AI and user experience

Developing AI products in 2024

Transcript

1. AI and user experience Developing AI products in 2024
2. jerryjappinen@lateralnord.com +358 40 7188776 @jerryjappinen Product design consultant Jerry Jäppinen
3. AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI AI
4. Intro to AI UX patterns Wrap-up Q&A
17. Would you sell this? Would you buy this? Can we productise AI technologies today?
18. What are AI technologies? Language models Image models Audio models Video models … Various types of input ⬇ Weights, embeddings ⬇ Various types of output
19. What can AI technologies do? Generate text Generate images Generate video Generate audio Manipulate text, images, video, audio Recognise patterns Scrape content Transform content Translate content Analyse natural language …
20. How do we productise? What do we need?
21. Where is the industry now? Gold rush Models are available, on-premises and cloud Some models are open-source Everyone and anyone can use them Not much technical expertise necessary You can build something in a couple of days
23. nhost.io
24. R&D Expertise Infrastructure Cost UX Not a blocker Not a blocker Not a blocker Not a blocker ???
25. R&D Expertise Infrastructure Cost UX Not a blocker Not a blocker Not a blocker Not a blocker expectations, behaviours, beliefs, motivations, attitudes, preferences, patterns, conventions,…
26. AI and user experience
27. How do users use AI technologies?
29. Let ’ s ask the experts
31. We don ’ t have distinct “AI patterns” Yet I think there will be
33. Would you talk to AI in daily life? If your entire o ff i ce suite is point-and- click?
34. Real products need to sit into existing tool landscape We interact with AI computers just like other computers
35. UX patterns Miscellaneous collection, observed by me Nothing academic or official
36. Text prompt • Very common • Microsoft Copilot, Midjourney, Notion • Similar to Spotlight, Google search
38. Chatbot • Long sessions with back-and-forth • Expectation of memory and iteration • Amazon, ChatGPT, Gemini, Observable AI assist
39. Access to custom data ☝
40. 🐣
41. “Google Maps launches a new AI” or “new chatbot”
42. Image input • Where do I get the image? • Live camera UX is different from file upload • We already have patterns for image input
43. Image to text to image https://reads.alibaba.com/ai- image-tools-ecommerce/
44. Voice
47. Voice • Siri, Cortana, Alexa • ChatGPT plugins, Samsung Live Translate
48. Voice • Quick responses • Clean environment • Need to concentrate • Can ’ t glance information • How to follow up? • Privacy and security?
49. VR, video, gestures
52. VR, video, gestures • VR has been around for a while – still difficult • We have knowledge about the UX patterns: how to avoid nausea, enable precision, interpret input • Needs specialised equipment • Libraries and APIs exist • Keeps failing on the market
53. Emerging UX patterns My emerging vocabulary specific to generative models
54. “Prompt-output”
55. “I sketch, you fi nalize” sketchlogo.ai Midjourney
56. “You sketch, I fi nalize” ➡ ??? https://reads.alibaba.com/ai-image-tools-ecommerce/
57. “Press for magic”
58. “Press for magic” 🪄 Remove background
59. “Just do it”
60. “Inform without input”
61. “No nothing”
62. What do all of these have in common?
63. Text prompt Chatbot Image input Image to text to image Voice VR Video Gestures “Prompt-output” “I sketch, you fi nalize” “You sketch, I fi nalize” “Press for magic” “Just do it” “Inform without input” “No nothing”
64. https://www.samsung.com/latin_en/support/mobile-devices/how-to-use-live-translate-for-phone- calls-on-the-galaxy-s24/#:~:text=Once%20you%20have%20set%20up,Tap%20on%20Live%20translate. https://www.youtube.com/watch?v=6LOY4KHzFOQ Check consumer expectations Many “AI products” are live for consumers already
65. User expectations are high Error tolerance is low
66. Imperfections and slow responses can be UX deal breakers AI does not excel at these
67. “Trust but verify”
69. Productisation
70. R&D Training Infrastructure Cost UX Not a blocker Not a blocker Not a blocker Not a blocker ???
71. R&D Training Infrastructure Cost UX Not a blocker Not a blocker Not a blocker Not a blocker Not a blocker
72. You can productise AI models right now
73. R&D Training Infrastructure Cost UX Use cases Jobs to be done Value
74. Can we create something totally novel?
75. Of course. But it ’ s very di ff i cult And you will probably fail many times, like most innovators
76. Full “AI work fl ows” will still take a while Start with clearly de fi ned speci fi c tasks
77. You can manipulate bitmap images right now using image models Can we manipulate 3D fi les with these models? Maybe not with these exact models, but there ’ s a reference. Something to build on
78. What can AI technologies do? Generate text Generate images Generate video Generate audio Manipulate text, images, video, audio Recognise patterns Scrape content Transform content Translate content Analyse natural language …
79. Deliver every day End-to-end
80. AI revolution?
81. That ’ s it!
83. jerryjappinen@lateralnord.com +358 40 7188776 @jerryjappinen Product design consultant Jerry Jäppinen