5 Second Test
Show a screen for 5 secs, close, ask what user remembers
A/B testing
A usability technique where users are randomly assigned one of two experiences and the success of each is measured for comparison. For a website, for example, you might have the server generate a random number and if that number is < X user sees version A but if the number is > X users sees version B. For A/B testing to be useful, "success" needs to be measurable, like number of click throughs or time on site or sales.
Accessibility
Designing products, devices, services, or environments for all people regardless of physical or mental requirements. An image is worth a thousand words unless you are blind. Stairs between floors are an inexpensive way to connect two levels and help people keep fit. They also keep wheel chaired people down.
Affinity diagram
A way to visually represent the relationships among terms, grouping together like things. Affinity diagramming is used for designing navigation schemes and helping to understand how different elements of a data set fit together. Labeling items with # is one way to establish affinities.
Affordances
The way a product signals how to use it. You pull handles. You push buttons. Well designed products don't require instruction manuals and the best can't be unintentionally mis-used.
After engagement report
Notes taken to reflect upon some planned activity after it is over. The typical questions are
1. what worked
2. what didn't
3. what was learned
4. what remains unknown
5. what to do next
6. what to do differently next time
Alternative paths
Different ways to get to the same place; people often discover unintended uses and unanticipated means to known ends.
Black hat session
Black Hat sessions are inspired by Edward DeBono's Six Thinking Hats. 'Six thinking hats' is a facilitative framework where teams adopt deliberate mental attitudes in order to make group work more dynamic and directed. With a group discussion using six thinking hats, each individual figuratively puts on a hat of a certain color. Each color signifies a particular point of view. For example, there's a hat for optimism (the yellow hat), one for emotion (the red hat), one for creativity (the green hat), etc. There's also a hat for judgment, negativity, and skepticism, and that is the black hat.
Card sort
A process for identifying the best way to organize information, discovering hierarchies and relationships. UXers often have a handful of potential users sort items to figure out how users are likely to think.
What goes with what? Which of these things is not like the others? What order should these go in?
Whiteboards and multi-colored Post-it Notes are common tools for answering these kinds of questions.
Choice architecture
The expression 'choice architecture' refers to the practice of designing user options in such a way that users will more likely than not choose the option the designer wants while thinking they are choosing freely. Thus choice architecture can be exploited for good or evil, depending on intention and outcome. Techniques include Framing, Defaults, Nudges, Order of presentation, and Choice overload.
1. Framing -- people tend to see what their eyes are trained to focus on, the painting rather than the frame, the object rather than the backdrop, what the designer wants rather than other possibilities. A classic example from politics is renaming an inheritance tax as a death tax.
2. Defaults -- people tend to accept the given when it takes energy or thought or knolwedge to do otherwise. Terms of service rely on this fact. Designers can set the defaults to accomplish what they want accomplished, give users the option to customize, and be fairly certain that most users will go with the defaults, while some won't even notice customization was an option. A classic example of using default settings for the greater good is that in some countries a driver's license comes with a statement that says the licensee is an organ doner. A licensed driver has to opt out to not be an organ doner. Given that setup, a person would have to think, I might die in a car wreck and if I do, I don't want anyone to get my remaining organs. Very few people are likely to think like that, unless a religious conviction or some other consideration requires them to.
3. Nudges -- gently directing a user's attention in one direction rather than another, offering "options" in such a way that there seems to be only one good option. Pick a card, any card, while subtly making one card stick out. Shaming and social proof are two nefarious methods of nudging. A less nefarious approach is to make the better option most prominent and a single step process rather than a several step process.
4. Order of presentation -- If people are in a hurry, they will pick the first option. If they think they are being careful, they may pick the last one. And if they had to read through many, they are most likely to choose the last because that's the only one they remember clearly. The goldilocks option is also a thing, put the best in the middle and exaggerate both extremes. Free (but crap) | Good enough | Awesome but too expensive. You can also influence a decision by giving a list of options where option C creates a context that makes option D more compelling than if a user encountered D after A or on its own.
5. Choice overload -- people tend to freeze or at least hesitate if given too many options. This is why sales opportunities tend to limit the available choices. Given a choice between either A or B will tend to lead to a quicker decision that given A or B or C or D.
Cognitive Walk Through
A step by step rehearsal of a near-future activity. What do I need to accomplish, how will I do it, what difficulties or opportunities might I encounter, and how will I respond to each one? The word "cognitive" implies mental, but a cognitive walk through may be embodied as well. If you have ever watched a bobsled or grand slalom event, you may have noticed that just before the athlete pushes off, they do the course turn by turn in their head; you can see their body twisting and turning, anticipating, reacting. They are imagining millisecond by millisecond exactly what they are about to do. They are embodying the coming race, rehearsing mentally and physically. You see it with practice swings in golf and other sports as well.

