Study guides / CCAO-F

Quick reference

One condensed cheat-sheet per domain - the tables and rules worth re-reading right before the exam.

System Prompt vs. Message: What Goes Where

Test: would this instruction apply to *every* message in the conversation, or just this one?

Goes in the System PromptGoes in the Message
Role / persona statementThe specific document, complaint, or data to act on
Tone and brand voiceA one-off request or question
Formatting rules that never changeAnything task-specific that varies run to run
Things Claude should never do

Fix for generic/inconsistent tone: add a short, specific role statement ("You are X, writing for Y") — not more adjectives describing the tone, and not a sampling setting like temperature.

When to Add a Role vs. Examples vs. XML Tags

SymptomFixWhy
Output is generic or tone drifts run to runRole statement in the system promptGives Claude a consistent perspective to filter instructions through
Output is inconsistent in structure/format despite detailed instructionsMultishot: 3–5 diverse worked examples in <example> tagsShows the exact pattern instead of describing it in prose
Claude confuses an example (or other section) for the real inputWrap each part in its own XML tag (<context>, <examples>, <input>, ...)Removes structural ambiguity about where one section ends and the next begins
One prompt does 5 things shallowly / drops a pieceTask decomposition into ordered stepsEach sub-task gets full attention instead of being blended together

Multishot Prompting Checklist

XML Tag Conventions

Common tags: <context>, <instructions>, <examples> (containing individual <example> blocks), <input>. These are conventions, not a fixed schema — any consistent, clearly-labeled tag name works (<background>, <constraints>, <document>, <question>).

Matching Prompting Approach to Task Type

Task TypePrompting ApproachDistractor to Avoid
AnalysisGive explicit criteria up front — what dimensions matter, what a good answer weighsLeaving criteria implicit and hoping Claude infers them
ResearchInstruct Claude to cross-check claims and cite sourcesTrusting ungrounded claims without a sourcing instruction
DraftingGive examples plus a clear audience/role — aim for one finished artifactOffering a menu of options when a single finished draft was wanted
BrainstormingAsk for volume and range first; evaluate/narrow as a separate later stepAsking Claude to judge quality while it's still generating — narrows output prematurely

Audience Framing & Task Decomposition Signals

Audience framing: name the reader's role, background, and purpose ("a general donor with no stats background who wants to know if the program worked") and ask for findings restated in plain, practical language. "Make it shorter/simpler" alone often just trims a still-jargon-heavy passage.

Decompose a request when: