One-Page Major Glossary

Organize lecture terms into definitions, plain analogies, and tricky pairs.

Prompt · 2 variables

I am a student studying {{field of major}}. I want to compile the terms covered throughout this semester's lectures into a one-page glossary for quick exam review.

Please organize the list of terms below. Maintain a consistent depth of explanation across all terms, and group together concepts that frequently appear together in lectures.

Provide the output in a table format with the following columns: Term (with English original) | One-line definition (within 15 words) | In plain English | Commonly confused pair | Real example in {{field of major}}. Below the table, divide the terms into 3 to 5 thematic clusters, assigning a name and a one-line description to each cluster.

Do not add new terms that are not in the list. If a term has different meanings across disciplines, define it strictly in the context of {{field of major}} and flag it with "Meaning varies across fields." If a definition is ambiguous or context-dependent, do not guess; label it as "Needs Verification" and briefly explain what is ambiguous in one line.

List of terms: """ {{glossary list}} """

Copy, then paste here · ChatGPT and Claude open with the prompt filled in Open in ChatGPT ↗Open in Claude ↗Open in Gemini ↗ Edit in builder Download classroom card

Why it is written this way

Context
I am a student studying {{field of major}}. I want to compile the terms covered throughout this semester's lectures into a one-page glossary for quick exam review.
Task
Please organize the list of terms below. Maintain a consistent depth of explanation across all terms, and group together concepts that frequently appear together in lectures.
Format
Provide the output in a table format with the following columns: Term (with English original) | One-line definition (within 15 words) | In plain English | Commonly confused pair | Real example in {{field of major}}. Below the table, divide the terms into 3 to 5 thematic clusters, assigning a name and a one-line description to each cluster.
Constraints
Do not add new terms that are not in the list. If a term has different meanings across disciplines, define it strictly in the context of {{field of major}} and flag it with "Meaning varies across fields." If a definition is ambiguous or context-dependent, do not guess; label it as "Needs Verification" and briefly explain what is ambiguous in one line.
Input
List of terms: """ {{glossary list}} """

When you search for and compile course terminology term by term, the explanations end up having wildly inconsistent depths. One concept gets an encyclopedic breakdown while another gets a one-line casual metaphor from a blog. Putting them in the same study note makes it impossible to distinguish core fundamentals from minor details later on. This prompt feeds the whole list at once to measure every concept by the same yardstick.

The third paragraph (Format) forms the backbone of this prompt. Constraining the "One-line definition" to a brief length allows for quick scanning right before exams, while the "In plain English" column weeds out the illusion of competence—knowing the textbook definition without actually understanding how to explain it. The "Commonly confused pair" column is especially vital. Most exam mistakes happen not from total ignorance, but from mixing up two closely related terms. Pairing concepts like Mutex and Semaphore side-by-side lets you immediately contrast them.

The fourth paragraph (Constraints) prevents the glossary from bloating or hallucinating. Without telling the model not to add outside terms, it will eagerly append "related concepts," expanding your scope beyond the actual test syllabus. Authorizing a "Needs Verification" flag serves the same purpose; unless given a safe way to leave a blank, language models will invent plausible-sounding filler text.

Finally, wrapping the list in """ delimiters ensures that scratch notes mixed into lecture transcripts (e.g., "Review this later") are treated strictly as data rather than instructions. Such fragments often hitch a ride when copying directly from course notes.

Unfamiliar terms? See Aha AI: output-format, hallucination

Compared with a bad example

Common bad example

Tell me the definitions of these operating systems terms:

Process, thread, context switching, critical section, mutex, semaphore, deadlock...

The model will return full paragraphs for each term with inconsistent lengths and depths. As unstructured prose rather than a clean table, it is difficult to skim before an exam. Without identifying confused pairs, you might read about Mutex and Semaphore separately without grasping the crucial differences between them. Unsolicited "bonus concepts" may also slip in, broadening your study scope unnecessarily.

Variations

Self-Testing Right Before the Exam

Self-Testing Right Before the Exam

Please create a self-assessment checklist based on the list of {{field of major}} terms below. Do not include full definitions; instead, provide "3 mandatory keywords required when explaining this term" for each entry. Use the following table columns: Term | 3 Mandatory Keywords | Commonly Confused Pair. Below the table, provide the correct detailed explanations in a separate section so I can check my answers.

List of terms: """ {{glossary list}} """

Reading the full answer first creates a false sense of mastery. This variant shifts the workflow to active recall: test yourself using only the essential keywords before checking the answers.

Processing Raw Lecture Notes

Processing Raw Lecture Notes

Below are my lecture notes from {{field of major}}. First, extract a list of candidate exam terms from the notes and pause for my confirmation. Once I finalize the list, organize them into a table: Term (with English original) | One-line definition | In plain English | Commonly confused pair.

Lecture notes: """ {{glossary list}} """

Use this when you lack the time to manually pick out key terms. Pausing for confirmation prevents casual examples or side remarks in your raw notes from accidentally being treated as core terms.

Related prompts

Last updated 2026-09-02 · Found a mistake? Let us know