The UX of AI: Making AI-Powered Apps Your Users Don't Hate - Kathryn Grayson Nanz, Progress Software

1. chunk 0 · 0:01–0:44 · 135 words · 743 chars
2. 0:01 Hi, my name is Kat.
3. 0:02 I'm a senior design and developer advocate at Progress Software, and I have spent most of my career focused on the front end.
4. 0:10 After taking a somewhat meandering path through design and into development, I eventually found my niche in the space where those two worlds overlap.
5. 0:19 My design background has given me a lot of insight into the UX side of software engineering, and the user research that I get to do as part of my work as developer advocate is one of my favorite parts of the role.
6. 0:31 I have spent a lot of my career teaching developers about design, about UX, and about how to build more user-friendly software, something that's always been valuable, but is more crucial than ever now that AI has entered the picture.
7. chunk 1 · 0:45–1:26 · 114 words · 647 chars
8. 0:45 I don't need to tell you that AI is a pretty unique new technology.
9. 0:50 It is rapidly developing and has so much potential to improve systems and software in ways that we couldn't have even dreamed of just a few years ago.
10. 0:59 However, along with all of that potential is also quite a bit of risk.
11. 1:04 AI's non-deterministic nature means that the output can wildly range in quality, format, style, and accuracy, even when we're trying our best to prevent that.
12. 1:14 On top of that, it requires entirely new types of interaction patterns to use.
13. chunk 2 · 1:20–2:01 · 117 words · 692 chars
14. 1:20 In fact, we've seen the emergence of new vocabulary, techniques, and sometimes entire roles meant to address that need.
15. 1:27 For those of us that are living and breathing this technology every day, concepts like prompt engineers, hallucinations, retrieval augmented generation, and so much more have all become regular parts of our lives.
16. 1:39 But for the vast majority of our users, that simply isn't the case yet.
17. 1:45 In any kind of technology, there's a gap between the developer who has by nature kind of become the subject matter expert and the user.
18. chunk 3 · 1:53–2:33 · 116 words · 648 chars
19. 1:53 The technical literacy of the average software engineer is always going to be higher than the average user of said software.
20. 2:00 That's where UX comes in.
21. 2:02 It's how we bridge the gap between what we intended when we built an application and what the user actually experiences.
22. 2:10 After all, it doesn't actually matter what our software can do if our users hate using it so much that they will avoid it at all costs.
23. 2:18 And right now, AI has a kind of serious UX problem.
24. 2:23 Our users are seeing AI features get added to basically everything right now, from their work software to their social media apps, right down to their computer and phone operating systems.
25. chunk 4 · 2:34–3:16 · 129 words · 685 chars
26. 2:34 But as a wise technologist once said, your scientists were so preoccupied with whether or not they could, they didn't stop to think if they should.
27. 2:43 We're really pushing our users to adopt these new tools and features, but we're not always making it easy to do so.
28. 2:51 It's common to see situations where a user is presented with a poorly designed AI feature that they really only have the barest idea how to use.
29. 3:00 Then, when they try it and it doesn't do what they wanted or expected it to do, they feel annoyed and off-put and kind of negative about AI generally.
30. chunk 5 · 3:09–3:45 · 108 words · 577 chars
31. 3:09 The more times they try an AI feature and get subpar results, the less likely they are to engage with it again in the future.
32. 3:17 Which means that, as the creators of these features and software, we really only have so many chances to get this right before our users just disengage and stop trying at all.
33. 3:28 In my personal opinion, this knowledge gap between developer and user when it comes to AI is one of the widest that I've seen with any technology.
34. 3:37 That makes it extremely hard for us to build AI powered features that our users are actually going to get the full benefit from.
35. chunk 6 · 3:47–4:29 · 120 words · 707 chars
36. 3:47 When Macintosh introduced their graphical user interface, it was, like AI is now, something that was very different and unfamiliar to their users.
37. 3:56 But a large part of their success and reputation was built on their ability to create a user experience that met users where they were.
38. 4:05 They borrowed vocabulary and user flows from real life.
39. 4:08 They included lots of icons and visual representations, and they really made sure to walk users through how to get the most out of their new personal computers.
40. chunk 7 · 4:17–4:56 · 113 words · 645 chars
41. 4:17 And over time, as the average user became more comfortable and more literate in the space, the user experience of the Macintosh evolved with them.
42. 4:26 We start to see more technical terms and fewer abstractions.
43. 4:30 Look at the difference here between the control panels in Macintosh System 1 and System 6.
44. 4:35 If you had presented a System 1 user with the words rate of insertion point blinking or RAM cache, it would have been pretty much meaningless to them.
45. 4:44 Similarly, we see that those low and high volume icons are gone in System 6, along with the little turtle and rabbit speed icons, right?
46. chunk 8 · 4:52–5:31 · 103 words · 596 chars
47. 4:52 That kind of more literal depiction wasn't needed anymore.
48. 4:57 Right now, we are probably somewhere around system three in this metaphor of introducing AI to users.
49. 5:04 We may not need the turtle and rabbit icons anymore, but we also can't yet assume that they will sit down with our AI software as experts.
50. 5:13 The good news here is that, unlike the Macintosh UI, we're not totally starting from scratch here.
51. 5:19 Our users have existing mental models about software usage that's gonna carry over to what we're building.
52. chunk 9 · 5:26–6:03 · 105 words · 583 chars
53. 5:26 They're just not always going to map over exactly one-to-one, but that's where we come in.
54. 5:32 As developers, it's our role to leverage these patterns that our users are already familiar with, start to combine them in new ways, and then introduce them to our users gradually in a way that's not going to feel overwhelming.
55. 5:45 A good user experience will not only provide a user with the tools, but also guide them how to use them.
56. 5:52 For instance, let's look at an AI chat interface.
57. 5:56 From a purely UI perspective, chatting with an LLM is almost, but not quite, like chatting with another user.
58. chunk 10 · 6:04–6:49 · 133 words · 765 chars
59. 6:04 So we'll be able to borrow some familiar patterns here, like having the user's chats show up on one side and the AI chats on the other, messages that appear above an input field with a send button, a scrollable message history, and more.
60. 6:18 That gives our users a really good jumping off point and a lot of visual clues about how to start interacting with an AI chat.
61. 6:26 However, the experience isn't quite close enough that we can just lift an existing interface from direct messages and repurpose it wholesale.

loading