A cognitive walk through isn't just verbal rehearsal pre-routine; it is going through the motions and the emotions, move by move, so that when it's show time, you can react without thinking. Often imagining the scene of engagement is a part of a cognitive walk through as well. You need to imagine yourself at the top of the precipice if you aren't already there.

That was a very dramatic rendition of a cognitive walk through, but thinking through a set of actions has to be more than procedural whenever it's possible for something to go other than as planned. If you have to give a speech, for example, if you memorize it word by word and then during the performance your train of thought is derailed, how do you recover? Even for stage performers reciting set lines, each performance is just a little different. You don't just do it over and over again; you live it over and over again.
Content Audit
Identifying, locating, and assessing documents for authorship, date last edited, purpose, audience, current state, ownership, and relevance for a current purpose. This information is typically kept and displayed in a spreadsheet or via a database.
Content Management Systems can automate the collection of much of this kind of metadata.
Contextual Inquiry
Observing and interviewing users in their actual work environment. Also known as observing in situ.
Curse of Knowledge
The assumption that what you know your users also know. Assuming a shared understanding leads to usability errors because what is obvious to you may be far from obvious for them.
Data / Feedback
In UX contexts, data refers to information (words, numbers, artifacts, and signs) gathered for purposes of discussion, reasoning, calculation, and decision making. Data is acquired by measuring, tracking, and analyzing. Data is relatively objective.
Feedback refers to user-perceptions. It can only be acquired by talking (questionnaires, ineterviews, in situ observations) with people and it is both subjectively derived and subjectively understood.
You can get data from a user without them knowing you did, but you can't get feedback that way.
Design Pattern / Schema
EOK (Easy Once You Know)
The phenomenon where tasks seem easy and obvious in hindsight, but are not apparent to new users. Related to the curse of knowledge, EOK emphasizes the need for outsider usability testing to identify issues not apparent to those with insider information.
Ethnography (ethno - people, graphy - writing)
A qualitative research method using observation, participation, and interviewing that seeks to accurately describe a people by understanding them as they understand themselves, from the inside as opposed to the outside. Objectivity, the view from the outside, is precisely what ethnography seeks to avoid.

From a UX perspective, what the designers and programmers of a product think about it doesn't matter even if they use the product themselves. To make a successful product you need to know what its like to use it without insider knowledge (to avoid the curse of knowledge and EOK). You need other people's perspectives. That is why UXers need to spend time with clients, living among them, as it were, to see and feel what it's like to be them, from the novice to the power user.

The connection between Rhetoric and Anthropology, where Ethnography came from, was formalized for me by Clifford Geertz's conclusion to his acknowledgements in Works and Lives: the Anthropologist as Writer
Finally, in lieu of a dedication, which would be presumptuous, I would like merely to mention the name of the man, nowhere cited in the body of the text, who has had no direct connection to it or me, but whose work has served as its governing inspiration at almost every point: Kenneth Burke.

