Design at the Speed of Adjectives — Paul Bakaus, Renaissance Geek, Inc.

AI Engineer · 15 min · 175 sentences · from YouTube's caption track

Each timecode opens YouTube at the start of that sentence. Line anchors (#s42) are the cue ids in the WebVTT, and every line carries its start and end seconds. All transcripts has every talk, and the whole corpus as one file.

00:01[music]
00:12Cool.
00:13Uh, let's get this going.
00:15Welcome everyone.
00:16Thanks for coming.
00:18Um, my name is Paul and, uh, I'm going to try to save you from the midday slump.
00:23So, let's, uh, let's see if we can do that.
00:26Um, okay.
00:27So this talk, this cold open of this talk will make a lot more sense if you know uh what impeccable is.
00:34Uh but if you don't know what it is, it's a design, it's a design skill that turns your coding harness into a better designer and hopefully you into a better designer.
00:41Um and you can try it out.
00:43It works across all harnesses, cloth code, github, copilot, cursor, codex, etc. Um, and this talk is really about uh my approach to how to building this tool as opposed to the tool itself.
00:58Um, but let's get started with a pretty typical website.
01:01So, this is a intentionally very basic website and I want to give you that one as context to what I'm going to show you next.
01:09So, you know, it's it's a it's it's an okay website.
01:12It's not great.
01:13It's pretty bland.
01:14Um but it at least it has some color some something.
01:18Um so now here is um the command make it bolder make the workflow section bolder with impeccable.
01:28Um so this is with impeccable installed.
01:31So now there are it's not perfect.
01:35There are some problems with this.
01:36for example, the um the section numbers that you have there, that's a very typical AI slop tail uh that uh that GPT loves to do and I mean Claude actually loves to do as well and
01:48it sometimes creeps in.
01:50So I wouldn't say this is perfect by any means but I think it's I would say bolder than before.
01:55Um now a lot of people install impeccable try it out uh and then they ask me well I don't know like maybe it could be placebo maybe the model is good enough in itself right uh not sure if it actually works well let's compare it to
02:10this is exactly the same project GPD55 on extra high um same exact prompt without impeccable so there is a slight difference I would say but you be the judge of
02:25Um, so the before and after is pretty different and I'm going to talk about why that is and um and and what the approach is.
02:36So designing at the speed of adjectives and um to get the elephant out of the room, they are not just adjectives, they're also verbs.
02:45Uh but some of them are adjectives.
02:50First off, the role of the engineer and the design are blurring.
02:53Um, I've seen more people become design engineers than ever.
02:58Designers are moving into code, engineers are moving into design and vice versa.
03:02Some of the best comments I get from people who walk up to me and say like, well, impeccable gives me this shared language of design that everybody can communicate now in.
03:11But really, these worlds are all colliding in my opinion and the typical handoff is kind of broken.
03:18like the the waterfall process of I start with design, maybe I start with like the what on the PM side, then it goes into design and then there's like this handoff and this critique process
03:28and then ultimately the engineer builds it.
03:30That thing is just not real anymore.
03:32I don't know about you, but um I think that's starting to collapse very quickly in small and large companies.
03:41And when it comes to the actual work of design, I feel like there's right now kind of like two worlds that you can play in.
03:48Either it's direct manipulation sort of like in the pixel space, right?
03:53So you're in Figma and you're manipulating margins, paddings, whatever it is.
03:57Um or you're in web flow or you're in some other tool where you directly manipulating the final output uh or the design.
04:05Now that's fine, but then you feel like you're getting behind because everybody else is like agentic and going crazy with loops and loop maxing, right?
04:13And now you're going on the other extreme, which is simply telling your agent, please design this for me or please build this.
04:19But it feels like to me at least there's this there's this middle ground that we haven't explored enough like what is the exact level of control?
04:27How can we insert the human in the loop at the exact right time?
04:32Uh and so this this came to mind then it's pretty popular tweet a while ago.
04:37Um so centering a diff with opus.
04:41Yes.
04:42Uh not a great use of opus.
04:45Uh but you know it kind of speaks to that problem.
04:48It's like okay well when do we use which tool?
04:51When is which tool adequate to do what job?
04:56In my opinion right now for most work the direct manipulation of padding, margins, spacing and so on is actually at a elevation that's too low.
