The Aboard Podcast

Paul Ford: Hi, I’m Paul Ford.

Rich Ziade: And I’m Rich Ziade.

Paul: And this is The Aboard Podcast, the podcast about how AI is changing the world of software, and software is everywhere, and you can’t stop it, and it’s a lot, and we’re all dealing with it together.

Rich: Blah, blah, blah.

Paul: No, this is a good one. [laughter] I want to show you something. I want to show you something I built with AI.

Rich: Oh, I’d love to see it.

Paul: It’s time to stop talking and start doing. You ready?

Rich: Walk the walk.

Paul: Let’s play the theme.

[intro music]

Paul: All right, Rich, what’s Aboard?

Rich: Aboard is an AI transformation company. We use great people, great tools, a great process to get you production-grade software faster than anyone. We’re really, really good at it, whether it’s an agent you’re spinning up, or software you’re standing up for your company. We’ve got a lot of years behind us and we know how to do it well.

Paul: We have great clients. And look, we’re your partner. That’s what’s emerging is we partner with you and we work with you kind of every day.

Rich: Plot twist. People matter.

Paul: Yeah. If you’ve ever read Rich writing in the newsletter—we should just give you your own blog called “People Matter.”

Rich: Oh, yeah, because you don’t write enough times on the newsletter, Paul Ford?

Paul: That wasn’t really where I was going with that.

Rich: Oh, you want to put me on my own newsletter?

Paul: I just think “People Matter” would probably—

Rich: I’m tired of being John Oates in this relationship. [laughter]

Paul: I think you’d be more of the Garfunkel.

Rich: Oooh!

Paul: Yeah, I know. Okay, look, I made something, and I want to use it as an opportunity to talk about the nature of product in the age of AI and all that stuff. But I also want to sort of talk, I want to show you what I built.

Rich: How’d you make it? Let’s talk about that for a minute.

Paul: Okay, so I gotta explain what it is. Every day, a series of bots comes together, reads a lot of news, and sends me one or more newsletters about my interests.

Rich: Every day?

Paul: Every day. Late at night, about 3 A.M.

Rich: Okay.

Paul: Okay?

Rich: You told it what your interests are and you unleashed bots on the internet?

Paul: I did. But I gotta tell you, it wasn’t that easy.

Rich: Hmm. Okay.

Paul: It wasn’t. This is what they tell you. They tell you, hey, you want your own little personalized newsletter?

Rich: Yeah.

Paul: You say, “Claude, make me a little newsletter.” Or ChatGPT. And it’ll be like, [Claude voice] “Of course, master.” And then it’ll go do whatever you want.

Rich: Yeah.

Paul: But that’s not how you get to quality. And quality is different with this stuff. Now, I’m going to actually walk through what the newsletter does for me and why I created it. And if you’re the kind of person who’s like, oh, no, they’re trying to replace writers, relax. That’s not what this is. It’s very much a digital product. It’s very much an AI-generated product. And it doesn’t pretend to be otherwise.

Rich: It’s gathering stuff that writers put out in the world.

Paul: We’ll talk about how I made it in a minute, but let me tell you what’s in it. So I go, it’s called the Aboard AI Rundown. Right?

Rich: Okay.

Paul: Because what is my job? My job is to share news about AI on LinkedIn. I have other responsibilities like selling services and delivering them.

Rich: Yeah.

Paul: But one of the things I really need to do is be very informed. I get called on to write and talk, and you can’t get caught up in a weekend. You have to just let your brain bake.

Rich: Mmm hmm.

Paul: And so I created a system that would kind of know about all the things that we care about at work.

Rich: Mmm hmm. Which, for us, happens to be AI.

Paul: Happens to be AI in a specific—

Rich: The industry, the players, the news that’s happening.

Paul: And focused on the things we do, which is sort of transformation and delivery and—

Rich: Consulting.