Wiki article on Kenneth Burke
Focus Group
From ChatGPT:
A "focus group" is a research method used to gather feedback and insights about a product, service, or concept from a selected group of people. This group is typically composed of potential users or current users of the product or service being evaluated. ... Focus groups in UX research are particularly valuable during the early stages of product development, when understanding user needs and reactions can significantly influence design decisions. However, the findings from focus groups are often complemented with other research methods, such as surveys or usability tests, to validate and broaden the understanding of user experiences.
Heuristics
In rhetoric the word heuristic means invention, the process of coming up with things to say. In contemporary language, a heuristic is a shortcut, a rule of thumb that works effectively for the most part most of the time. Jakob Nielsen, one of the OGs of usability, identified 10 usability heuristics:
1. visibility of system status -- keep users informed
2. use familiar, real world, language -- no jargon, no site specific lingo
3. users should be in control -- provide levels of undo, save work in the background
4. follow industry standards -- save means save regardless of platform
5. don't let users make mistakes
6. recognition over recall -- don't make users remember or have to think
7. flexible designs -- experts should have shortcuts and other tools that aren't visible to novices who will be distracted or confused by them
8. minimalist design -- don't clutter the screen, don't add images as decoration
9. no error should be fatal -- offer clear signposts and ways to start over efficiently
10. provide help -- but design so no one needs it (and assume no one will read it)
Nielsen Norman Group
Heuristic analysis is the practice of having informed users -- people who know the 10 heuristics -- use a product to see where it fails to conform. It's a quick and typically cheap kind of quality control. If you pattern what you make after industry standards, you can presume you're designs conform, though you should verify.
Human Computer Interaction
Hypothesis
A useful, falsifiable assertion. The purpose of research is to find out if H is or is not the case where H is important to know. Do users like A or B? Well, what does like mean? How do you measure like? And what difference does it make if they like or don't like?

