Latest / Superlinear / Make Your Coding Agents Expert Designers

Transcript

Make Your Coding Agents Expert Designers · Superlinear

0:00
Brandon: It's
0:00
Christine: It's
0:00
Brandon: like we're
0:00
Christine: so
0:00
Brandon: we're
0:00
Christine: terrible.
0:01
Brandon: Oh my god.
0:02
Christine: it's
0:02
Brandon: [laughter]
0:02
Christine: so bad. [laughter]
0:03
Brandon: It's so
0:03
Christine: When
0:03
Brandon: bad.
0:03
Christine: I saw it Once you understand the actual production pipeline, you can replace individual stages, or accelerate them with AI.
0:10
Brandon: It's so
0:10
Christine: [laughter] Look
0:11
Brandon: good. It's
0:11
Christine: at
0:11
Brandon: so
0:11
Christine: the difference.
0:12
Brandon: it's so much different.
0:13
Christine: finally a front-end that doesn't look like those generic AI slop.
0:16
Brandon: anything that you're making that that can be designed if you figure out the workflow then you can make quality a- artifacts of any kind.
0:25
Christine: I gave myself multiple places along the way where I could now judge and steer it
0:30
Brandon: This is the secret.
0:30
Brandon: People are not using this enough.
0:33
Brandon: OK? What do I mean?
0:59
Christine: Hey everyone. This episode we're looking at how to build better design workflows with AI and how that can help you create beautiful, delightful and usable artifacts for your projects.
1:10
Christine: We'll show you through three real examples.
1:13
Christine: So, if you've tried building front-ends with AI, there's a good chance that you've run into this. Well, at least I've run into this really often.
1:22
Christine: You give a coding agent a prompt like, build me a website.
1:26
Christine: And technically it can.
1:29
Christine: But what often comes back feels super generic. Like you always see the same layouts, the same visual language, the same AI feel.
1:40
Christine: So the other day, Brendan and I came across this Hacker News post and it linked to this website and I thought it was really funny.
1:49
Brandon: I'll
1:49
Christine: Yeah,
1:49
Brandon: share
1:49
Christine: this one.
1:49
Brandon: it.
1:51
Brandon: Every
1:51
Christine: [laughter]
1:51
Brandon: f-ing website, slop edition.
1:54
Brandon: And it just it looks terrible, doesn't it?
1:59
Brandon: we're used to it now.
1:59
Brandon: It's there's the boxes, there's logos, there's the same kind of language, there's buttons that look the same, there's monospace fonts, which we also have on our website. [laughter] But
2:10
Christine: [laughter]
2:11
Brandon: [UM] but yeah, it it[UM] it's lazy[UH] and I think it makes it's something that a lot of people don't know how to fix. They don't know how to build websites that aren't shit[UM] they don't know
2:30
Christine: [sniff]
2:30
Brandon: how to design with the agents.
2:31
Christine: [breath]
2:31
Brandon: I mean, this is something.
2:33
Brandon: Let me share a few tweets[UM] this is just tweet- tweets from the last few days. So[UM] OK, look at this[UH] I hate building front-ends with AI.
2:44
Brandon: Cloud, Codex, and Kime can generate a dashboard in thirty seconds.
2:48
Brandon: Then I spend the next six hours explaining that the main button is invisible, the table breaks on mobile, every screen looks like the same pile of rounded cards, et cetera This is from this is from the boring marketer.
3:00
Brandon: As good as AI is at coding, damn, it still sucks at design.
3:05
Brandon: And then there's a nice response on that.
3:10
Brandon: I'm not a designer but I understand the struggle. The output is still pretty mediocre. It feels like something new needs to be built here.
3:17
Christine: I see it so often as well around me, like so many people are complaining about the design by AI.
3:25
Christine: does so much AI-generated design still look so AI-generated, I guess?
3:31
Brandon: Mm-hmm. Mm-hmm.
3:32
Christine: I I know you've run into this too, Brandon, since we talk a lot about it.
3:34
Christine: Do you think the models are actually bad at design?
3:39
Christine: Or are we just asking them to work in a wrong way?
3:43
Brandon: We're asking them to work in the wrong way.
3:44
Brandon: [laughter] So this
3:45
Christine: Mm-hmm.
3:45
Brandon: this this is something that, you know, like everyone I've faced[UH] a lot[UM] especially early on when I started using agents and it bothered me.
3:56
Brandon: And I I tried lots of different things. I banged my head on the wall for months trying different techniques. I think this was you know back in December December, January, like early winter times[UM] I had a a variety of different workflows over the over the the months[laughter][UM] but you know like everything you know you you can't expect to just one-shot stuff right? I mean this whole podcast exists because one-shotting is not enough right?
4:30
Brandon: This is the point
4:30
Christine: Mm-hmm.
4:31
Brandon: [UM] when we talk about harness engineering when we talk about all the different techniques and ideas and workflows and tools and steps that you do when you're writing software, like these things actually affect the quality of the output.
4:48
Brandon: Right? So.
4:48
Christine: One-shotting is great for prototyping though, right?
4:51
Christine: But once you want
4:52
Brandon: Mm-hmm.
4:52
Christine: to build something more serious, then it often falls short.
4:56
Brandon: Yeah, like sometimes, well, yes. [laughter] What, when, when you want to build something serious, it falls you can apply these ideas that probably you're familiar with in the context of software engineering to other domains[UM] so like design, right?
5:15
Brandon: So like if if if we think about it, OK, what's the difference between one-shotting some bad software and the workflows that all of us do to actually produce something that's of some higher quality?
5:31
Brandon: And I think it's it's just breaking stuff down, thinking about what are the ways that people solve this problem?
5:41
Brandon: What are the things that they do?
5:43
Brandon: What responsibilities do different people have when they're working together to write software?
5:49
Brandon: And that leads to some interesting harness engineering stuff.
5:53
Brandon: Not this episode.
5:55
Brandon: But the point is we can do the same thing for design.
6:01
Brandon: And.
6:02
Brandon: Well,
6:02
Christine: Mm, yeah.
6:02
Brandon: we can do the same thing
6:03
Christine: That makes
6:03
Brandon: for design.
6:03
Christine: sense.
6:05
Christine: I think that r- approach approach really makes sense and we a- actually also applied this to our workflow for designing the superlier- superlinear website
6:15
Brandon: it's real, you know, like our website is something that we're using for this podcast, we care about the podcast, we put effort into it.
6:24
Brandon: And [UH]
6:25
Christine: Yeah, we really wanted
6:26
Brandon: it's not a toy.