Paul: Consulting and sort of, you know, it’s very interesting to me, and this will be, I don’t expect anyone else to be thrilled by this, but I like to know what Accenture is going to do about AI today.

Rich: Right.

Paul: I want to know that because it just helps me understand the world I’m in.

Rich: Sure.

Paul: I have another newsletter just like this. I won’t talk about it too much because it gets too confusing, but I also am trying to understand the world of one of our clients. It’s a big insurance company.

Rich: Okay.

Paul: And it sends me an insurance newsletter.

Rich: Cool.

Paul: I’m starting to share that with the client. Basically any subject at all, you can feed it to this thing.

Rich: All right, so this is worth saying: You didn’t one-off this.

Paul: I started that way, but now it’s generalized.

Rich: And so you fill out a form of some kind?

Paul: Yeah. Basically, it’s a setup—

Rich: Tell it what industries you’re interested in and what topics you care about, and it puts it together?

Paul: So that’s a good question.

Rich: Thanks.

Paul: Yes, it’s a system. It has subscribers and I go in and I have a set of prompts and it absorbs feeds of news.

Rich: Mmm hmm.

Paul: And then it synthesizes the feeds and then it uses actually a pretty—now see, I started with like, “Hey, AI, just write me one of these.”

Rich: Okay.

Paul: It broke all the time.

Rich: Mmm hmm.

Paul: Because AI isn’t necessarily good at knowing what news to get or how to organize it or what a subject would be or what a key—

Rich: Quality is not in the conversation a lot these days.

Paul: No, that’s right. So it’s just sort of like it did an okay—it was exciting at first, but it wasn’t really useful after a couple of days.

Rich: So you kept refining it.

Paul: I kept refining it. And I’ll tell you, I’ve been refining it since probably about October.

Rich: Wow! Okay, so this isn’t, I typed some stuff in a box.

Paul: Now look, I’m going to be a little arrogant for a minute, and just forgive me. I’m a very, very good and very senior editorial thinker. I used to be an editor in magazines.

Rich: Mmm hmm.

Paul: And I used to build content-management platforms. As someone who, and I’m known for that. People call me in New York City.

Rich: I don’t think you’re dropping a bombshell. [laughing]

Paul: I’m not, I’m not. But I’m just saying. And so what I have been doing over the last couple months is as a product person who focuses a lot on editorial.

Rich: Yeah, you’re an editorial product manager.

Paul: Shaping this—not trying to simulate humans, but trying to make it a useful tool that I can use every morning to, and I don’t just copy and paste into LinkedIn. I need it to guide me to articles that have interesting data in them that I can then go read.

Rich: Mmm hmm.

Paul: And share relevant quotations.

Rich: Mmm hmm.

Paul: And use that to drive our social and so on, but also to get me ready and get me prepped for kind of what’s out in the world.

Rich: Mmm hmm.

Paul: So look, let me just describe it to you for a minute and then I’ll tell you how—it’s actually easier to talk through the sections and how each one’s a little different.

Rich: Okay.

Paul: So the first thing, it has—

Rich: Let me recap before you dive in.

Paul: Okay.

Rich: Every morning…

Paul: I wake up and there’s a message there.

Rich: And it is a nicely formatted newsletter, essentially.

Paul: It’s pretty long. There’s a lot of detail. It starts with a picture.

Rich: Okay.

Paul: The picture is generated by Gemini, which is Google’s…

Rich: Okay. So you’re using different AI services.

Paul: I’m using different languages.

Rich: Okay.

Paul: I’m using databases the old way.

Rich: Okay.

Paul: I’m using a web platform that I built and vibe coded.

Rich: Okay. It’s worth saying out loud, you’re going to get into how you got here.

Paul: Absolutely.

Rich: But you did not spin up a few AI agents and they email you every morning.

Paul: I did that. It just wasn’t that good.

Rich: That’s important.

Paul: I couldn’t make it good.

Rich: Okay.