From ChatGPT:
In a User Experience (UX) setting, a good hypothesis serves as a valuable tool for guiding research, design, and evaluation efforts. Here are some characteristics of a good hypothesis in a UX context:
1. Clear and Specific: A good hypothesis should be clear, specific, and focused on a particular aspect of the user experience. It should leave no room for ambiguity and clearly state what you aim to test or investigate.
2. Testable: Your hypothesis should be testable, meaning that it can be proven true or false through research or experimentation. It should be framed in a way that allows you to collect data and evidence to support or reject it.
3. Based on User Insights: A strong UX hypothesis is often informed by user research and insights. It should reflect a deep understanding of your target users, their needs, behaviors, and pain points.
4. Linked to a Goal: A UX hypothesis should align with broader project or product goals. It should help you move closer to achieving those goals by addressing a specific aspect of the user experience.
5. Measurable and Quantifiable: To assess the validity of your hypothesis, it should include measurable variables or metrics. This allows you to quantify the impact of your proposed changes or interventions.
6. Time-Bound: A hypothesis should have a clear timeframe or duration for testing. This helps in planning and executing research and evaluation activities efficiently.
7. Hypothesis Statement: It's often helpful to structure your hypothesis as a statement that follows the "If-Then-Because" format. For example, "If we improve the checkout process by reducing the number of steps, then we expect to see an increase in the conversion rate, because it will be more user-friendly."
8. Grounded in Prior Knowledge: Your hypothesis should be informed by existing knowledge, whether it's from prior research, best practices, or industry benchmarks. It should build upon what is already known or assumed.
9. Focused on Impact: A good hypothesis should address a problem or opportunity that, if solved or leveraged, would have a meaningful impact on the user experience and, by extension, on the success of the product or project.
10. Open to Revision: Hypotheses are not set in stone. They should be flexible and open to revision based on the findings and insights obtained during the research or testing phase. You should be willing to adjust your hypothesis if the data doesn't support it.
11. Ethical: It's important that your hypothesis respects ethical considerations, especially when conducting user research. Ensure that you are not causing harm or discomfort to users and that you have obtained proper consent.
12. Relevant to the Target Audience: Your hypothesis should address issues or opportunities that are relevant and meaningful to your target users. It should enhance their experience or solve a problem they face.
In the UX field, hypotheses play a critical role in guiding the design and evaluation process, helping to ensure that your efforts are focused and data-driven. They serve as a foundation for creating user-centered solutions and improving the overall user experience.
In situ
Latin for 'in the place', referring to on-site observation and engagement to deepen understanding. It values direct observation over reported information, emphasizing the importance of cultural immersion and careful, non-intrusive inquiry.
Contextual reporting and rich contextual reporting are synonyms. The Anthropologist Clifford Geertz used the expression "thick description." The goal is to make your readers imagine the scene so completely that they feel like they are there with you.
Informant Reliability
How credibile is your informant or participant? Do they know what they are talking about? Are they telling the truth? Might they be witholding or sugar or shit coating? Are they making stuff up to look smart or cooperative?
Information Architecture
The structural design of information systems, focusing on organization, labeling, searching, and navigation. Key components include site structure, navigation design, taxonomy, search optimization, metadata, URLs, and labels. The goal is to create a user-friendly structure that evolves with content and user needs.
George: Hey Claude, define information architecture for me
Claude: Information architecture is the structural design of a website, application, or other information system. It focuses on organizing, labeling, searching, and navigating content in an intuitive way that meets user needs. The main components of information architecture for web design include:
- Site structure - How the site's pages and sections are organized. A common structure is a hierarchical model with main sections and subpages.
- Navigation design - The interface to move between pages and sections. This includes menus, links, buttons, and other navigational elements. Effective navigation is intuitive and helps users find desired content.
- Taxonomy - A classification system to categorize and label content. This includes site-wide taxonomies for topics, as well as labeling schemes within content types.
- Search - Allowing users to find content by entering keywords. Search should be optimized to return relevant results.
- Metadata - Data that describes content, like page titles, descriptions, tags. This improves findability and search engine optimization.
- URLs - Unique web addresses that represent content pages and reflect the site hierarchy. Well-structured URLs improve usability.
- Labels - Descriptive text used to represent content, categories, and site sections. Clear, consistent labels help users know what content they will find.
  The goal of information architecture is to create a structure optimized for usability. A solid IA allows users to efficiently navigate and digest content. It evolves over time as content and user needs change. Testing IA with real users reveals issues to improve. Overall, good information architecture is essential for an effective web presence.
Informed Consent
