AI and UX Flashcards

1
Q

Why use AI in UX?

A

Increased Productivity
* Many studies have shown that business professionals produce deliverables faster using AI.

Improved Quality
* AI generates as many ideas as you want in no time, and often with the same or better potential as human ideas that require extensive effort to produce.

Enhance Your Skills
* AI has the power to augment the skills that humans already possess. The flip side to infinite ideation is the increased need for human curation of those ideas, winnowing them down to the few that bear further exploration and implementation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

3 reasons to include a heavy dose of human judgement in the workflow (AI in UX)

A

Humans Must Select Ideas Suggested by AI: the beauty of AI is its ability to generate endless ideas and variations, but not all will be useful (or even reasonable) suggestions.

Hallucinations Can Be Convincing: human judgment is to catch “hallucinations” where AI proclaims things with great confidence that are false.

Bias Lurks in Training Data: Current AI also exhibits some bias because it reflects its training data, which mostly came from reading the internet.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

How to use AI - Provide ample context in your prompts

A
  • For example, if you want to have ChatGPT help you craft a research plan, you’ll need to give it lots of details — the type of study, the target audience, research budget, timeline, etc.
  • These details can be provided in a few different places:
    • In one very specific and long initial prompt
    • In a sequence of several prompts
    • ChatGPT’s custom instructions
  • ChatGPT’s custom instructions feature allows you to specify information that you always want it to take into account.
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

How to use AI - Ask for multiple options and/or Iterate on the output

A

The process of using AI (specially composing prompts) is iterative and requires adjustments to fine-tune the outcomes. Don’t be satisfied with the outcome of your first prompt.
* Accordion editing: Users adjust AI-generated text length iteratively by expanding and compressing.
* Apple picking: Users reference elements in previous AI responses to modify the following prompt.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

How to use AI - Build a prompt library

A

Build up a prompt library with the exact wording of prompts that have worked well for your scenarios

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Specific UX Tasks for AI - Design

A
  • Generate ideas to inspire creativity
  • Create illustrations for personas and journey maps
  • Plan out a workshop agenda
  • Produce text and images for use in prototypes to increase realism and relevancy instead of “lorem ipsum”
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Specific UX Tasks for AI - Research

A
  • Write user interview questions
  • Sentiment analysis for initial theme finding
  • Analyzing user feedback: “Identify the most common pain points mentioned in the following user feedback: [feedback].”
  • Rewrite research reports to be clearer for your audience, who are often not UX specialists
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Specific UX Tasks for AI - Content

A
  • Write text more efficiently, such as for emails, concepts, or posts, based on outlines you provide
  • Improving UX writing: “Make the following text more concise and userfriendly: [text].”
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What AI Can’t Do

A
  • AI-derived design critique is dangerous because many of its insights are wrong
  • AI cannot substitute for user research with real users
How well did you know this?
1
Not at all
2
3
4
5
Perfectly