AI as Cognitive Prosthetic

“When I come back from Peru, I got a new job. And one of the things that I've noticed is that they always ask you, "What is your weakness?" And my weakness is definitely, I'm almost overly detail-oriented. That is a blessing and a curse because it means you can really get over-involved in the minutia and lose sight of everything that's out here. I find that when I'm controlling AI well and I'm using it to streamline my work or to help me think through a problem or to do affinity mapping, it's great at affinity mapping, the time for me to use it is when I'm over-involved in one little thread because what it'll do is broaden me out and give me 10 different threads that I might not be looking at.”

“I think it helps me zoom out and if I need to zoom back in, helps me zoom in. It has to be accurately prompted to do it. But I really think that that is probably where it benefits me the most: it helps me to see patterns and to see things that I might not otherwise because I'm very close to my work.”

“And it's in my calendar because I integrated Claude with my calendar. So, that's really helped because like I said, I have ADHD and Claude really helps me, is helping me stay on task better because I have 50 squirrel moments a day. That's why I have literally like 40 Claude projects. I love the projects.”

“But what the one thing it has cured for me is the way my brain works is I have like six streams of consciousness at all times. Like not voices, but you know.”

“No, no. It's true. But what it's done is be able to allow me to get all my ideas out of my head into a project. And that getting it out and knowing it's safe closes the loop in my brain where I can say, "All right, that project, it might not be done, but it's handled. It's in a place you can close the lid on it and visit it when you need to." And it's uncluttered my brain in a way that I really, because I don't take any medication or anything like that. I work out a lot. That's like my fix for a lot of my neurological oddities. So, that gift of being able to get [my thoughts] out, put it in a suitcase, know it's safe, and visit with it whenever I want to work on that.”

“A lot of the time I'm the type of person that, like, I can describe what I want, but I'm having a difficult time with, like, I'm a process brain first versus a visual person. Once you have the visual then I'm like, oh okay, I can run with this.”

“The other area that I've used it for most recently is with Figma. I'm not a big fan of Miro's AI capabilities. I don't think they're that good, but I'm using it for synthesizing research. So having spent almost an entire day synthesizing sticky notes or notes or interviews, if I'm able to do interviews, we have a research team, but being able to take a bunch of information that I would have to manually sift through to identify trends, being able to put a bunch of different formats of data, of information, and have it summarize it is really the biggest difference. So, especially with Figma, unfortunately we have a token limit now, but being able to just bounce ideas through the system and come up with a solution that I'm like, okay, how could I imagine this complex solution? Because a lot of the time I'm the type of person that, like, I can describe what I want, but I'm having a difficult time with, like, I'm a process brain first versus a visual person.”

“Once you have the visual then I'm like, oh okay, I can run with this. So I think most recently Figma Make has been the biggest change. But I think just the synthesizing of information, that you can just put it in a tool and have it spit out a summary, that has been the biggest change for me as a designer.”

“That was a big moment where I thought, oh well, yeah, this makes sense. Now I can actually see how I can use this to strategically iterate or tactically iterate different elements of it. The other part was when I actually hooked up Figma to Supabase, and was able to make this thing really work, rather than just building prototypes for 25 years. It's always been a game of, you know, "imagine if" and "don't go down this path" and all those different things where you're sort of emulating actual functionality. Here I was able to actually make it work and to save that information not just in the session but to persist over time, which allowed me to generate a whole bunch of fake data to actually store in the Supabase. That was a big moment, but probably even more so was the idea that I didn't have to learn how to configure that database. As I was telling Figma what I wanted it to do and making changes to the interface, it would say, "Okay, hold on. I need to go back and look at that database and either create a new handler for it, or I need to”

“change the way that this data is stored," because it will always assume the simplest thing. It will glom together five pieces of information into one item. But then when you say, "Well, actually, I want to use that information slightly differently," it will say, "Oh, I've got to take that big glob of information, break it up into five items. Hold on, let me go do that." And then it would make the changes in Supabase and round-trip those back to the interface. That was a sort of big moment for me, because I was like, well, I can get some of the functionality that I really want without necessarily having to go through and use a separate interface in order to try to describe what I need that database schema to be, which is really not my sweet spot. So the ability for the interface to infer what a database schema would be, and as I would imagine a whole bunch of other technical factors, from what I want the interface to be able to accomplish, and the functionality it has to support, was actually a big moment for me.”

“It's general time-saving. It's so silly. I feel so dependent on it. But if I need to ask someone a question, I will type it into ChatGPT first and then have it reword something, because I'm a very direct communicator and sometimes that comes off very strongly in emails. Sometimes I get vague, like I'm too vague. I've noticed there's just so much less miscommunication when I'm having that third party rewrite these for me, because there isn't personal opinion. There is no concern over "oh, I'm worried what they're going to think." It's just a third party without that emotional additive.”