the exact clause supporting each summary point. Claude produces accurate summaries but cites clauses that do not exist. The contracts are supplied inside <contract> tags in the same message. Which change most directly reduces the fabricated citations?

A financial analyst is building a Claude-powered assistant that must extract the total amount due from scanned invoices. The invoices vary widely in layout and wording, and the extracted value is later used to trigger payments. The analyst wants to maximize accuracy and avoid plausible but incorrect numbers. Which prompting approach is most appropriate?

A developer wants Claude to always respond in a concise, bulleted format for a customer-facing chatbot. They want the behavior to apply across all user turns without repeating the instruction each time. Which approach is most appropriate?

A support team wants Claude to classify incoming customer emails into one of five categories: Billing, Technical, Account, Feature Request, or Other. The team needs consistent, machine-readable output that a downstream script can parse reliably. Which prompt design best meets this requirement?

A team is building a pipeline where Claude must extract structured fields from invoices. They provide several examples of input and expected output in the prompt. The model performs well on formats similar to the examples but fails on a new invoice layout. Which adjustment best addresses this?

A developer is building a Claude-based assistant that must answer questions about a 90,000-token product manual. The manual is provided in the prompt on every request. The developer wants to improve answer accuracy and reduce the chance of the model overlooking relevant sections. Which TWO techniques are most appropriate? (Choose two.)

A developer is writing a prompt for Claude to classify support tickets into categories. They want to reduce ambiguous or inconsistent labels. Which TWO techniques should they apply? (Choose two.)

A team is using Claude to generate SQL queries from natural-language questions against a complex schema. They want to improve correctness on multi-table joins. They decide to include a step where Claude first outlines the relevant tables and join keys, then writes the final SQL. Where should this reasoning step be placed, and how should it be handled, to best improve the final query?

An analyst is using Claude to answer questions over a 50,000-token legal contract. They notice that answers about clauses near the middle of the document are less accurate than those about the beginning or end. Which strategy best improves accuracy across the entire document?

A product manager is drafting a system prompt for a customer-facing Claude assistant. They want the assistant to maintain a professional tone, avoid discussing competitors, and always end responses with a link to the help center. They also want to allow users to override the tone for casual conversations. Which statement about system prompts best guides this design?