Ethical research requires willing participation on the part of any human subject involved. In order to willingly consent, each participant must know what the research's is, who is conducting it, why it is being conducted, how it will be conducted, and how long it will take, the foreseeable risks or discomforts, that they can stop whenever they want for any reason, that the information will be anonymous and stored in a secure way. They also need to know whatever benefit, if any, they will receive for participating. Each participant must sign and date the consent form, which must be written at a reading level any subject can understand.
Interface
The part of a product or service that users interact with. The design goal is typically simplicty.
Intermittent Reinforcement
Using random rewards to create habitual use or addiction. It's a technique used in various contexts, including digital product design, to increase engagement.
Interview
A face-to-face, question-driven conversation where responses are recorded for analysis. Effective interviews often involve transcription for coding and theme identification, and may require a team approach for natural engagement and accurate recording.
For UX, interviews are neither interogations nor evaluations. The goal is to learn what a person is experiencing and why without judgement.
Intuitive Design
A design that doesn't require instructions to use successfully. What is described as intuitive is often just coventional. The learning happened so long ago you don't remember learning it and now you rely on it without thinking.
It Must Be Broken
When a user doesn't achieve their expected outcome, they are likely to blame the product. The most common user error is assuming one hasn't made one.
This concept highlights the importance of intuitive and error-tolerant design.
Iterative Design
A process of continuous improvement in design through repeated cycles of testing, feedback, and refinement. It emphasizes adaptability and responsiveness to user needs and feedback.
Journey Map
Visualization of the process a person goes through to accomplish a goal.
Leading Questions
Questions that suggest a particular answer. In UX, it's important to ask unbiased questions that don't lead respondents to a preferred answer.
Likert Scale
A method for measuring subjective impressions on a scale from zero to full or low to high. Typically people use an even number of nodes on the scale so that people can't choose a non-committal middle score. If, for example you offer 5 nodes, the tendency will be toward 3. If you offer 4 or 6, then people have to pick a side.
Example: On a scale of from 1 to 4 where 1 is not helpful and 4 is very helpful, how to do you rate this section of the book? 1------------------2------------------3-------------------4
To get truly insightful information from this method of subjective measurement you need to label each option: 1 = not helpful, 2 = somewhat helpful, 3 = helpful, 4=very helpful. You also need to know precisely what differentiates somewhat from not very. Thus Likert scales are often a good place to start dividing a population into segments, but a bad place to stop. You almost always need to follow up with a questionnaire to find out what didn't work for them that led them to say somewhat helpful, what worked what didn't. The only time a Likert scale is useful on its own is when the options are unambiguously different.
A classic example is the 😊 😞 you might see at the exit of a bathroom in an airport. Different cultures and different people within the same culture have different ideas of cleanliness, but there's enough overlap to make a simple yes or no useful, especially if you have more than just a few data points.
Margin of Error
ChatGPT:
A statistical measure used in surveys and polls to quantify the uncertainty or potential variability in the results due to sampling error.
In other words, when you do a study, how statistically confident should you be that the numbers you gathered from your sample are representative of the entire population? The larger the percentage of the entire population you sample, the greater your confidence can be that any individual drawn from the population will display the attribute identified in the sample.
Mental Modal
Assumptions a person has about how something works and therefore how to use it.
If you design things, you need to know how people expect them to work and accommodate those expectations in some way.
As a researcher, your goal is to discover users' mental models and to use that knowledge to design and test the usability of your products. It is important to remember that a mental model might have little to do with reality and still work for the person who thinks that way. Most of the time your goal is to enable the model rather than correct it, unless you are a teacher, of course.
Minimal Viable Product
The highest fidelity prototype or alpha release of a product, sufficient to gather user feedback and make improvements.
Mockup
Visual representations of a product in low or high fidelity, used in the design and testing phases.
N value
The number of respondents in a study or survey. A larger N value typically indicates more reliable data.
Navigation
How a user finds what they are looking for. The goal is to make everything no more than a few clicks away, a mile wide and an inch deep. The standard techniques are menus top navigation bars
dropdowns
side bars
search boxes, site maps ChatGPT -- HTML Sitemap: This is a human-readable page that includes links to all the important pages on your site. It's often placed in the footer or another easily accessible location., jumptos (like a table of contents or list of section headings that take user to that part of the same file when clicked), accordions, and link text (text that when clicked takes a user to another file (internal link) or another website (external link). It was once common to have both global (access all sections of a website) and local navigation (access all parts of a section) on every screen. Global was often achieved by a menu bar across the top and local by a column of links down the left side. Local navigation is less common now, although some big sites use a "mega menu," which combines both.

