Ognjen Divljak (@ogiogi) header
Ognjen Divljak (@ogiogi) profile picture

Product designer building with AI. Learning in public, sharing what works.

Banja Luka
Joined April 2008
Photo by Ognjen Divljak (@ogiogi)Photo by Ognjen Divljak (@ogiogi)Photo by Ognjen Divljak (@ogiogi)Photo by Ognjen Divljak (@ogiogi)Photo by Ognjen Divljak (@ogiogi)Photo by Ognjen Divljak (@ogiogi)Photo by Ognjen Divljak (@ogiogi)Photo by Ognjen Divljak (@ogiogi)Photo by Ognjen Divljak (@ogiogi)
I think chat is the wrong main screen for agents. I just want a list: done, waiting on me, stuck
1
1
3,535
before AI I had a list of projects I never finished now I have a github full of half built products I never finished how do you actually stay focused on one?
1
49
correct. my competitive advantage is now saying "no, not that one" to an agent 40 times a day
your Figma skills are not your competitive advantage anymore
1
2
89
every screen in my concept demo has a small tag: proven or new proven means a real app already does it this way. new means it's my bet it moved the review from "do we like this" to "do we believe the new parts"
2
49
designing with AI feels fast at the start. you get a lot on screen in minutes. then the polish takes way longer. aligning everything, fixing the small details. is it the same for you?
48
AI will do the well defined design work. The hard part was always deciding what to build when nobody agrees, and saying what it costs. That's the job now.
67
good UI didn't come from a prompt it came from being annoyed enough to iterate all day.
62
two designers planning a new product first topic: tech stack what a time to be alive
46
a working prototype is the new standard for product meetings first meeting should already be half ready. if we're just talking about the idea, we're wasting everyone's time
42
Everyone can picture AI going wrong. almost nobody can picture it going right i think that's a design problem. nobody has drawn what a normal day looks like in the good version
Two things I’ve been thinking about regarding AI: • People often highlight the risks involved in AI, which are surely very real. I’m struck, however, by how hard it is to understand the contours of the positive scenario. There are easy-to-perceive and frequently invoked elements of a positive vision — more diseases cured, more material abundance, etc. — which sound great, but these are by themselves just ingredients. I’m curious what the larger equilibrium is supposed to look like. Do people work? If so, why? What is their marginal contribution? If not, how are resources allocated? What is scarce? What is the ratio between humans and AIs? Are humans in control, whatever that means? One sometimes hears the Culture novels invoked as one scenario, but I’m not sure they depict a desirable outcome. (AI runs everything and humans compete in games? Iain Banks himself said that the humans in the Culture are “somewhere between passengers, pets and parasites.”) There is Richard Brautigan’s famous poem, but do we want to be “returned to our mammal brothers and sisters”? (Isn’t that rewinding Genesis?) We could say that it was hard to imagine the world of 1900 from the vantage point of 1700, and that’s assuredly true. But nobody in 1700 was trying to recast humanity itself within a couple of years — things necessarily unfolded slowly and by increments, and therefore with the possibility for error correction. Given how rapid the rate of progress in AI may be, it feels strange for the upside case to be so opaque. • There is increasing discussion of whether AIs are conscious or how we would know whether they are, with conclusions there often assumed to be relevant to matters of moral worth. At first blush, this seems a rather arcane, benign, or even absurd issue. (Remember the response to Blake Lemoine’s fears.) Setting aside the terms of the debate itself, or the relevant demarcation criteria, it seems to me a quite high-stakes question, for an affirmative answer — that is, granting moral worth to AIs — would presumably mean that the aggregate worth of AIs would soon outweigh that of humans in any utilitarian calculus. The AIs will be exceptionally wise and intelligent, and vastly more numerous (especially once one considers the imminent future and the AIs not yet born). As such, even epsilon of moral worth will multiply to a lot once one considers the quadrillions that could soon exist. (This is effectively a distributed version of the Nozick’s utility monster.) If this conclusion is unpalatable, I think one of three propositions needs to be rejected: the premise AIs can have moral worth; utilitarianism itself; or the belief that there is even a possibility that they will be far more numerous than humans. With both of these matters (contours of future society; AI moral worth), there is the possibility of dramatic change. Today, people argue about datacenters. I’m curious how popular support for AI will evolve as more people come to understand these medium-term questions and the relevant stakes. What is the vision for AI that most people would be excited about?
1
137
honest question for people building with agents how do you keep up? new tool every day, and testing them all properly is basically a full time job feels like only influencers can do it, and they're not shipping anything
16
8
447
same problem. hundreds of screens across files, easy to lose the empty and error ones I dumped them on one board once. an atlas that agents keep updated would be better
Our tool has so many screens, flow and states that it's easy to lose track of them. Today I had Claude build an Atlas tool that keeps track of them all and an MCP to update them after they change. Since agents can easily keep it up to date with recurring tasks this is such a nice add.
1
57
Designing with AI felt easy at first. Now it's kind of harder? I can spin up 20 variations in a minute, so picking one takes forever. I thought I was saving time, but I'm just spending it on more options. Not sure the end result is even better.
1
1
50
funny how half the design accounts I followed stopped posting about design now it's all agents, prompts and "I built this in 10 min" I miss the posts about spacing and type
2
77
we needed to brainstorm how to improve our internal tools instead of a meeting, I did a 20 min brain dump in Claude Code and shared the artifact the team is building on it async. we meet once, only to decide how many of your meetings end with an actual decision?
69
figma, claude code, codex. I use all three every week none of them ever told me a screen was bad that part is still on me
4
3
311
the revolut story isn't "designers are leaving figma". it's "the design system finally lives where an agent can read it". no coded system, no speedup. you just get faster slop.
7
5
247
voice is the interface I actually use now / this makes it one sentence away. try it
Everyone said "Hey Grok" was impossible on iPhone. Even Grok said Apple keeps wake words for Siri only. So I kept digging, and I found a way. Now I just say "Hey Grok" and Grok Bot voice chat opens. No extra apps, no cost, all built into iOS. How to set it up: 1. Make sure your Grok Bot app is up to date 2. Shortcuts app → + → Add Action → search "Grok Bot" → pick "Start Voice Chat with Bot" 3. Settings → Accessibility → Vocal Shortcuts → Set Up → pick that shortcut → type "Hey Grok" and say it 3 times 4. In the shortcut's details, turn on "Allow Running When Locked" If your phone is locked, iOS asks for one tap first. If Face ID already unlocked it, it's fully hands-free.
39
My feed has been full of smart home wall displays lately, so I had to make my own
43
Night mode for a solar energy app. Trying to keep it clean.
55