Paul: Okay? And then what happened is when I started to actually get enough data into it, it couldn’t handle all the data.

Rich: Mmm hmm.

Paul: So I needed to go in and program and product manage and actually build this as a product.

Rich: Yes.

Paul: Now the way you do that is sometimes you actually log into a system and say some words.

Rich: Yeah.

Paul: That’s different. I didn’t write a lot of lines of code, but absolutely, I have read through the code, I’ve looked at this system. I’ve thought about it as I walked around and rode my bike. All the things you do when you’re building a product in a platform, I’ve done on this in a slightly new way over many months. And I’m going to be frank. When I was talking about myself as an editorial advisor, there’s no way I would have done this for less than a couple of hundred thousand dollars with a team in the past. This is not light work.

Rich: Yeah.

Paul: And I got to be frank, not many people could pull this off. It’s a skill I have.

Rich: Not just that. You are the president of a company.

Paul: Yes.

Rich: So this wasn’t, like, you’re going head-down for five months.

Paul: No—

Rich: That’s not what’s happening.

Paul: I’m doing this on the train, I’m doing this on the weekends. But what’s critical is every day it sent me another one and I’d be like, I don’t like that.

Rich: Okay. Do you feel good about how it, what it sends you today?

Paul: It’s not just that. I get evidence that it’s good. And here’s the evidence. The evidence is I go on podcasts and I don’t have to prepare. I go on, like, people call me, they’re like, Paul, come talk about this thing.

Rich: Uh huh.

Paul: And I don’t have to prepare because I know the industry really, really well.

Rich: Whatever industry you want.

Paul: When I go talk to other AI people, they do not have information I do not—they have information that I don’t have, but not much.

Rich: Got it. When we come back, we’re going to talk about your journey and how you got here.

Paul: Wonderful.

[typing noise]

Paul: Hey, Rich.

Rich: Hey, Paul.

Paul: Do you need a really great mattress?

Rich: Always.

Paul: That’s not why we’re here.

Rich: Oh, good.

Paul: We’re here to talk about our company, Aboard, and what we actually do for once. And in fact, I think it is time for us to grow up and read a piece of paper that tells people what we really do and why.

Rich: Okay.

Paul: Okay, I’m going to start. You ready?

Rich: Go.

Paul: AI is everywhere right now. And for most companies, it’s creating more confusion than clarity. There is immense opportunity and value out there, and most organizations don’t know how to get to it. And that is true. You wrote that. That is true.

Rich: It really is true.

Paul: Mmm hmm.

Rich: Where do you start? What matters to a company or an organization? And how do you turn any of it into something real?

Paul: Look: You and I and the team here at Aboard have been on the ground with some of the world’s largest companies, helping them navigate complex transformations about AI and about other stuff. And we deliver real systems. We deliver real software that works great. It is not decks and memos. It is things that you can do to drive revenue and grow your organization every day.

Rich: Aboard is how we do that today. We keep AI in check.

Paul: Mmm hmm.

Rich: And don’t rush to it. We actually want to learn about your company and organization. And then slowly, methodically, we deliver real solutions built with AI, sometimes empowered by AI, whether it’s an agent or an app, that makes your company perform better and do better. And it’s always delivered faster and cheaper because the tools are incredible today.

Paul: It’s like rapid, rapid management consulting. Except unlike management consulting, there’s no hype, there’s no endless planning, just real outcomes in production.

Rich: If you’re ready to take advantage of all this change, reach out. We love to give advice, even if we don’t work together.

Paul: Even if you don’t want it. [laughter]

Rich: That’s true.

Paul: Yeah.

Rich: Visit aboard.com or email us at hello@aboard.com.

Paul: That’s it. All right. And get that mattress.

[typing noise]

Rich: All right. Paul?

Paul: Yes?

Rich: You’re excited. You’re animated by this amazing—apparently not enough people are emailing you and you needed a friend, a very informed friend.