The worst navigation schemes make users "pogostick" or bounce forward and backward, up and down, looking for something. Bad navigation schemes also call known things by unknown names or bury the most often sought after items among less sought after ones.
Operationalize
To make a concept measurable and actionable, often used in research and data analysis.
Order Effects
The influence of question order in surveys or questionnaires on respondent answers. Includes effects like anchoring, consistency, fatigue, memory retrieval, and priming.

Some common order effects are:
1. Anchoring -- sales people take advantage of this effect by giving you a "retail price" that is far higher than the price you are to pay and thus by contrast you feel like you are getting deal. In a questionnaire, if you were to preface a question by saying something like, the national average of hours worked is 80 a week, and then ask how many the respondent works, they will likely be influenced by the 80 hours anchor. How they are influenced may be very hard to tell unless you can ask a clarifying question later.
2. Consistency -- people don't like to contradict themselves but they are ok with hypocrisy when the don't notice it. So if you ask a question and then later ask another one that indicates a contrary answerer to a respondent, they will contradict themselves if it has been a few questions since but they will lie to be consistent if the contrary question comes right after the one they just answered.
3. Fatigue -- people start ticking boxes with little or no thought when asked too many questions. Because questionnaires are now very common, people get tired quickly. Ask the least number of questions possible.
4. Memory retrieval -- People will often select the last option simply because it is most vivid in working memory.
5. Priming -- a preceding question can influence how a subsequent question is answered. If you were to ask, for example, about something that triggers a positive memory, then the next question might be answered in the most optimistic fashion possible, and vice versa. Since you probably don't know what triggers a given respondent, you have be generally on guard about how QA might effect QB
6. Social desirability -- people, most people, don't like to express opinions they think abnormal or self-diminishing. If you ask someone about their alcohol consumption, they are likely to under report if they think they drink more than they "should." Any potentially embarrassing question has to be asked carefully, non-judgmentally.
Pain point
Or pinch point or bottle neck. A place where a user has a negative experience, typically frustration or confusion, that leads them to abandon or start over whatever process they were trying to complete.
One of UX's primary goals is to identify pain ponts so that designers or engineers can eliminate them.
Perpetual Novice
A user who interacts with a product so infrequently that each use feels like the first. Design for these users requires a focus on recognition over recall to ease their experience.
Personas
A persona is a research-based representation of a segment of your inteneded population (audience), depicted as if a real person, a simulated individual that is in fact a generalization. A persona is not a stereotype. It is not a character, and even less a caricature. A persona is a composite.
Each persona has a name, biographical data, a photograph of someone who looks like what the data suggests, a context, a primary goal, a set of attitudes, beliefs, identifications, and mental models (how they think something works which may or may not resemble reality).
Businesses use personae to make sure that everyone writing for the company -- or designing for the company -- has a clear sense of who they are writing to and working for.
Prototype
A version of a product that has full functionality and closely resembles the final version. It's more advanced than a high-fidelity mockup and is used for final testing before production.
Quantitative / Qualitative Research
Three methods of research: Quantitative produces numbers, qualitative produces narratives, and mixed produces numbers-backed narratives. All three are performed in order to inform decision-making.
To some extent the object of analysis determines which method is best, but a researcher's skill-set often dtermines what kinds of objects they will choose to analyze.
Questionnaire
A collection of questions the answers to which should provide insight into a specific respondents' attitudes towards something. Questions can be close-ended (yes or no) Likert scale (Strongly agree - Strongly disagree) or open-ended, where the informant can say whatever they want to say. Questionnaires are typically short, 5 questions at most.

Research Question : What was your checkout experience like and what effect will it have on your next purchase? 1) On a scale of 1 to 5 where 1 is not satisfied and 5 is totally satisfied, how would you rate your checkout experience? 2) Do you plan to shop with us again? NOTE the risk of a testing effect here. The answer to 1) might influence the answer to 2) but a person might have a different reason for how they answered 2. Reminding a person that checking out sucked might lead them to the conclusion they wouldn't return. But if they hadn't been reminded, they might say they would return.

A questionnaire should begin by providing the informant with a context, what the research is about, and why their opinion matters, but it should not lead them to any preconceived ideas about how they should answer or who they want the interviewer to think they are.
Sample Size
The subset of a total population that receives a survey or questionnaire. In digital environments, the sample size can potentially include all users, but in-person interviews require a representative sample size to be determined beforehand.
Sample Size Calculator
Sample, Convenience
A sample composed of individuals who are readily available, people who work for the company or students enrolled in a psychology class or a UX class, which means they have attributes that are likely to make them non-representative of the intended population.
Sample, Representative
A subset of a population that provides statistically generalizable data, representing the diverse variations within the user base of a product or service.
From ChatGPT:
To identify a representative sample size for a population of N, you can use statistical formulas and calculators that help determine the required sample size based on your desired level of confidence and margin of error. One commonly used formula is:

n = (Z^2 * p * (1-p)) / E^2

Where:
- n is the required sample size.
- Z is the Z-score, which corresponds to your desired level of confidence (e.g., 1.96 for 95% confidence).
- p is the estimated proportion of the population with the attribute you're interested in.
- E is the desired margin of error (expressed as a decimal).

