1. What does the "closing ritual" for a multi-session project involve?
Correct. The closing ritual is asking Claude to help update the project brief — covering what changed in Current State, new constraints, closed questions, and the next session's goal. This ensures session continuity.
Incorrect. The closing ritual involves asking Claude to help update the project brief based on what was accomplished. This 5-minute investment ensures the brief is accurate for the next session.
2. When two constraints conflict in a prompt, what does Claude typically do?
Correct. Claude typically surfaces constraint conflicts rather than silently resolving them. This is useful behavior — it tells you to either relax one constraint or split the task into two separate requests.
Not quite. Claude typically flags conflicts. This is helpful because it signals that you need to redesign the prompt — either loosening one constraint or splitting the task into two prompts.
3. What was the key addition Notion's internal prompt library database included that most teams omit — and why did it matter?
Correct. The Status field — active, archived, or needs-revision — gave users confidence information: knowing a prompt was tested two weeks ago versus eight months ago changes reliance decisions.
The Status field was the key addition. Knowing whether a prompt is active, archived, or needs revision prevents users from over-trusting stale entries or ignoring current ones.
4. What is the recommended phrase to include in prompts when using source material that may postdate Claude's training cutoff?
Correct. "Based only on the following information I'm providing" anchors Claude to your supplied material, preventing it from supplementing with potentially outdated training data.
The lesson recommends "Based only on the following information I'm providing" — this anchors Claude to your supplied material and prevents it from mixing in potentially outdated training data.
5. Why is specifying audience often more impactful than specifying your own role?
Correct. When audience isn't specified, Claude defaults to "general educated reader" — which changes vocabulary, depth, examples, and assumed knowledge in ways that rarely suit professional outputs.
Not quite. The reason is that Claude defaults to a generic reader assumption without audience guidance. Explicit audience specification calibrates vocabulary, depth, and assumed knowledge to what the actual audience needs.
6. According to the HubSpot case study, what is the most reliable mechanism for voice transfer to Claude?
Correct. Connor Cirillo's voice document prioritized example text above all other elements. Real examples — actual paragraphs in the target voice — are the most powerful voice transfer mechanism because Claude pattern-matches against them directly.
Not quite. Example text is the most reliable mechanism. Real paragraphs in the target voice give Claude something to pattern-match against directly — far more effective than adjectives, descriptions, or external references.
7. According to this module, when should prompts be revised? Which answer best reflects the lesson's guidance?
Correct. The four revision triggers are: model update, output degradation, scope change, and discovery of a better technique — not fixed schedules or whims.
Revision should be triggered by specific signals: model updates, output degradation, scope changes, or learning a new technique worth incorporating — not by fixed schedules.
8. What is the recommended team library governance structure described in Lesson 4?
Correct. A rotating 90-day library owner role plus a 24-hour review period treats the shared library as a curated product rather than a shared folder — preventing quality degradation.
The recommended structure is one library owner per rolling 90-day term with a 24-hour review period before new entries go live — enough structure to prevent chaos without requiring excessive overhead.
9. What was the specific symptom of context drift observed by Stripe's engineering team?
Correct. Stripe's team observed subtle drift in variable naming conventions and error-handling patterns — a gradual erosion of specificity as the detailed system prompt was diluted by conversation volume.
Incorrect. The symptom was subtle drift in variable naming conventions and error-handling patterns — gradual, not dramatic. The detailed API conventions were being diluted by the volume of subsequent exchanges.
10. Why do structural length constraints outperform word count limits?
Correct. "Five bullets" forces a prioritization decision — which five things matter most? "Under 200 words" often just cuts off a longer response without improving the selection of content.
Incorrect. The key difference is that structural constraints force prioritization. "Three bullets" means Claude must decide which three items are most important. Word count limits often just truncate without improving what's included.
11. What signal does it send when you are still making major revisions at message six of a conversation with Claude?
Correct. The lesson is explicit: continued major revisions at message six signal a flawed foundation. Continuing to iterate compounds the problem; starting fresh with a better prompt is more efficient.
Persistent major revision needs at message six signal a structural flaw in the original prompt. Rebuilding from scratch is more efficient than continued iteration on a flawed foundation.
12. What key finding from Notion's 2024 internal research justified the discipline of starting fresh conversations for complex tasks?
Correct. Notion's research found fresh-start users consistently outperformed long-session users, even controlling for task complexity — because starting fresh forces clarity about what actually matters.
Not quite. Notion's finding was that fresh-start users with well-crafted setup prompts consistently outperformed long-session users across the board. The mechanism: starting fresh forces you to know what actually matters before you begin.
13. In a Claude context window, which content appears first?
Correct. The system prompt always appears first in the context window, followed by conversation history in chronological order, then the current user message at the bottom.
Incorrect. The system prompt appears first in the context window, establishing the foundational instructions before any conversation history.
14. What did HubSpot's 2023 internal audit reveal about time-to-first-draft for library users versus from-scratch writers?
Correct. The audit found library users reached a usable first draft in 8 minutes vs. 31 minutes — a roughly 4× speed advantage.
Library users averaged 8 minutes to first usable draft versus 31 minutes for from-scratch writers.
15. What is a "token" in the context of Claude's language model?
Correct. A token is the unit Claude uses to measure text — roughly ¾ of a word in English. All context window limits are measured in tokens.
Not quite. A token is Claude's unit of text measurement — approximately ¾ of a word in English. All context window limits are expressed in tokens.
16. Why does this module specifically recommend XML-style tags as a placeholder convention for Claude prompts?
Correct. Because Claude's training included XML-structured documents, these tags carry semantic meaning for the model — not just visual convenience for the user.
The module explains that Claude's training data included substantial structured documents with XML-like markup, making those tags semantically meaningful rather than purely visual.
17. According to the Accenture 2023 survey, professionals who rated AI "not useful" had one characteristic in common. What was it?
Correct. The correlation between prompt length and satisfaction was strong — over 70% of "not useful" ratings came from prompts under 15 words, while "very useful" ratings averaged 47 words with purpose, audience, and constraints included.
The Accenture data showed that over 70% of professionals who rated AI "not useful" had written initial prompts of fewer than 15 words — missing purpose, audience, and constraints entirely.
18. A voice brief's four components are: positive examples, positive rules, negative rules, and what fourth element?
Correct. The four voice brief elements are: positive examples, positive rules (style directives), negative rules (anti-patterns), and a persona anchor — a sentence describing who is speaking, such as "a knowledgeable friend who is also an expert."
Incorrect. The fourth element is the persona anchor: a one-sentence description of who is "speaking" — for example, "a knowledgeable friend who happens to be an expert — warm, direct, never condescending."
19. Ethan Mollick's (Wharton, 2023) research found that the most effective AI users shared which specific habit after each productive session?
Correct. Mollick observed this micro-decision habit — asking whether you'd want to start from this prompt again — as the primary driver of productive library building.
Mollick documented the habit of asking "Would I want to start exactly here next time?" at the end of productive sessions, saving the prompt when the answer was yes.
20. Why did Rohan Desai's prompt template produce better NDA summaries than Lena Hartmann's single-line prompts?
Correct. Rohan's five-element structure gave Claude everything it needed: who to be, what to work from, what to produce, how to format it, and what to exclude.
The structural completeness was the difference: role, source document, specific output, required format, and explicit constraints. Lena's single-line prompts gave Claude almost nothing to work from.