Paul: There’s a little truth in that. No, look, here’s the thing. You know how you use this technology, so the first thing it does. Okay, it gives me a picture. Okay. Getting the day started because it was just hard to be met by a wall of text. And I like to see what Gemini can pull off.

Rich: Sure.

Paul: So—

Rich: But are you genuinely interested in the content that it’s putting in front of you?

Paul: In the picture? I’m interested in what AI can do, right?

Rich: Right.

Paul: So I have it kind of collage together some of the ideas in the newsletter.

Rich: Have you learned, on occasion, have you learned something you would have never otherwise learned?

Paul: From the images? No. But from the newsletter, absolutely.

Rich: Okay, so when you say images, there’s a header image. There’s a few images in the newsletter.

Paul: Absolutely.

Rich: Okay. How did you get here? It wasn’t going well in October and November. You’re banging away at it. And now you’re really happy with what you have.

Paul: I did a few things. So first of all, I learned how to really refine data using these tools. And it’s not as obvious as people think. So what you might think you do and what you can do is you can say, “Hey, look at this, this webpage,” right? “Can you summarize that for me? And you can make, you know, and then could you make it into a poem? Can you do something silly with it?” And I tried that. I tried to do, like, “Okay, keep me interested.”

Rich: Uh huh.

Paul: But I didn’t want that. I get tired when—it gets really, really tiring when it tries to be a person.

Rich: And also, the open-ended asks like that don’t go well.

Paul: They don’t go well. So what, the first section, after the picture—so the picture is just like, just kind of, because I’m waking up looking at this. But the first section is called “By the Numbers.” And what I said is, “Okay, go find news that has statistics and large sort of numbers in it, information, data.”

Rich: Mmm hmm.

Paul: “And then create a section for me called ‘By the Numbers’ that breaks out three or four or five really interesting important numbers, percentages, whatever that will help me—”

Rich: This is a thing. By the numbers—

Paul: Well, look, I used to work at Harper’s Magazine. We had the Harper’s Index which was just literally kind of ironic—

Rich: Stats.

Paul: Yeah, statistics.

Rich: Yeah.

Paul: And so the first number is 30 billion. Anthropic’s claimed 30 billion annual run rate is inflated, according to OpenAI revenue chief. So there’s a little conflict. Okay, that came from—

Rich: OpenAI’s revenue chief commented on Anthropic?

Paul: Said anthropic is full of it. So that’s good, that’s immediately, like—

Rich: There’s a lot of schoolyard bullshit here.

Paul: It’s a lot. It’s good to share. Okay. 25%, which is the number of organizations realizing significant value from AI despite 75% of C-suite leaders ranking it as among their priorities, per a Pearson and AWS study.

Rich: Mmm hmm. Okay, so this is useful and catchy. Like, it’s nice to snack on. Right? That’s this information. But it wasn’t easy to get here.

Paul: No. So I’m going to give you, I’m going to go real nerdy for a minute. Okay, you ready?

Rich: Go nerdy.

Paul: So I have a set of 300 feeds that get pulled in, and they’re pulled in periodically over the day.

Rich: How did you compile that list?

Paul: Some of them I was already reading in my kind of feed environment, right? But then I had AI go find some feeds. I have it do a Gemini search every morning so it can pull in news that the feeds don’t find.

Rich: Gemini is able to search yesterday’s news.

Paul: Because it’s Google.

Rich: It’s Google.

Paul: So it’s stuff that you don’t see normally in your feeds.

Rich: Yeah.

Paul: Okay? So it pulls in—

Rich: So sort of putting this all together.

Paul: Putting in stuff, so maybe a couple hundred articles are coming in every day.

Rich: Okay?

Paul: So then I go and I get the text of the articles.

Rich: Okay.

Paul: So I’m spidering. It’s got a bunch of different spiders and tools, probably a dozen.

Rich: Did you have to handcraft the spidering?

Paul: Yes. I mean, I had to have AI handcraft the spiders.