6:27
Christine: it to be good. Yeah, we really want it to be good and nice [laughter] And
6:31
Brandon: Yeah
6:31
Christine: if we
6:32
Brandon: [UH]
6:32
Christine: had simply told a coding agent, make superlier- superlinear a great website, w- it probably wouldn't have built a great website. At least, you know, we'd we'd both of us didn't believe that.
6:42
Christine: We'd end up with
6:43
Brandon: Yeah.
6:43
Christine: something really generic. But we wanted something that was like unique to us, unique to the show that conveys like our intents Yeah,
6:52
Brandon: So how do we do
6:52
Christine: we
6:52
Brandon: that
6:52
Christine: we were we tried to be really thoughtful, like how does a good process look like to create a new brand identity basically.
7:00
Christine: And it's really important to build a good foundation before you jump into
7:05
Brandon: [UH]
7:05
Christine: the design.
7:06
Christine: There are actually a lot of upstream decisions before the visual design.
7:11
Christine: And when you just one-shot it, you skip all of those.
7:14
Christine: And [UM] I've worked with various start-ups and brand agencies to build their brands before.
7:20
Christine: And typically before a brand agency starts designing things, there are usually a bunch of ups- upstream questions like [UM] what are we trying to achieve?
7:32
Christine: Who exactly are we trying to reach?
7:34
Christine: What do we want those people to feel or believe about us? And what do we stand for?
7:40
Christine: And
7:40
Brandon: I
7:41
Christine: only
7:41
Brandon: mean,
7:41
Christine: then[UM] comes the question what visual identity expresses all of that.
7:48
Christine: For example, a visual
7:49
Brandon: I
7:49
Christine: identity intended to create urgency
7:51
Brandon: think
7:52
Christine: or some
7:52
Brandon: it's
7:52
Christine: fear
7:53
Brandon: a
7:53
Christine: of missing out would look completely
7:55
Brandon: good
7:55
Christine: different from one intended to make something feel
7:58
Brandon: idea to
7:58
Christine: calm and
7:59
Brandon: do that. I
7:59
Christine: easy to
7:59
Brandon: mean,
7:59
Christine: use
8:00
Brandon: I think it's
8:00
Christine: and trustworthy.
8:01
Brandon: a good idea
8:02
Christine: So, yeah, the
8:03
Brandon: I
8:03
Christine: important thing is that the website isn't actually the beginning of the design process. It's actually downstream of all these decisions[UM] and yeah [UM] actually all these
8:15
Brandon: mean, I
8:15
Christine: decisions,
8:15
Brandon: think it's
8:16
Christine: all these steps that I just mentioned, they can be done with AI too.
8:19
Brandon: a
8:20
Christine: And let's let's show you through [UM] the superior
8:24
Brandon: good
8:24
Christine: how we did this for Superlinear's
8:26
Brandon: idea
8:26
Christine: brand
8:26
Brandon: to
8:26
Christine: and website
8:27
Brandon: do that. I
8:28
Christine: because we certainly didn't pay a brand agency to build our brand first, Brennan and I did the signal workshop where we asked ourselves and got [UM] got really clear for ourselves[UH] things like what are we trying to achieve and[UM] who are we trying to reach[UM] and during this process we did use AI to do research or we used AI for the thinking process and [UM] we also thought
8:56
Brandon: And we had a
8:56
Christine: about
8:56
Brandon: conversation,
8:57
Christine: ok-
8:58
Brandon: right?
8:58
Christine: Yeah. Yeah.
8:59
Brandon: We
8:59
Christine: Yeah.
8:59
Brandon: just we
8:59
Christine: It w-
8:59
Brandon: just
8:59
Christine: a lot of conversation.
9:01
Brandon: yeah, we we just talked to each other, we brainstormed together.
9:05
Christine: Yeah. It's just to get these [UM] just to align it amongst us and also define it because[UH] as we said earlier, this all
9:16
Brandon: Yeah,
9:16
Christine: defines
9:16
Brandon: I think that's a good point.
9:17
Christine: the downstream visual identity[UM] so yeah and we we talk through like OK how exactly do we want those people who are going to listen probably to feel or believe about us after listening to the podcast?
9:31
Christine: And what do we stand for you know what are [UM] our values and belief because that will decide a visual identity that's unique to you and not just a generic [UH] AI design
9:45
Brandon: And you know
9:45
Christine: [UM]
9:45
Brandon: for the for the for the listeners[UM]
9:49
Christine: Mm-hmm.
9:49
Brandon: who can't see[UM]
9:50
Christine: Oh, right.
9:51
Brandon: it's
9:51
Christine: [laughter]
9:51
Brandon: probably interesting just to just to say what we ended up on[UM] do you wanna do you wanna just read read out the the the last slide
9:59
Christine: Yeah. [UM]
10:00
Brandon: and this one the [UM] starting from maybe the v- the values.
10:06
Brandon: Or
10:06
Christine: yes.
10:06
Brandon: you can or
10:07
Christine: S-
10:07
Brandon: you could
10:08
Christine: [laughter]
10:08
Brandon: or anywhere. Go ahead
10:10
Christine: Yeah, so for the people who who were not seeing my screen, I was just scrolling through like some of the notes that we made during our workshop[UH] where we just talked to one another and just put down like the notes and things that we believe.
10:24
Christine: So [UM] the
10:26
Brandon: I'm
10:26
Christine: the s- for for example this podcast in- is intended for software engineers who are already
10:32
Brandon: sorry.
10:32
Christine: building with
10:32
Brandon: I'm
10:33
Christine: AI
10:33
Brandon: not
10:33
Christine: but
10:33
Brandon: sure what
10:33
Christine: want to stay
10:34
Brandon: you're
10:34
Christine: close
10:34
Brandon: talking
10:34
Christine: to the frontier.
10:36
Christine: And [UM] we were thinking that maybe people don't want to wade through all the endless noise and try a bunch of crap before finding the real ideas that actually matter.
10:46
Christine: And we wanted to help people to discover[UM] see new angles[UM] trying better approaches so they can, like, build more things than before.
10:59
Christine: OK, yeah. And [UM] and here we have our values and belief that defines our identity, like what is unique to us.
11:07
Christine: So we believe that while we really want our podcasts to be accessible and easy to understand for our audience[UM] we want we are we are and also want to convey our honesty. We don't have hidden agendas.
11:22
Christine: We want our podcasts to be grounded, like grounded in first principles, facts, logic, like not not hype[UM] we are also very optimistic.
11:31
Christine: We see possibilities and are excited about them.