05:08And on the other hand um if you go fully agentic you get web pages like this now that you would you would get this in like 2022 I would say.
05:17So everybody here can point out the typical AI slot patterns.
05:21Um but the purple gradients were actually way beyond that.
05:24there are no purple gradients anymore uh in most frontier models.
05:29Um now we just get this and it's kind of wears a different suit as Claude would say.
05:33Um but uh but it really is slop as well.
05:37It's just a moving target.
05:39So now we have I call this claude beige.
05:41We have these instrument serif fonts.
05:43We have italics.
05:44And it's not necessarily a bad design.
05:46It's just everything that comes out of claw design looks that way.
05:50And when everything looks the same, you kind of get algorithmic unilo as I call it.
05:56Uh so also not great.
05:58Now here's my first hot take of today's session.
06:02You cannot oneshot design.
06:05Um now many people want to and maybe we'll get there eventually.
06:08I just don't think it's possible at the current moment.
06:12Uh maybe not ever.
06:14Um, I think in order to build something that really looks and feels great and is effective design, you need to have something that's context context rich which has been informed by what you're trying to do, what your audience is, what you're trying to build.
06:29And also it will have to be multi-shot.
06:32You will have to iterate on your design.
06:34Uh, and you I mean even if you're a soloreneur, but if you're not a soloreneur, you might have different people who have different opinions.
06:41Users have opinions.
06:42I mean design is messy.
06:43it's process and wishing it away and just saying like solve this problem for me agent will not unfortunately solve your problem.
06:52Um now the other problem is if you don't know the language of design or if your stakeholders don't know the language of design gets really frustrating really quickly too.
07:02So if you've ever designed something um you kind of know like this kind of experience um and then you know the inner feeling builds up of like and at some point you're like
07:15uh so really what you have to ask first is what's the emotional territory?
07:20What should this never feel like?
07:22What's what's the reference?
07:23What's the audience?
07:24These are all really important questions to figure out.
07:27Like you can't go to a human design studio even if it's the best design studio in the world.
07:33You go to design director and you say like you know what I want to design for my brand and a design dire not nods.
07:40It's like got it and then walks away.
07:42That doesn't make any sense.
07:44Like they obviously have to figure out what it is that you're trying to build and what you're trying to get out of it.
07:50Importantly on this example even sort of like the 2026 version of AI slop you know quickly vibe coded page nobody decided anything here like you just oneshotted this nobody decided
08:03anything on this page this was just I mean it's maybe competent but completely empty so my uh thesis that I make here and what I've been trying to build over the last couple months is a tool that gives you
08:20just the amount of control needed to steer your agent in the right direction with adjectives and verbs.
08:26And these are the types of words I'm talking about.
08:29Talking about words like make this bolder, make this quieter, uh distill this.
08:34So basically simplification, um polish this, um make it denser or harden this.
08:40Um harden for instance would mean uh make sure that this design works across the board.
08:44Maybe the performance is bad on certain devices.
08:47Maybe it's not responsive.
08:48Um, and so these are these are words that we use in the world of design.
08:54And I noticed when seeing two people attempt the exact same task and one is an engineer who's never really touched design at all and the other one is a designer
09:04um there's a stark difference even when they use the same model and same harness everything in the output that they're getting based on the language that they use.
09:12So, I've been trying to put that language basically compress it into a skill uh and into a system to be able to express yourselves better.
09:22And so, for example, you could have like a baseline um over here, but then you make it bolder and the agent actually knows what bolder in your context means.
09:32You make it quieter, it knows what it means.
09:34You distill and it knows what it means.
09:40Um, but then bolder how what does bolder mean in the context of your project?
09:45That's a really important question because as you could tell at the beginning of the demo uh in the cold open uh when you just ask GPT or claude whatever make this bolder it doesn't know anything about what you mean.
09:58Uh now it has its own sense of reference of like what boulder could mean but it will do whatever it wants right it will invent new colors it will invent new gradients.
10:07it will I mean it doesn't matter um what it actually means in impeccable not gradients not glass not neon but actually hierarchy scale decisive type so uh things that
10:22uh don't break your design system and adequately raise the attention that the user would put on it uh and this is an actual sentence from the the file that is loaded when you say bolder impeccable
10:38um show someone your work and say AI make this bolder made this bolder if they believe you you failed this is something that we actually instruct the agent to do for themselves and then the agent oftent times
10:51reflects and like I don't know think I did some bad work here an adjective is a light wart and a light wart such a German term and Matt Puk actually talked about this recently uh who also makes some really excellent skills.
11:09And so this is uh stolen by one of his tweets, but I really think uh um it makes a lot of sense.
11:15Um these are words that h that you basically imbue with meaning that you infuse with meaning and they mean something.
11:22They already mean something to the model, but then you translate this into the area that you're interested in and the right altitude really shifts.
11:34Um, now I don't think you can solve any problems at that altitude.
11:39That's super important too.
11:41Uh, there is still room for the very beginning.
11:44For instance, if you just want exploratory work and you just want to get something on the screen or you just want the last amount of polish.
11:50I don't think right now uh AI is good enough to replace humans for the last 5, 10, maybe even 20% of the work to get it from good to great.
11:59Uh but it does actually make it better.
12:04Now I've built tools for more than 20 years.
12:07I guess I'm dating myself here.
12:09Uh but whenever I build a tool, I actually map the workflow first.
12:13I think about what is the actual workflow of the target user that I'm trying to help.
12:17And the workflow of design is not linear.
12:20It's messy.
12:21Has many different stages.
12:23Uh there are different people involved.
12:25And so I kind of mapped every part of the process and thought about well what are the injection points along that route and how can we help along that route.
12:35And so you start with initialization with the shaping process of design uh you go over to uh crafting to iterating uh with all these verbs and adjectives and then to the actual harden and polish phase and finally you kind of bring it back to your design system.
12:49You do some tech debt cleanup design deck cleanup.
12:53Um, now here's one example of a command that I wasn't actually sure about shipping and it's called overdrive.
13:00Um, I basically built this uh built this command in Impeccable that uh tries to create something completely over the top and it was kind of like a a half of a joke maybe.
13:12Um, but people absolutely are rabbit about this about this thing.
13:15Um, and they love it.
13:17Um, and so this is just one example of I mean this is not oneshotted.
13:21Uh this is a um sort of realistic event horizon shader um that I've built for my shader library radiant shaders.
13:28But I did actually use the overdrive command for this to uh overdrive it even more uh and make it more ridiculous.
13:35So sometimes I come up with these uh commands I'm actually not sure about and I test them with the community and once it sticks uh I realize okay well there are more people who are getting joy out of this.
13:46Um oh here we go.
13:50Here we go.
13:50Okay.
13:51Um, an adjective with nothing behind is just a nicer prompt.
13:55So, you really have to tell the agent what you mean by the word that you're using.
14:00Uh, it it has so many different meanings uh within its training materials that you really have to tell it.
14:06Um, now here's another thing.
14:09I've gotten so many requests for an automatic way of using Impeccable.
14:15So many.
14:16It's so frustrating.
14:17Like so at least once a week somebody tweets at me say like you know what would be cool just let impeccable do all the work by itself.
14:24I don't have to decide on any command anymore.
14:26That's not the point.
14:27The point is to give you a way to steer what you want to end up with.
14:32It's never going to be a tool to oneshot design.
14:35That's not the intent.
14:36And I'll never I mean there's a pull request standing uh standing out right now that I'm going to close because of that.
14:43There is no auto and there will be no auto in my opinion and uh this is a bit awkward maybe for some of the next speakers but I think taste cannot be amplified
14:55uh sorry I think taste can be amplified I think I call this amplified craft uh and I think you can work with tools to sharpen your taste and bring out more of your taste I really do not think it can be lab ground lab grown I think
15:08it is uh taste by definition sort of is uh contextual It's cultural.
15:14It's scars.
15:16And once everybody replicates the same thing, it starts to become really muddy and we don't think of it as taste anymore.
15:23That's my opinion.
15:24And I know this is like a hotly contested topic.
15:26Uh, but I'm not trying to solve taste with my tools.
15:30Um, that's what I got.
15:33Uh, this was about finding the right level of control for design.
15:36Thank you very much.
15:37And, uh, I think I have time for a few questions if you have any.
15:40Thank you.
15:56[music]