Rich: Okay.

Paul: Okay? And then there’s certain—

Rich: You told AI to use like a parser, like Readability, which is excellent.

Paul: It’s beautiful. Whoever created that was a genius.

Rich: Yeah. Or Beautiful Soup or one of those. Like, I’m trying to get a sense of how much, how much tactical guidance you had to give it.

Paul: 100% tactical guidance.

Rich: Okay. So I’m going to compliment you again.

Paul: Thank you.

Rich: Now you are, we’re similar in this way. I think I’m more of a sort of big-picture platform thinker than you are. But you’re a technical hobbyist that is deeply knowledgeable about the tools out there.

Paul: Look, I’m often in a position where I have to describe the change that the tools are bringing.

Rich: Yeah.

Paul: Ethically, I don’t feel comfortable unless I know them top to bottom. And I enjoy it.

Rich: That’s the thing, right? It’s a 1-2 hit. You created these newsletters because you were, we were touching industries when we would land clients that were alien to you, and you wanted to learn about that.

Paul: I gotta tell you, I know a lot about how to be, what a managing general agent insurance firm does now.

Rich: I have to say, I wish I had your level of insecurity.

Paul: Yeah.

Rich: About knowledge of other domains. Like, I’m not saying that as a snide remark. Like, I actually think it fuels a lot of your thinking. I think your technical know-how is also fueled by that, to a large extent. I want to wrap this point up as general advice, and then we’ll come back to your journey here for a second. These tools are actually picking up a lot of tools when you ask it to do something.

Paul: That’s right.

Rich: They’re doing that all the time.

Paul: That’s right.

Rich: And lifting the hood and actually being a little curious about all the stuff they’re picking up, which are frankly sitting there in GitHub or they’re libraries that are widely used is really good. Because you don’t have to code. We’re not saying go code. What you’re really finding out is, wow, these happen to be the toolbox that the whole world has been using for the last 30 years.

Paul: It throws open the treasure box.

Rich: Yes. I had this similar experience when I made that, we talked about in the previous podcast. I couldn’t go past the bug in the little Family Feud game I was making with Claude.

Paul: Mmm hmm.

Rich: And finally I was like, okay, I know about this library. Just use this library.

Paul: That’s right.

Rich: And it fixed it.

Paul: That’s right. Sometimes—that’s right. If you know the platforms and the approaches, you will be so much more successful.

Rich: Yes.

Paul: But it will also teach you the platforms and approaches.

Rich: This is the teaching, we’ve said in the past there’s a teaching challenge that comes with all this change.

Paul: That’s right.

Rich: It brings down your anxiety, but also it’s just what’s going to be asked to the world.

Paul: So I’m going to keep describing the platform. So first of all, it gives me those stats.

Rich: All right, so let me go back to where we were.

Paul: I will, I will. It also gives me a couple glossary terms, like change management.

Rich: You’re jumping.

Paul: Transparency—

Rich: You’re jumping ahead again.

Paul: Okay, fine. It pulls—

Rich: Hold on. I got 400 sources being parsed—

Paul: In a database with full text.

Rich: Okay. Now that’s just a glob of stuff.

Paul: It is, but it’s organized by time, and you can search through it.

Rich: Oh!

Paul: And not only can you search—

Rich: There’s a data model here.

Paul: Yeah, of course.

Rich: Time-based.

Paul: Of course. So, well, I have to know because I don’t want the newsletter—

Rich: Are you latching on metadata to all these?

Paul: I’m using RSS, I’m using the time it’s ingested, all that. I had to figure all that out. It has to have a good, clear timestamp because otherwise, how can you make a newsletter? It’s got news in it.

Rich: Yeah.

Paul: Okay? So I do that. And so now I have chronology.

Rich: Okay…

Paul: But I don’t have subjects. Now the first thing that you might think is like, all right, put it all in a big blob, send it over to Claude. And it’ll give you back—

Rich: Make a newsletter.