Here's how to use this formula:
1. Determine your desired level of confidence (usually expressed as a percentage, such as 95% or 99%).
2. Estimate the proportion (p) of the population that possesses the attribute you're interested in. If you don't have an estimate, you can use 0.5 for a conservative estimate, which will give you the largest required sample size.
3. Decide on your desired margin of error (E), which represents the maximum acceptable difference between your sample estimate and the population parameter.
4. Plug these values into the formula to calculate the required sample size (n).
Keep in mind that there are online sample size calculators and software tools available that can simplify this process for you. You can enter your specific values, and these tools will provide you with the recommended sample size.

Additionally, if you're working with complex survey designs or populations with specific characteristics, you may need to consider stratified sampling or other methods to ensure your sample is truly representative.

Always remember that the quality of your sample and the accuracy of your results depend on how well you select and collect your data, so careful planning and consideration of your research objectives are crucial.
Sample, Self-Selected
A group of participants who volunteer to be test subjects. Because they self-selected, they can't be assumed to represent the intended population as a whole.
Scenarios and Storyboards
From MS's Copilot:
A scenario in UX is a narrative that describes how a user interacts with a product or service to achieve a specific goal. It usually includes the user’s context, motivation, actions, system responses, and expected outcomes. Scenarios help to illustrate the user’s needs, behaviors, and pain points, as well as the value and benefits of the product or service. Scenarios also guide the design and evaluation of the user interface, as they provide realistic and concrete examples of how the user would use the product or service in different situations.
Some examples of scenarios are:
Alice wants to book a flight to Paris for her vacation. She opens the travel app on her smartphone and searches for flights from New York to Paris on the dates she prefers. She filters the results by price, duration, and airline. She selects the best option and proceeds to the payment page. She enters her credit card details and confirms the booking. She receives a confirmation email with her itinerary and boarding pass.

Bob needs to write a report for his boss by tomorrow. He opens the word processor on his laptop and creates a new document. He types the title and the introduction. He inserts a table of contents and some headings. He copies and pastes some data from a spreadsheet and formats it. He adds some charts and images from the internet. He checks the spelling and grammar. He saves the document and exports it as a PDF. He attaches the PDF to an email and sends it to his boss.

Carol wants to watch a movie on her smart TV. She turns on the TV and browses the streaming service. She looks at the recommendations and the genres. She finds a movie that interests her and reads the synopsis and the reviews. She decides to watch the movie and presses the play button. She adjusts the volume and the brightness. She pauses the movie when she needs to go to the bathroom. She resumes the movie and enjoys it.

interaction-design.org
User Scenarios
Step-by-Step Guide to User Scenarios
SMART
In project management, the acronyum SMART stands for:
Specific: What exactly do you hope to achieve?
Measurable: Can you measure change well enough to know what effects your efforts are having?
Achievable: Can you do this?
Relevant: Will doing this accomplish something important?
Time-bound: What is your deadline? Also in the sense of kairos, is this the right time?
Research projects require a solid rational and this framework can be very useful.
Survey
A method of collecting data from a group, focusing on identifying trends or patterns through numerous questions. Surveys provide a broader focus compared to the more narrowly focused questionnaires.

A survey should begin by providing the informant with a context, what the research is about, and why their opinion matters, but it should not lead them to any preconceived ideas about how they should answer or who they want the interviewer to think they are.
Task Analysis
A step by step description of how a task is performed, used as a blueprint to design a process.
From a UX perspective, a task analysis involves watching a person do what they do to accomplish a goal. While you can ask an informant to self-report, many tasks have implicit steps and so the informant may unintentionally leave some steps out.
Watching (while present or via recording) someone perform the task while they say what they are doing and thinking as they do each step can provide a much more precise description.
Task analysis should be done from observations in the client world rather than from how an engineer imagines an existing process is performed or thinks it should be because the imagined and the ideal may not serve a pre-existing reality. On the other hand, if the process doesn't already exist and users will learn to do it based on the steps provided, than an ideal representation will be necessary. It can then be validated via user observations.
Think Aloud Protocol
A UX research method where users verbalize their thoughts and feelings while interacting with a product, providing insights into their cognitive processes and experiences.
From Claude:
The think aloud protocol is a method used in user experience (UX) research to gain insights into how users think and feel as they complete tasks on a product or service.
- Researchers ask representative users to perform typical tasks while verbalizing their thoughts, feelings, questions etc. as they go. For example, a user might say "I'm clicking on this button because I want to see my account details".
- Sessions are recorded or observed, taking note of what users say and do. Researchers aim to avoid interfering with the participant's natural behavior.
- After the session, researchers analyze the notes and recordings to identify usability issues, confusion points and insights into the user's mental model.
- Feedback is used to iterate on the product design and make the user experience more intuitive. Key benefits of think aloud studies:
- Provides direct access to user thought processes, questions and emotions
- rather than having to infer them.
- Identifies usability issues and confusion points that may not be uncovered by observation alone.
- Useful early in design process to understand user expectations and mental models.
- Complements other UX research methods like surveys and analytics.
- Relatively quick and inexpensive to conduct.
- Can be done remotely via screensharing and video conferencing.
Limitations include possible interference with natural behavior, and difficulty interpreting complex cognitive processes. Overall, the think aloud protocol is a flexible UX research method to uncover insights from representative users.
Unanticipated Uses
UXers sometimes discover that users have found an undocumented way to do something or even sometimes how to do things the designers hadn't designed it to do. UXers also sometimes discover unmet needs that future designs can address.
Feature creep, however, and project sprawl are to be avoided.
Usability Research
Research methods aimed at eliminating the possibility of user errors or frustrations. Usability seeks objective data rather than subjective assesments. It assumes all users are essentially the same -- utilitiy over aesthetics (look) or phenomenology (feel).
Use Case
From MS's Copilot:
A use case in user experience research is a written description of how a user interacts with a product or service to achieve a specific goal⁴. It outlines the steps that the user takes, the system responses, and the expected outcomes. Use cases help to define the user requirements, design the user interface, and test the usability of the product or service³. Use cases can also help to communicate the value proposition and benefits of the product or service to the stakeholders and potential customers⁵.

Some examples of use cases are:

- As a customer, I want to order a pizza online, so I can get it delivered to my home.

- As a student, I want to enroll in a course, so I can learn new skills and earn credits.

- As a manager, I want to generate a report, so I can analyze the performance of my team.

Use cases are different from user stories, which are shorter and more informal descriptions of user needs and goals. User stories are often used in agile development methods, while use cases are more common in traditional or waterfall methods¹. User stories focus on the value and benefit of the feature, while use cases describe the details and logic of the interaction².

Source: Conversation with Bing, 11/17/2023
User Flows
The path a user takes through a product, highlighting how they interact with the product to complete tasks. It involves understanding the user's journey, time spent on tasks, and their navigational choices.
User-Centered Design
Designing a product from the perspective of the users rather than from the perspectives of engineers, accountants, or marketing teams.
User-Experience Research
An ethnographic methodology using surveys, questionnaires, interviews, task/observational analysis, prototyping, and usability testing to understand how people feel about using a product, often while they are using it. The goal is to understand what it's like to be the user well enough to know how to improve the product experience and thus increase repeat sales. While UX typically informs the product design or redesign, it may discover that how the product is understood needs to be addressed rather than the product itself.
User-Experience Strategy
The planning phase prior to designing, focusing on aligning design decisions with user needs and business goals.
Wayfinding
Designing clear, intuitive guidance systems to help users navigate physical or digital spaces. This involves the use of visual, tactile, or auditory signs to guide users effectively.
Wireframe
A low-fidelity mockup, a gray scale representation of a product's basic look and function. A wireframe might be nothing more than a sketch on a scrap of paper. Fast and cheap.