WEBVTT 00:00:03.040 --> 00:00:07.934 In the design process, sometimes the  conversation is the design. 00:00:07.934 --> 00:00:15.497 And this idea gives me a new opportunity to remind you that we're doing an almost imaginative exercise here, 00:00:15.497 --> 00:00:20.880 but that building products will always require collaboration. 00:00:24.768 --> 00:00:31.715 Product design is about *people* using their critical thinking and feeling skills to solve problems for other people. 00:00:31.715 --> 00:00:37.760 And the process we're going through is not ideal, because it excludes real humans from it. 00:00:37.776 --> 00:00:45.640 But that's the goal here: learning about how far we can go with just AI and understanding its limitations on the way. 00:00:45.640 --> 00:00:53.356 Now we have an understanding of the market, the competition, the design questions we want to address with our product, 00:00:53.356 --> 00:00:59.817 some insights about our fictional users, it's time for the fun part – *brainstorming*. 00:00:59.817 --> 00:01:07.349 This is the part where I feel that AI is most robust right now, so let's see how we can co-create ideas with the help of AI. 00:01:07.349 --> 00:01:16.142 I will be feeding the 'how might we's and user stories to ChatGPT and ask it to come up with corresponding ideas to address them. 00:01:16.142 --> 00:01:23.936 The prompt could be something like: "Amazing, what are some ideas for a product (mobile application)" – it's important to specify context – 00:01:23.936 --> 00:01:31.645 "that could address these user needs and stories?" Let's see what our AI-powered brainstorming partner will come up with. 00:01:35.085 --> 00:01:39.972 As you can see, the initial response  is pretty generic. 00:01:39.972 --> 00:01:48.793 However, using prompting-refinement techniques, I will feed it more context and detailed instructions to get it where I want to. 00:01:48.920 --> 00:01:56.538 I'm going to take the most interesting ideas and ask it to dive deeper into them while keeping the persona in mind. 00:01:56.538 --> 00:02:04.825 I could also ask it to shorten the list of ideas, but this time I choose to use my critical thinking to choose the juiciest ones. 00:02:04.825 --> 00:02:11.461 I'm going to narrow down the scope of this conversation by prompting GPT to expand on a couple of ideas: 00:02:11.461 --> 00:02:16.155 the focus mode and smart task prioritization. 00:02:18.459 --> 00:02:24.384 As you can see, it's pretty interesting that GPT is already listing features and functionality. 00:02:24.384 --> 00:02:29.031 Okay, so these feel like pretty promising ideas – quite tangible. 00:02:29.031 --> 00:02:35.183 So, the natural next step would be to put more *detail* onto them, as well as more *clarity*. 00:02:35.183 --> 00:02:39.646 What do these ideas actually mean? How would these features actually look? 00:02:39.646 --> 00:02:42.838 Basically translating them into functionality. 00:02:42.838 --> 00:02:48.929 With the promising ideas that GPT generated, we're going to move further down the UX process line 00:02:48.929 --> 00:02:57.033 and try to translate them into functionality and features. This stage makes no exception for requiring critical thinking efforts. 00:02:57.033 --> 00:03:02.519 AI is not yet in a place in which it can reliably tell us what to build. 00:03:02.519 --> 00:03:08.606 If you really want to build meaningful products made of relevant features and useful functionality, 00:03:08.606 --> 00:03:15.821 you have to think it out yourself. AI will probably generate something quite generic, and it doesn't have the capacity 00:03:15.821 --> 00:03:20.354 to innovate and build an interesting, surprising product. 00:03:20.354 --> 00:03:26.440 I'm going to prompt GPT to translate the ideas mentioned before into a set of features. 00:03:26.440 --> 00:03:32.610 I'm going to focus the conversation on one of the ideas we've identified. The prompt could be something like: 00:03:32.610 --> 00:03:37.775 "Can you translate the ideas for Focus mode into features?" 00:03:43.360 --> 00:03:50.586 You could continue this exercise by trying to prioritize the list of features with the help of GPT. 00:03:50.586 --> 00:03:55.200 The prompt could be something like, "Which of these are the most important ones, 00:03:55.200 --> 00:04:00.381 the key features that would differentiate  this product from others in the market?" 00:04:04.599 --> 00:04:11.891 It feels that GPT sort of lost its way  here and it's repeating some of the earlier answers. 00:04:11.891 --> 00:04:17.559 But with refinement and proper prompts,  we can probably get it back on track 00:04:17.559 --> 00:04:20.534 and back in the context we were in. 00:04:20.534 --> 00:04:24.480 So, I'm going to try  to correct its course by instructing it to use 00:04:24.480 --> 00:04:30.705 the answers from the previous question  to create a priority list between them.   00:04:33.133 --> 00:04:38.616 This didn't go as planned, so we will try to refine the prompt even more. 00:04:46.000 --> 00:04:51.400 Finally, I'm getting the answer I was looking for. As you can see, I provided   00:04:51.400 --> 00:04:56.720 specific context, specific Instructions,  and I was pretty clear with the goal I   00:04:56.720 --> 00:05:01.080 had in mind when trying to get an output from GPT. 00:05:01.080 --> 00:05:05.675 It was finally able to prioritize between the feature it came up with. 00:05:05.675 --> 00:05:11.252 Most times, you'll need a couple of prompts before you can get the best result from GPT. 00:05:11.252 --> 00:05:16.568 This is a process of trial and error, there's a lot of experimentation involved, and I want to recommend 00:05:16.568 --> 00:05:22.840 everyone to try a couple of prompts, try a longer conversation until you get to the place 00:05:22.840 --> 00:05:25.778 where you feel the answer is most useful for you. 00:05:25.778 --> 00:05:29.737 You could take this exercise even further, making it more visual with 00:05:29.737 --> 00:05:34.440 plugins from GPT that help you generate diagrams, even user flows. 00:05:34.470 --> 00:05:40.458 Plugins are available here, and by using the list of features I've just generated and defined, 00:05:40.458 --> 00:05:44.239 I can ask it to create a user flow. 00:05:48.441 --> 00:05:54.995 We now have a – even though pretty basic – user journey map generated with the help of AI 00:05:54.995 --> 00:05:59.480 based on AI content.  It's pretty exciting if you think about it.