Paul: Yeah, but it just doesn’t work. It’s too much, or it’s just too, it just kind of broke all the time in different ways.

Rich: Yeah.

Paul: Because we all know that like it doesn’t really work. You gotta have, like, batches, you gotta constrain things.

Rich: Yeah.

Paul: So instead what I did is I installed a little LLM-ish technology on my server. It’s embeddings. Embeddings are a way of breaking up text and sort of doing the same kind of weird vector stuff that LLMs do.

Rich: Mmm hmm.

Paul: But teeny tiny. 384 dimensions instead of, like, billions and zillions and trillions. Rich: Mmm hmm.

Paul: Okay. So just like this little tiny—

Rich: Shades of RDF.

Paul: Yeah, little tiny—topics. It’s just, what it means is when you say—

Rich: Bits of data.

Paul: When you say OpenAI, it knows you mean big AI companies.

Rich: Right.

Paul: Right? That’s all. And you didn’t have to go, OpenAI or Anthropic or blah blah blah.

Rich: So you’re creating a little vector, baby vector database.

Paul: So that’s sitting there in the server and when all the text comes in, it gets vectorized. Which means that I can say, I can start to sort of pre-cluster. The reason to do that is that those queries take two to three seconds versus, like, five minutes.

Rich: Right.

Paul: So I can—

Rich: It’s cheaper.

Paul: I can assemble and organize and I can also de-duplicate and get rid of a lot of information because ultimately this thing is gonna cost about three bucks a day to send if I’m using straight API calls. It’s a little cheaper because I got it wired it into my Claude account. Just run a command line and does it once a day.

Rich: Uh huh.

Paul: But, like, it adds up. Like, if I kept it running and I hadn’t done this, it’s like 10, 15 bucks a day. It’s not worth it. Like, or it is, but it’s like it starts to get silly.

Rich: So today, this is worth pointing out, every time it fires off a newsletter to you, it’s costing $3.

Paul: It would if I was using the straight-up API, but I have some little hacks in there.

Rich: Okay, and what is it costing you now?

Paul: Zero. Because it’s, I have the Claude Max plan. I run it command line at like—

Rich: Okay.

Paul: This wouldn’t—

Rich: But you’re using much less tokens.

Paul: Oh absolutely. Because then what I do is I pass it to Haiku, which is their baby model.

Rich: Mmm hmm.

Paul: And I pass it to, and there was a point where I was passing it to one of the really, like, Gemini models to kind of do some fact checking.

Rich: Flash or whatever.

Paul: Yeah, I didn’t need it. But, like, so then Haiku, then Sonnet does some summarization, and then there are some sections that are really dense.

Rich: So you’re kind of, you’re sort of, you’re coming up to the model buffet to see what is faster, cheaper, easier.

Paul: That’s right.

Rich: And effective.

Paul: That’s right. And people don’t think that way. They just type in the box. But instead, if you treat these as different surfaces that do different things and really get to know them, you get—so the other thing is, every time I wanted to generate it to test, it would take 20, 30 minutes.

Rich: Ah.

Paul: And so I wanted to get that down and now it takes about five.

Rich: Okay.

Paul: So this is programming, dude. Like, there’s no difference.

Rich: This is the thing worth pointing out, right? Which is this is a product of about 30 years of technical-domain knowledge.

Paul: Yes.

Rich: I think people may have thought when we started this podcast that it was going to be a, wow, he’s got a bag of tricks. And I can do them, too. But everything you just threw out is going to sound alien to a lot of people. It’s worth saying that out loud.

Paul: No. And you know what’s funny? And this is what’s tricky. It’s a product. Like, if a client comes to us, I can’t give this away because it costs too much. I cannot for free give you $1,000 of token time for your particular company in your particular industry.

Rich: Yeah.

Paul: However, I can forward you this email for free.

