System Prompt
The initial instruction message sent to Claude with the system parameter in an API call. It sets the overall behaviour, persona, constraints, and output format for the conversation. System prompts are not part of the message history — they sit above it and persist across all turns.
Exam context: Know the difference between system prompts and user messages. The exam tests system prompt best practices: clear role definition, explicit constraints, output format specification, and avoiding conflicting instructions.
See also: 4.1 System Prompts
Structured Output
A technique for getting Claude to return responses in a specific, machine-parseable format such as JSON, XML, or YAML. This is achieved through explicit format instructions in the prompt, JSON Schema definitions, or by using prefilling to start Claude's response with an opening delimiter.
Exam context: The exam tests multiple approaches to structured output: prompt-based instructions, tool-use schemas (which guarantee valid JSON), and prefilling. Know the trade-offs between each approach and when tool-use is more reliable than prompt instructions alone.
See also: 4.2 Structured Output
Prompt Chaining
An orchestration technique where the output of one Claude call becomes the input to the next. Each step in the chain has a focused, specific task. Chaining decomposes a complex problem into manageable steps and allows for validation or transformation between steps.
Exam context: Know when to use prompt chaining versus a single prompt. The exam tests the principle that each link in the chain should do one thing well. Understand how to pass context between chain steps and where to insert validation gates.
See also: 4.3 Prompt Chaining
Few-Shot Examples
Input-output pairs included in the prompt to demonstrate the desired behaviour, format, or reasoning pattern. By showing Claude concrete examples of correct responses, you reduce ambiguity and improve consistency. Few-shot examples are placed in the system prompt or user message before the actual request.
Exam context: Know best practices for few-shot examples: use diverse examples that cover edge cases, place them before the request, and match the exact format you want in the output. The exam may test how many examples are typically needed (2-5 is usually sufficient).
See also: 4.4 Few-Shot & Examples
Prompt Optimisation
The iterative process of refining prompts to improve output quality, reduce costs, and increase reliability. Techniques include simplifying instructions, removing ambiguity, adding constraints, adjusting temperature, and testing against a set of evaluation cases.
Exam context: The exam tests systematic approaches to prompt improvement rather than ad-hoc tweaking. Know the evaluation-driven workflow: define test cases, measure baseline performance, make targeted changes, and measure again.
See also: 4.5 Prompt Optimisation
Output Validation
Programmatic checks applied to Claude's responses to verify they meet expected criteria before being used downstream. Validation can check format (valid JSON, correct schema), content (required fields present, values within ranges), and safety (no prohibited content). Failed validation triggers a retry or fallback.
Exam context: Know the common validation strategies: schema validation (JSON Schema, Zod, Pydantic), content checks, and multi-pass validation where Claude reviews its own output. Understand how validation fits into an agentic loop.
See also: 4.6 Output Validation
Prefilling
A technique where you start Claude's response by including the beginning of the assistant message. By providing an opening token (such as { for JSON or <result> for XML), you guide Claude to continue in the expected format. Prefilling is set by including a partial assistant message in the API call.
Exam context: Know how prefilling works at the API level (adding a partial assistant message) and when it is most useful (ensuring structured output format). Understand that prefilling is not available in all interfaces — it requires direct API access.
See also: 4.2 Structured Output
XML Tags
Delimiters used within prompts to structure content into clearly labelled sections. Claude is trained to understand XML-style tags like <instructions>, <context>, and <examples>. Using tags makes prompts more readable and helps Claude identify the purpose of each section.
Exam context: The exam favours XML tags as Anthropic's recommended approach for structuring long prompts. Know common tag patterns and the principle that tagged sections reduce misinterpretation of prompt boundaries.
See also: 4.1 System Prompts
Chain of Thought
A prompting technique that instructs Claude to show its reasoning step by step before arriving at a final answer. This improves accuracy on complex tasks by forcing the model to work through the problem methodically. Chain of thought can be elicited by adding instructions like "think step by step" or by using extended thinking.
Exam context: Know when chain of thought helps (complex reasoning, multi-step problems) and when it is unnecessary (simple factual retrieval). Understand the relationship between chain of thought prompting and Claude's extended thinking feature.
See also: 4.1 System Prompts
Temperature
A parameter (0.0 to 1.0) that controls the randomness of Claude's responses. Lower temperatures (e.g., 0.0) produce more deterministic, focused output. Higher temperatures (e.g., 0.8) produce more varied, creative output. The default is 1.0.
Exam context: Know the appropriate temperature settings for different use cases: low temperature for structured output, code generation, and factual tasks; higher temperature for creative writing and brainstorming. Understand that temperature 0 does not guarantee identical outputs.
See also: 4.5 Prompt Optimisation