11:34
Christine: And then personality-wise, we are curious, always looking for new approaches, always trying to understand things, possibility-seeking, practical. We always want to bring ideas back to usefulness and actually actual building and practices to improve the craft.
11:51
Christine: And [UH] we also want to be generous. We want to share our knowledge and make difficult ideas and concepts easier to understand[UM]
11:59
Brandon: And and like
12:01
Christine: mhm.
12:01
Brandon: if you if if you're thinking about this, like this stuff is really sort of abstract and far away from the actual thing that we're delivering which is a podcast. But[UM] I guess before AI I think this stuff was still helpful cuz it helped align people in an organization.
12:21
Brandon: But now maybe you can start to see like if we give these words to the LLM it will steer the agent in the right direction.
12:31
Brandon: Anyway,
12:31
Christine: Yes.
12:31
Brandon: we're we're we're about to see more of that but
12:34
Christine: Yeah, no no,
12:34
Brandon: go ahead
12:34
Christine: exactly. So we gave all this what I just walked [UM] you know, all this about our goals, our who it's intended for, the our our identity, we gave all this context to actually I gave it to just CBT[UM] and then we asked [UH] so it was like above I I built this context above and then the prompt that I gave JetTPT is OK now give me different suggestions for the visual brand[UM] and I asked for guidelines a lot of typos by the way but I asked [laughter] it for guidelines for the visual brand, the style, the feel, the vibe, the color palette[UM] guidelines for visual assets that we may create down down the line
13:18
Brandon: Oh.
13:18
Christine: [UM] I
13:19
Brandon: [breath]
13:19
Christine: also asked about metaphors, typography[UM] and all of that.
13:24
Christine: And then[UM] AI gave us different five different individual brand directions.
13:30
Brandon: before we knew which one wanted[UM] we we we tried we tried a couple I think[UM] we've we we've kind of dug back through our history[UM] so I I I think I think at this point Christine[UM] I ended up with some copy of this result from
13:51
Christine: Yes,
13:52
Brandon: from your
13:52
Christine: exactly.
13:52
Brandon: chat GPT
13:53
Christine: This
13:54
Brandon: and
13:54
Christine: is where actually you you took [UM] this part[UH] where we were like,
13:58
Brandon: Mm-hmm.
13:58
Christine: OK, we like field notes from the frontier, we like this direction, and then basically you took you took it from here.
14:04
Christine: I think you fed it to Claude?
14:06
Brandon: OK, so at this point I like to loop in Claude.
14:11
Brandon: So so here I've taken the output from Christine's chat GPT and I said, can you make the design doc again but with these two instead?
14:21
Brandon: Be very detailed[UH] and then I I pasted the Signal Workshop vibe and Field Notes from the Frontier. What what Christine said.
14:32
Brandon: Why is that? I think Claude adds more human language
14:36
Christine: Yeah.
14:36
Brandon: that I think is more descriptive for for visual things[UM] so so Claude then produces a document with more detailed basically a more detailed prompt.
14:46
Brandon: But the real interesting thing the real interesting part of this workflow the key to designing good front-end applications using AI tools is using Chats GPT image.
15:04
Christine: Yeah.
15:04
Brandon: I pasted the signal workshop direction from that doc[UM] it turns out we didn't like this one, so we tried another one.
15:13
Brandon: But bear with me.
15:14
Brandon: So all this long thing was generated from Cloud.
15:18
Brandon: But at the very bottom I said, draw this website homepage.
15:21
Brandon: You can also say draw this with the Create Image tool.
15:23
Brandon: And what you get is you get a website that actually looks like a website. It doesn't look like garbage.
15:30
Brandon: You know
15:31
Christine: [laughter]
15:32
Brandon: [UM] you you get garbage if you just ask your your coding agent to build you a website.
15:39
Brandon: Even even using that nice prompt from Claude, you you get garbage.
15:42
Brandon: But you don't get garbage with the Create Image tool.
15:46
Brandon: Anyway, it turns out this particular mock-up is garbage-like.
15:50
Brandon: So.
15:50
Christine: [laughter]
15:50
Brandon: But it's decent, right?
15:50
Brandon: It's decent. And [UM][laughter] and at least, you know [UH] we have enough experience to know that if you keep trying this with more ideas, then sometimes you get something good.
16:02
Brandon: For example, here is the field notes from the frontier.
16:06
Brandon: And look, it's something kinda good.
16:09
Brandon: Christine and I thought it was kinda good.
16:11
Christine: I remember when I saw this and I thought, oh my gosh, really? You know, I I really really like this one.
16:22
Brandon: Yeah.
16:22
Christine: I think the important thing is that we could react to these design directions before the coding agent even wrote a line of front-end code.
16:33
Christine: Right? Like, we we saw the first one and w- and before we put the coding agent to work we were we were already like we don't we don't like this. This is this one
16:41
Brandon: And
16:41
Christine: is out.
16:42
Christine: And th- and then we saw this one and we were like this is it.
16:45
Brandon: I there there's something about like the the latest like image gen tool by ChachiBT where
16:50
Christine: [laughter]
16:50
Brandon: it's just really good at imagining the thing that you want.
16:56
Brandon: It doesn't have to doesn't have to understand HTML or figure out how to write the HTML and CSS to make it look like this. It's just kind of I don't know. It's it's magical. It's amazing[UM] so so we we we liked this direction but we didn't we didn't like it exactly
17:11
Christine: [laughter]
17:11
Brandon: as is.
17:12
Brandon: And so we said add
17:14
Christine: [laughter]
17:14
Brandon: more modern elements like a terminal. Make it more minimalist.
17:18
Brandon: And look, it's a little better.
17:20
Brandon: You know? It feels a little better[UH] and then we gave it more feedback.
17:26
Brandon: And if you're watching this[UM] you'll see something that kinda looks like our website
17:31
Christine: [laughter]
17:32
Brandon: [UH] and and then and then we just gave we just gave some direction to update the copy and you literally get like our exact website out[UM] we we we removed one of the components here but otherwise this is almost exactly our website.
17:47
Brandon: I mean, look at it.
17:49
Christine: It's so
17:49
Brandon: Here's.
17:49
Christine: cool. I really I really like it.
17:52
Brandon: Yeah,
17:52
Christine: It's
17:52
Brandon: and look
17:52
Christine: [UM]
17:52
Brandon: here's here's [UH]
17:54
Christine: Yeah.
17:54
Brandon: here's our website just for comparison.
17:56
Brandon: It looks the same, right[UM]
17:59
Christine: Yeah.