Rich: A couple more questions about how does it assemble it? Is there some place where a draft lives and then it pushes it into the email?

Paul: Yeah. So there’s a scaffolding that’s kind of an outline, a set of prompts and rules, and there’s some scripts that run, that assembles each section as its own thing.

Rich: Did you do any actual coding?

Paul: Yeah, what I didn’t do is a lot, I didn’t write a line, like—yes, I’ve had editors open, looked at it, but that all gets blown away with the next section, the next session.

Rich: Yeah.

Paul: But what have, I absolutely have read through the code and made it narrate each sort of step and document the data that was going through. And I know that there is a JSON data blob that gets generated by the database output that then gets fed to Haiku.

Rich: Yeah, yeah.

Paul: So, like, yeah, no, no, like all of that. If you asked me to reproduce this system from here using all my coding skills, I could. I would just sit down and write the code and I would know what to do.

Rich: Got it.

Paul: Okay. So then—

Rich: I have a couple of closing questions.

Paul: There’s two other kinds of sections that I want to talk through.

Rich: Okay.

Paul: Okay? One is called Strategy Prompts. And what it does is it looks at our business.

Rich: Uh huh.

Paul: It looks at the news, and it actually has a little model of our business, like, a little financial model that I program. Little guy.

Rich: Okay…

Paul: Think Excel’s spreadsheet.

Rich: Little cutie.

Paul: Yeah. And it says, “Hey, you’re running an AI transformation shop. You work with customers and clients and you do these sort of things. Here’s what the news is saying. Let me be a strategist for a minute and ask you some leading questions.” So in this case, it’s like, wait a minute, we got ChatGPT Enterprise has hit. Okay? ChatGPT Enterprise is Codex and their sort of enterprise offering, and all their stuff is like one big stack. Right?

Rich: Okay.

Paul: So it’s no longer split up. Everybody can kind of have it in your org. And so the questions it’s asking is, like, “Hey, wait a minute, you guys are trying to deliver this stuff, but it’s coming out of the box over there with OpenAI. How are you going to compete?”

Rich: Yeah, yeah.

Paul: It’s a good question. And it’s actually a question I think we tend to avoid. And I’m kind of glad to have a robot do it.

Rich: We’ve been very moat-centric these days.

Paul: Yes. And so, you know, it talks about things like context engineering, TDD, but it gives me actions. It’s like, “Draft Aboard’s point of view on AI-ready development practices. Build a one page checklist clients can self-assess against—” Am I going to do that? No. I’m just not.

Rich: Yeah.

Paul: Like, it doesn’t, that’s not where we are as a company right now.

Rich: Yeah.

Paul: But the framing is actually good for just jarring my head a little bit.

Rich: Yeah.

Paul: And making me go like, wait a minute, what are people thinking here?

Rich: Yeah.

Paul: Like, what is going on? And then it asks, like, a big old question at the end. It likes to get dramatic. “Is Aboard value in the build or the process? The answer changes pricing and ICP—” Which is Insane Clown Posse. So I don’t know why.

Rich: Oooh.

Paul: I don’t know, is ICP a thing? Do you know ICP?

Rich: I don’t know what that means.

Paul: Somebody does.

Rich: I know Insane Clown Posse.

Paul: You can write in—hold on. Go ahead. Ideal Customer Profile, baby. That was it.

Rich: Ooh.

Paul: Thank you, Gabe. Thank you.

Rich: Okay?

Paul: Okay, I’m going to tell you, so that is it. That’s Opus.

Rich: Uh huh.

Paul: Opus goes, runs the strategy and actually tries to be a consultant for a minute.

Rich: Yeah.

Paul: And then I have Opus do one more thing. I got to tell you about it. I got to tell you about it.

Rich: Okay.Go for it.

Paul: It’s called Product Improv Theater.

Rich: Oh, Jesus, Paul.

Paul: And so what it does is—

Rich: No more computer for you.

Paul: It takes all the news of the day.