17:59
Brandon: but yeah, yeah I mean we're we're happy with this, right? Like I I I mean just to let's just brag about our website. I mean look you can hover over stuff and there's blue scribbles, there's like there's kind of this friendly blue scribble that reminds you of writing in a notebook in school, there's a highlighter effect[UM] the the fonts are kind of interesting. There's some of this monospace thing that I guess we should remove cuz it's kind of sloppy but you know it's just it feels polished but also approachable.
18:33
Brandon: Right
18:34
Christine: I agree.
18:35
Christine: I feel like because we separated like deciding what it should look like from implementing it in code, that gave us like a a much higher bandwidth[UM] or a much higher bandwidth way to steer the design.
18:52
Christine: And [UM] yeah, that way we could also steer [UH] the coding agent in a way where we we could steer it in a direction[UM] to a direction[UH] where we think the website should look like.
19:07
Christine: And [UH] in this case we used ChetTPT image generation for it[UM] I actually tried giving this prompt to other AI tools too but the results are not looking as nice[UM]
19:20
Brandon: [lipsmack]
19:21
Christine: Yeah and with yeah and with this direction like the ChetTPT image the the coding agent produced such a better design, a great a website that looks great and also works great.
19:35
Brandon: Yeah, I think I think it's really it's not only the fast feedback. I mean that's that's nice. That's like a nice bonus because it takes a little bit longer to build a web page but but even you know you can ask Fable like, oh give me a make you know prototype this for me and it'll it'll be almost the same time like in my take a minute and a half in the same way it takes a minute and a half to do a create image call from Chatsy-Petey sometimes.
19:59
Brandon: But there's something about the level of fidelity, the level of detail that you can get in one shot that it seems like unreachable with other design tools or with other tools at all with with coding agents directly with some of these other products.
20:14
Christine: Right.
20:15
Brandon: I mean we won't shame the other products. They're just
20:18
Christine: [laughter] So
20:18
Brandon: like nothing and trust me I mean we've tried everything.
20:22
Brandon: Every time there's a new tool we're trying it.
20:24
Brandon: The best the best thing you can do is asking ChachiBT to draw it for you
20:29
Christine: you really think it's because jetty-beaty's able to like express maybe like has a broader range to express things because it's not taking into a- account like how to code it, how to create it.
20:42
Brandon: Yeah, there's something about you can ex- ChachiBT can explore or the the models. The models can like do s- things that are more advanced in fewer tokens, I guess? Like the the reasoning that the model is doing in image space can get something that's way more detailed with I guess the same amount of of tokens[UH] compared to[UM] compared to other models trying to draw it[laughter] other image models or just[UM] prototyping it as a website.
21:18
Christine: Mm-hmm.
21:19
Christine: OK. So we basically were off-loaded, like, deciding what the design should be to a much better tool
21:26
Brandon: Mm-hmm.
21:27
Christine: [UM]
21:28
Brandon: Yeah.
21:28
Christine: and
21:28
Brandon: And and.
21:29
Christine: and after we have that we give it to the coding agent. Mm-hmm.
21:32
Brandon: Yeah, and I I I think it's important to note too, I guess it wasn't just to be really clear, I jumped from showing you the image to hey the website's done[UM] and obviously there's a step in between which is asking your coding agent to build it.
21:48
Brandon: In this case for this website[UM] we tried a few things because it was right when Fable came out is when we were building this website.
21:58
Brandon: And
21:58
Christine: Mm-hmm.
21:58
Brandon: before Fable I had other tools in my pipeline to take the image and turn it into something that [UM] well basically there there were other steps before it got to the coding agent to make something good but I've found now Fable is so good that you can give it give it an image and it'll give you the website and doing anything in between just slows it down.
22:20
Brandon: So so so maybe we should just like summarize this workflow really quickly.
22:25
Christine: What
22:26
Brandon: And and it's fractal too, which I think is cool, right? So[UH]
22:31
Christine: do
22:31
Brandon: so
22:31
Christine: you mean
22:31
Brandon: what do
22:31
Christine: with
22:31
Brandon: I [UM]
22:31
Christine: fractal?
22:33
Brandon: I mean there's like a workflow inside of a workflow.
22:36
Brandon: Because in the beginning we talked about a brand workflow.
22:39
Christine: Mm-hmm.
22:40
Brandon: So [UH] so Christine is very familiar with these these brand exercises and so she understood OK instead of just one-shotting like with with an LL give me my give me my values for example[UM] we broke that down into a bunch of steps and the human was in the loop, a few humans were in the loop, Christine and I worked together and
23:05
Christine: Mm-hmm.
23:05
Brandon: we got something
23:06
Christine: Mm.
23:07
Brandon: I think really strong out of that because we spent more time breaking
23:10
Christine: That's
23:10
Brandon: it down.
23:10
Christine: right.
23:11
Brandon: And that that whole process was just one step of this design workflow,
23:17
Christine: Yeah. That's
23:17
Brandon: which again,
23:18
Christine: right. That's right.
23:18
Brandon: we didn't just try and one-shot
23:20
Christine: Uh-huh. Mm-hmm.
23:20
Christine: Mm-hmm.
23:20
Brandon: with an
23:21
Christine: That's
23:21
Brandon: LM.
23:21
Christine: right.
23:22
Brandon: First
23:22
Christine: Mm-hmm.
23:22
Brandon: we did this brand exercise,
23:23
Christine: Mm-hmm.
23:24
Brandon: then we
23:25
Christine: That's right.
23:26
Brandon: turned
23:26
Christine: That's right.
23:26
Brandon: that
23:26
Christine: That's right.
23:26
Brandon: into
23:26
Christine: That's right. That's We're gonna get that sorted out
23:28
Brandon: [UM] we we we s- well in this case we fed that to Chachi BT, Christine talked to it a few times and got something out around some design directions, we took that and flushed it out and put and then we took those and drew them with Chatsy-BT image.
23:43
Brandon: And from that we can give that to a coding agent and get the website.
23:46
Christine: I really love this example, but there's also another example that I also really, really like our own custom podcast editor and it has this mini-map that lets you navigate through a
23:59
Brandon: [throatclearing]
23:59
Christine: long episode.
24:01
Brandon: In this case I had an idea for something that I wasn't sure could work but it might.
24:06
Brandon: So, OK.
24:08
Brandon: So yeah, so let me let me let me set the stage here
24:10
Christine: Mm-hmm.
24:10
Brandon: [UM] so like like Christine said[UH] I've been working on a podcast editor to edit our podcast because editing sucks.
24:22
Brandon: [laughter]
24:22
Christine: [laughter]
24:22
Brandon: It's very frustrating.
24:24
Brandon: So[UM][UH]
24:26
Christine: And
24:26
Brandon: and
24:26
Christine: it takes a lot of time. [laughter]
24:27
Brandon: it takes so much time.
24:27
Brandon: It's so much time. That is worth building software to help you do it faster.
24:32
Brandon: guess like the way that we are editing the podcast is by looking at the looking at the transcripts. This is like a modern way that people are editing these days.
24:44
Brandon: But it's very easy to get lost
24:46
Christine: Mm-hmm.
24:47
Brandon: where you know like our our raw footage is over an hour usually sometimes much longer than that and and I thought, OK, I'm constantly lost.
25:01
Brandon: How can I understand where I am in the context of the episode, number one, and number two, easily jump to some other part of where I want to go?
25:13
Brandon: OK?
25:14
Brandon: And so that th- this is the problem.
25:17
Brandon: And
25:18
Christine: Mm.
25:19
Brandon: An analogist problem came to my head[UH] that has been solved by text editors.
25:25
Brandon: OK? So[UM] I'm an engineer.
25:28
Brandon: Sometimes you open up a source code file that's like ten thousand lines long and it's hard to know where you are in it.
25:35
Christine: Mm-hmm. Mm. Mm-hmm
25:36
Brandon: And the[UH] something that originally was popularized by the Sublime text editor a long
25:42
Christine: [UM]
25:42
Brandon: time ago is showing a mini-map.
25:43
Christine: [breath]
25:44
Brandon: So showing[UM] on the side a silhouette, a shape of the code[UH] where you it's it's too zoomed out to actually see what the text says, but you can see the you know the shape of it, like the tab, if there's a function[UM] you know how how indented it is. And you can learn the shape of the file if you're in it enough.
26:05
Brandon: And that can give you a sense, well one you can see where you are and then you can see where you wanna jump to easily.
26:10
Christine: Mm-hmm.
26:10
Brandon: And so
26:10
Christine: [breath]
26:10
Brandon: so that this this was the this was the idea and and and this is where[UM] I started another design workflow that that you know Christine and I think is interesting.
26:25
Brandon: So actually I'm gonna share I had one of my agents generate
26:31
Christine: [breath]
26:32
Brandon: a[UH] recreation of the conversation I had with the agents to solve this or or to to start off this kind of design pass so I can I can kind of talk over it. So I've I've I've shared my screen[UM] and I'm just gonna I'm just gonna like skim and and talk around it. So so it starts with[UM] you know what I was doing at the time which was prototyping the the new version of this editor.
26:58
Brandon: And then I said in a in a side-chat[UM] can you give me a
27:03
Christine: Mm-hmm.
27:03
Brandon: prompt for my
27:04
Christine: Mm.
27:04
Brandon: design agent to design a beautiful mini-map that we can put on the right? So I I wanted a mini-map on the right.
27:10
Brandon: And I gave it some more context.
27:11
Christine: Mm-hmm [breath]
27:12
Brandon: I said ultimately we want as much info in there that we can as long as we can show it in a beautiful way.
27:20
Brandon: Let's tell the designer everything I started with this and I then used ChachiPT image because that's what you always need to do when you're designing.
27:30
Brandon: And this
27:30
Christine: Cool.
27:30
Brandon: is what
27:30
Christine: So so AI was
27:31
Brandon: [UM]
27:31
Christine: not
27:31
Brandon: [UM]
27:32
Christine: just rendering an idea that you already had.
27:35
Christine: It was actually participating in a design process with you. So it was AI was a design partner.
27:42
Christine: Is that right?
27:43
Brandon: Yes. AI was a design partner in designing this one particular component
27:48
Christine: Mm-hmm.
27:48
Brandon: [UM] of of
27:50
Christine: It's almost like what would
27:51
Brandon: of
27:51
Christine: happen
27:51
Brandon: this website.
27:51
Christine: in a in
27:51
Brandon: Mm-hmm
27:52
Christine: a product team, right? Like someone identifies some user problem and then the team explores some different approaches and then a designer brings something back and everyone reacts and then it gets refined.
28:05
Brandon: Exactly.
28:06
Brandon: Exactly. This is the.
28:08
Brandon: This empowers one person. It empowers the the builder to work with I guess to to be to start a product conversation.
28:20
Brandon: To start a product conversation with another product person, with a designer and with an engineer, essentially.
28:27
Christine: Mm-hmm.
28:28
Brandon: And so that this first conversation is sort of I guess you could say with a with another product person, cuz we're riffing and we're coming up with a brief, a design brief
28:37
Christine: Yeah.
28:38
Brandon: that we would give a designer.
28:39
Brandon: And who's the designer?
28:41
Brandon: Chat GPT. [laughter] Draw image.
28:43
Christine: [laughter]
28:43
Brandon: Draw image is our designer[UM] and then and then eventually you give it to an engineer to build it.
28:47
Brandon: Right?
28:49
Brandon: So[UM] Yeah.
28:52
Christine: Yeah, this is cool.
28:52
Christine: I've not I've not used I've not done this before.
28:57
Brandon: And this is this is different, right? This isn't saying[breath] in our last example we had a particular[UM] we had a particular design in mind from Claude. You know, we had a it's like, hey, draw this particular thing for me. This this time we are giving a design brief.
29:16
Brandon: OK?
29:16
Brandon: We're designing
29:17
Christine: Mm-hmm.
29:17
Brandon: one component[UM] we want[UH] let me scroll in here.
29:24
Brandon: Well anyway this is so long.
29:26
Brandon: Well anyway [UH] I'm not gonna I'm not gonna dig through the prompt. But the point is a a design brief can give
29:32
Christine: Wow.
29:32
Brandon: you.
29:34
Brandon: Yeah.
29:35
Brandon: How cool is this? OK, let me let me zoom in.
29:37
Christine: Wow. It is this looks so cool. I've not seen it in our video editor yet.
29:40
Christine: [laughter] I think you've you've s- you've seen it.
29:43
Christine: I've not seen it yet.
29:45
Christine: But this is this looks so cool.
29:48
Christine: I would.
29:49
Christine: Yeah.
29:50
Brandon: Well, this is the bad version, so it's not that cool.
29:53
Christine: Is it?
29:53
Brandon: But it's good.
29:53
Christine: It looks
29:54
Brandon: I mean it's so
29:54
Christine: it does look cool.
29:54
Christine: [laughter] It
29:56
Brandon: so
29:56
Christine: does look
29:56
Brandon: I
29:57
Christine: cool to me.
29:58
Brandon: mean look look so [UH] the designer iterated on a few different ideas, right? It said, OK, what if we had two different spines of conversation[UM]
30:10
Christine: Mm-hmm.
30:11
Brandon: what if we were using edges[UH] what if we just saw the edits and then and then it chose a particular direction by combining different ideas that it got in the exploration.
30:24
Brandon: So the reasoning what we're what we're seeing here is a visualization of the reasoning trace of the agent reflected in the drawing that we got back, which I think is like crazy[UM] but and and then as a human as the as acting as the product person I guess you could say I asked for something else.
30:50
Brandon: Right[UM] I guess this is where I said hey the waveform is not useful because the waveform shape when you zoom out just looks like noise.
31:00
Brandon: So this was like some direction I gave to the the designer[UM] and and I said you know there are other things that can that can help with the visual shape maybe like the scene assignments chapters other intents that's what we're calling like cuts or mutes or[UM] different kinds of[UH] modifications to the to the the the feed.
31:22
Christine: Oh
31:23
Brandon: And and then I asked for another design brief.
31:26
Brandon: And
31:28
Christine: wait, it didn't show that? I thought when I looked at it I thought I saw those [UM] symbols and I thought they represented those different
31:35
Brandon: the
31:35
Christine: moments.
31:35
Brandon: symbols were in there[UM] but but now it's way better.
31:41
Brandon: So.
31:43
Christine: Mm.
31:44
Brandon: So now.
31:45
Christine: Oh yeah, this is even better.
31:47
Brandon: Yeah.
31:48
Brandon: So now there's again there's these different concepts. So the shrunk manuscript, that's interesting.
31:54
Brandon: Cuz that that has more of a shape. There's like the turn rhythm, so seeing who's talking left Brandon, right Christine.
32:02
Brandon: Or if we're talking over each other there's it's on both[UM] [laughter] then there's like maybe [UH] the different scenes or the chapters[UM] and this kind of final refined direction combines these things in a nice way, I thought. So[UM]
32:20
Christine: I would
32:20
Brandon: you
32:20
Christine: love
32:20
Brandon: can see the
32:20
Christine: to
32:20
Brandon: scenes,
32:20
Christine: see the actual graphs for our
32:23
Brandon: you
32:23
Christine: episodes.
32:23
Brandon: can see the turns, yeah[UH] well, you can't see it yet because I'm not done building
32:28
Christine: [laughter]
32:28
Brandon: it, but [laughter]
32:29
Christine: But
32:30
Brandon: [UM]
32:31
Christine: yeah,
32:31
Brandon: [UH]
32:32
Christine: I I feel like I'm a very [UH] visual learner and also like when I see something f- when I try to understand something as soon as I see something visually it just helps a lot.
32:41
Christine: And this would I think this this helps a lot with[UM] just seeing at a glance different things about how we did the podcast.
32:49
Brandon: Yeah, I I think I mean I think this solves the problem because just like source code, seeing a reflection of the transcript of who's saying what, well not seeing exactly what we're saying but seeing like, oh this person talked for a long time in a row and you know Christine interrupted right here when Brandon was monologuing. That is reflected in the silhouette of the episode, which is exactly what I want. And so I
33:13
Christine: Yeah.
33:15
Brandon: [UM] I'm pretty sure this is gonna be very helpful once it's once it's done being built. It's you know it's in it's it's being built in the background. It needs a maybe another day.
33:26
Brandon: But [UH]
33:27
Christine: It's
33:27
Brandon: yeah.
33:27
Christine: it's it's so cool that the design brief turned that like vaguish idea into something concrete, like and also con- concrete enough to explore it visually.
33:39
Christine: And once you had a design that you liked then then it it just became an implementation problem for the coding agent
33:46
Brandon: Exactly.
33:46
Christine: [UM]
33:46
Brandon: And and and like we said, you can give you can give images to Fable and[UM] you know, you need to set up your feedback loops, you need to do proper harness engineering, we've talked about that a a million times[UM] and if you do that, you'll eventually get something that looks and feels exactly like the you know exactly like the screenshot wants
34:09
Christine: Yeah. I I had the[UM] I had the same experience building a a custom three-D model for a game.
34:16
Christine: Maybe maybe I can[UH] yeah maybe I can show that too[UM] as a real example.
34:21
Brandon: Yeah
34:21
Christine: So, yeah, I'm building a game and I ran into basically the same problem as you.
34:27
Christine: So the main character of my game is a chicken[laughter] and because you're staring at this character the entire time when you play [UM] I really wanted to get that right.
34:36
Christine: So, my first attempt was basically, hey coding agent, make me this chicken.
34:40
Christine: [laughter] And it did, but it was just not the chicken that I wanted. It was, yeah, it
34:49
Brandon: m-
34:49
Christine: was, OK, let me just show you.
34:50
Brandon: show
34:50
Christine: [laughter]
34:50
Brandon: everyone.
34:50
Christine: My
34:52
Brandon: [laughter]
34:52
Christine: ugly chicken.
34:54
Christine: I actually did show it to you, Brendan[UM]
34:56
Brandon: Oh yeah.
34:58
Brandon: It's really ugly.
34:58
Christine: Yeah.
34:59
Brandon: It's
34:59
Christine: [laughter]
34:59
Brandon: so ugly. Let me
35:00
Christine: [UH]
35:00
Brandon: [laughter] I'm excited to see it again.
35:03
Christine: let's see.
35:04
Christine: Oh, here it is.
35:06
Christine: Sure.
35:07
Christine: Yeah, it's,
35:10
Brandon: So
35:11
Christine: I was
35:11
Brandon: bad.
35:11
Christine: like, oh
35:11
Brandon: It's
35:11
Christine: my
35:11
Brandon: so
35:11
Christine: god.
35:11
Brandon: bad.
35:12
Christine: Yeah, this
35:13
Brandon: It
35:13
Christine: is
35:13
Brandon: I
35:13
Christine: like not
35:13
Brandon: I mean,
35:14
Christine: good.
35:14
Brandon: look at it.
35:15
Christine: Mm-hmm.
35:15
Brandon: It's it's it's like the equivalent of that that website we showed earlier. It's like it's like the clearly AI slop feel but but in the three-D model.
35:25
Christine: Yeah.
35:26
Christine: Yeah, so so[UM] Yeah, I think the reason why this w- this turned out so bad is[UM] this game, I was building this game for Roblox,
35:34
Brandon: [laughter]
35:35
Christine: so the coding agent probably tried to use the building blocks available in Roblox, which are very limited[UM] to construct that three-D model of the chicken character and it just didn't work[UM] yeah.
35:47
Christine: So so I tried m- to prompt my way out of it and that also did not work.
35:52
Christine: And then I took a different approach.
35:55
Christine: I I looked at how[UM] a good three-D model[UH] or a good three-D three-D model [UH] or a good three-D character would actually get made.
36:05
Christine: And then I reconstructed the production workflow that you'd normally use to create a game character properly.
36:12
Christine: So basically [UM] you start with a goal and audience, you know, just just like our whole [laughter] our whole [UM] workflow when we decided on a brand[UH] strategy or brand identity for[UM] Superlinear's podcast. For basically when you're building a game it's it's similar. You have a goal, you have to think about your audience. So for me it was teenagers.
36:35
Christine: And that determines the style. Like if it's for kids you might want it to be more cartoonish. If it's for adults you might want it to be[UH] have a more realistic style.
36:45
Christine: And then [UM] I actually did use ChattyPT as well to create the character direction[UM] and then
36:54
Brandon: It's
36:54
Christine: I
36:55
Brandon: always
36:55
Christine: asked
36:55
Brandon: Chachi
36:55
Christine: ChattyP-
36:55
Brandon: PT image. That's the secret.
36:57
Christine: [lipsmack]
36:58
Brandon: That's the
36:58
Christine: Yeah!
36:58
Brandon: secret design tool.
37:00
Christine: So I I actually used ChattyPT to create like this[UH] character direction and [UM] and that now I have the proper reference material. So this is a turn-around sheet[UM] and then
37:13
Brandon: Now it looks good.
37:14
Christine: you c- Yeah, well [laughter] the one that Chatty-BT creates is good. And now I need to turn it into an actual three-D model. So instead of asking[UH] the coding agent to build it, I used[UM] another AI tool called Meshi.
37:32
Christine: So here it is.
37:33
Christine: And in Meshi basically you can like [UM] paste or drag and drop the image that you created using Chatty-BT, like the turn-around sheet with the different like front view, side view, back view.
37:45
Christine: And then you can just generate the three-D model[UM] And that's what I tried and I think let me show you the results[UM] yeah.
38:00
Christine: So this, look at this.
38:02
Brandon: This
38:03
Christine: Isn't
38:03
Brandon: is amazing.
38:03
Christine: this?
38:04
Brandon: This
38:04
Christine: Well,
38:04
Brandon: is
38:04
Christine: yeah.
38:04
Brandon: quality.
38:06
Brandon: Yeah.
38:06
Christine: Right[UM] Yeah, I really I really like this. I when I saw this I was like, yes![laughter] Finally[UM] a a design that looks great [UM] But [UM] there are technical constraints, like for example [UM] Roblox puts limits on how complex an individual mesh can be[UM] so your tool h- the the model has to be created for the environments it's eventually going to.
38:36
Christine: And [UH] a single mesh in Roblox case can have up to twenty thousand triangles
38:41
Brandon: [laughter]
38:42
Christine: [UM] or or twenty thousand faces and if you look at this it's seven hundred thousand.
38:48
Christine: So then you can [UM] change the settings in Meshi and then I regenerated another one and you can see like this one has [UM] twenty twenty thousand faces. So this would fit for my for my for the game engine that I'm going to use.
39:04
Christine: and once you've done that [UM] you can also like also you already see it here you can rig the character and then you can also like [UM]
39:13
Brandon: And rigging
39:14
Christine: [UH] af-
39:14
Brandon: w- w- rigging is [UM] explain that to us?
39:19
Christine: Yes [UH] so when when you rig the character you can like[UM] you can decide like where the joints are in that three-D model so then when you[UH] and when you know where the joints are you can like make like animations like this [laughter] like a dancing
39:34
Brandon: Yeah.
39:35
Christine: chicken and it and it looks and it looks nice and fun[UM] and then basically after that you just export it[UM] and then import into your game.
39:45
Christine: And you know look at this. The quality is so much better than this one.
39:53
Brandon: I yeah and I mean like this is so cool right? Cuz I I think this example shows that it's really anything that you need to design.
40:04
Brandon: Like it could be it could be a website, it could be a part of a website or a part of an app, but it can also be something different like a like a three-D model[UM] and you know maybe you're not using
40:14
Christine: [laughter]
40:14
Brandon: three-D models in your projects but but the idea is anything if you if you figure out, OK, what is it that people usually do to make this thing properly and then try and map that workflow to different AI tools and pipe them together and actually put effort into it, right? It's not free, you know, you have to spend some time[UM] then I I think that's
40:48
Christine: Yes.
40:48
Brandon: like that's the key thing here
40:51
Christine: Yes.
40:56
Christine: all those steps, all those indivi- or And [UM] yeah, I guess instead of asking one model to somehow jump from just the PROMs, like, hey, in my case I need a design for my character to and then and then instead of just expecting the model to just jump from that to the finished asset[UM][UM] to get that final result that I would be happy with.
41:29
Brandon: Every step is a steering point and also every step is an opportunity to use a different tool, the right tool, for that point in time
41:37
Christine: Yes.
41:38
Christine: Yes[UM] Yeah.
41:42
Christine: And I guess if we[UM] zoom back out and look at all these you know the three examples that we mentioned they they look like completely different things.
41:50
Christine: Like
41:52
Brandon: [throatclearing]
41:52
Christine: it's a website, it's a podcast editing interface and there's a three-D game character.
41:56
Brandon: [throatclearing]
41:57
Christine: But like Brendan mentioned the structure's basically the same.
42:00
Christine: So quick comparison
42:02
Brandon: [sniff]
42:03
Christine: [UM] website was brand and then the concepts and then implementation.
42:07
Brandon: [throatclearing]
42:08
Christine: With the minimap we had problem, brief, visual exploration, and then implementation.
42:14
Brandon: [sniff]
42:15
Christine: And for and then for the character we have art
42:16
Brandon: [throatclearing]
42:17
Christine: direction, reference, model, and then implementing it into the game. So in every case we created this intermediate artifacts that made the next decision
42:28
Brandon: [sniff]
42:28
Christine: easier and gave us somewhere to steer or to choose a different tool to use that's better at
42:33
Brandon: [throatclearing][throatclearing]
42:33
Christine: that step[UM] Yeah.
42:36
Brandon: Yeah. And and I guess another maybe another point here is like coding agents by themselves are not good designers.
42:43
Brandon: But coding agents paired with other tools like ChatGPT Image[laughter][UM] or or if you're doing something more in more exciting like a three-D model then tools like Meshi you can combine those with coding agents and you can get quality out of it.
43:00
Christine: Yes.
43:01
Christine: Yes. And[UM] if we go down this line of thinking, something that comes up in my mind is [UM] I feel my instincts are almost the opposite of one-shotting.
43:15
Christine: Whenever I'm building something important with agents, I want to first understand, like, how would really competent humans do this? Like, what is the actual workflow?
43:25
Christine: What are the important decisions and deliverables along the way?
43:30
Christine: And once I understand that, I use AI to accelerate or re- replace parts of that process.
43:38
Christine: And I I really like working this way because I know where the important decisions happen, I understand what I'm building, and I know where to intervene if something goes wrong.
43:47
Christine: Brandon, I also know you do something so different sometimes, like when we talk I get the impression that you you give it often give an agent a goal, you let it run overnight and then you wake up to something that works?
44:01
Christine: And then it makes me wonder, am I am I overengineering this?
44:16
Brandon: I struggle with sometimes because I'm too lazy[UH] [laughter] but but one way to
44:21
Christine: Or
44:22
Brandon: think
44:22
Christine: just
44:22
Brandon: about
44:22
Christine: too
44:22
Brandon: it
44:22
Christine: quick,
44:22
Brandon: is
44:22
Christine: I guess.
44:23
Brandon: yeah.
44:24
Brandon: The the a- the approach you're describing I think of as maybe going bottom-up.
44:27
Brandon: Like you you wanna deeply understand how something works and then once you have that you can say OK it's these five steps or these ten steps and then you can say OK what should I do in these different steps. And if you do that and you learn that and you do it well you're gonna get something good at the end of it.
44:43
Brandon: What I what I like to do is I go top-down[UM] so what do I mean by that? I start by just one-shotting and then and then[UM] sometimes that's fine.
44:54
Brandon: Like it it it depends what you're doing. If you're building an internal tool, yeah it can be vibe-coded crap, it doesn't matter[UM] but [UH] but then you know for whatever I'm trying to do I judge the output, I judge the artifact that comes out and is it is it good or is it bad? [laughter] And if it's bad then then [UM] I decompose it.
45:15
Brandon: OK? And I I think design is a really good example of this because no matter h- every single time I tried to to one-shot something I had to decompose it into into different steps.
45:27
Brandon: And and you know you start with two steps and then you say OK the first step is bad so I'm gonna break that into two different steps or five different steps. And I just keep decomposing and breaking down things into more and more steps and then try different tools until I get the thing that I want out of it [UM] so so I don't think you're overdoing it.
45:50
Brandon: I think I think spending that time to make the process better where it matters is really valuable[UH] and and it sounds like you're doing that. And look, you you you started with that ugly chicken and you ended up with a beautiful chicken. So [UH] so so that's good. I think where it where it could go wrong is if you if you take this to the extreme and you spend all this time breaking down work that could be done in one shot[UM] and and you spend a lot of time on it when it's unnecessary.
46:20
Christine: Yeah,
46:21
Brandon: [laughter]
46:21
Christine: I do I do think that's true. I think, yeah, I think I am I think I do agree that[UM] we do not need to reconstruct some giant professional workflow every time we ask AI to do something.
46:36
Christine: And
46:36
Brandon: [laughter]
46:36
Christine: I I guess if if if the model, you know, would have created that AI character correctly right away, then I wouldn't I wouldn't have dived into like that workflow how how people properly create three-D characters
46:49
Brandon: [UM]
46:49
Christine: [UM] So yeah, I think I think I agree, actually agree with that approach.
46:52
Christine: Start simple, but when the quality isn't there, don't just keep, you know, rewriting the PROMs. Maybe expose more of the hidden process, like [UM] ask what process would produce this if it were really done if it were done really well, and what intermediate artifacts am I skipping right now?
47:15
Christine: Because like we said, every useful intermediate artifact gives you another place to apply your own judgment and steer the result and maybe find a better tool to use that's better at
47:24
Brandon: I'm
47:24
Christine: that task.
47:25
Brandon: sorry. I'm not sure what you're
47:27
Christine: I [UH] while
47:27
Brandon: talking
47:27
Christine: you
47:28
Brandon: about.
47:28
Christine: were talking I I also got reminded I think it I think it's also like really true what you're saying like your observation. I'm really trying to learn because[UM] basically what we're doing here is building software and I don't have like that rich software engineering experience that you have, so I also intentionally want to slow down for my own understanding, for my learning, so I know what I'm doing[UM] that that kind of rem- reminds me of a of a blog post that I've seen from Mario Zechner, the creator of Pi. I don't know if you remember, you probably have seen it
47:59
Brandon: Mm-hmm.
47:59
Christine: too, like, slow the F down. [laughter]
48:02
Brandon: Mm-hmm.
48:02
Christine: You
48:02
Brandon: Mm-hmm.
48:03
Christine: remember that one?
48:04
Christine: Yeah
48:04
Brandon: I do.
48:05
Christine: [UM] I think I yeah, sometimes I'm lazy too, or I'm i- impatient and I want to one-shot it, but often I try to be really intentional about understanding what I'm doing or what's happening.
48:16
Brandon: Yeah.
48:17
Brandon: I mean, doing this podcast helps us slow down because we in order to explain something we really have to understand it[laughter] maybe something for everyone to think about.
48:28
Brandon: OK, on the surface what we talked about was design and how to design properly.
48:34
Brandon: And hopefully you can actually take this away and and solve design problems that you run into now that you know use Chatshubuti image basically [UH] and then as we were saying decompose things properly et cetera.
48:46
Brandon: But but just remember this is not just about design.
48:51
Brandon: It's about anything really. So
48:53
Christine: [laughter]
48:54
Brandon: the point is in the same way that you can decompose[UH] you know you can turn a one-shot prompt to vibe code something into harness engineering and build good software.
49:04
Brandon: You can turn a one-shot design task that's that gives garbage results into a proper workflow that produces a quality asset or a quality artifact by putting effort into it.
49:17
Brandon: And you can do the same thing for any any kind of problem that you run into if you if you kind of take this approach.
49:25
Christine: Agree.
49:26
Christine: Yeah.
49:27
Christine: Well, that's it for this episode of Superlinear[UM] a few of you told us you wanted more real examples of how we're actually using the ideas that we're sharing during the episodes. So in this one we tried showing you how we applied the practices and things that we've been building ourselves[UM] let us know if you want us to do more episodes like this.
49:49
Christine: And I'm also especially curious[UM] if anyone of our listeners have found a workflow where breaking down the task into stages also improves what your agent could produce.
50:02
Christine: Please tell us in the comments and subscribe if you want to catch the next episode.
50:07
Christine: See you next time.
50:08
Brandon: Bye everyone.