Rich: Uh huh.

Paul: And it says, “Given what we know about a board’s business model and maybe a little bit of what we just learned in that strategy session—” Notice how the pieces fit together?

Rich: Yeah.

Paul: Okay. “Can you go ahead and improvise and make up a product that might help this company?”

Rich: Okay…

Paul: Okay? So in this case, it created Context Mesh, a one-live context layer that makes every AI tool in your stack actually know what’s going on. It’s a shared organizational context API that ingests live signals from Slack, Teams, Calendar, Jira, CRM, and Docs, and exposes them as a queryable knowledge layer via MCP endpoints that any AI tool can call. And then, Richard, then.

Rich: Mmm?

Paul: It builds it. It makes, it prototypes it for me.

Rich: Oh God.

Paul: No one’s ever thought of this before. It’s absolutely random. It comes out of the news. And it builds me, every day, another prototype piece of software, another web application.

Rich: This is upsetting.

Paul: And then it sends me a screenshot of it, and I get to look at it, and I’m just in paradise, because it’s the silliest and also most useful thing.

Rich: Okay. Not great stuff.

Paul: No, no, no. It’s not—like, it’s not, Pentagon hasn’t come in here and done the branding guide.

Rich: No, I know, but… Pentagram, you mean.

Paul: Well, yeah, no, those are different!

Rich: The Pentagon doesn’t do branding, as far as I know.

Paul: No, they actually do. When they’re setting up new countries after they’ve, like, killed someone?

Rich: They’ve got to come up with a flag logo?

Paul: Yeah. No, you really do.

Rich: Fair enough.

Paul: Go ahead.

Rich: I mean, this is just you playing.

Paul: It isn’t—

Rich: There’s no useful utility in these.

Paul: That is absolutely not true. Some of these ideas are good, and I’ve showed them the people, and they’re like, “They’re pretty good.”

Rich: Interesting.

Paul: And then it tells you who the buyer is. CIOs and heads of AI. Tells you why it’s a good idea, and it’s because, and it gives you, like, a nice list. It gives you a TAM. It gives you ARR.

Rich: Yeah, yeah, yeah.

Paul: And then it plays devil’s advocate and tells you why this is a bad idea. And then it gives you—

Rich: Good God.

Paul: Then it does some competitive research.

Rich: No more—go to the Brooklyn Botanical Garden.

Paul: No, I’ve been there. Been there many times. One of my first dates with my wife was there. But regardless—it was very hot and a man took off his shirt and he was so covered with hair that I will never forget it. [laughter] It was the hairiest man I’ve ever seen. Brooklyn Botanical Garden, 2000 and something.

Rich: Yeah.

Paul: Then it gives me news that’s related and it gives me competitors to that product. This is a very good, serendipitous way to just get a little more—

Rich: Venture out a little.

Paul: Yeah. Just, never saw it before, never going to see it again. Am I going to take this to a client? Kind of probably once a year, I’m going to go—

Rich: Check this out. This is kind of fun.

Paul: Kind of wacky. You want to talk about it?

Rich: Yeah.

Paul: And then—I’ll go through the rest in, like, 30 seconds. It does a thing called it finds a big cheese. In this case, it’s Anthony Tan, the co founder and CEO of Grab, which is a Southeast Asian super app that he’s recreating as an AI-native platform.

Rich: It’s like a WeChat.

Paul: That’s right. And so it gives you that. And then it actually just breaks down some news and it contextualizes the news. So Google releases Gemma 4, which is an LLM that kind of can run on your phone. And it gives me a summary and then it says, “No more choosing between capability and data privacy. If you’re building for regulated industries or enterprises with strict data residency rules, local agents eliminated API dependencies entirely.” Not bad. Like, okay, good.

Rich: Okay.

Paul: So on we go, on we go. And it gives me lots of news and it reads some PDFs and then it goes, it goes to YouTube.

Rich: So this is—

Paul: It goes to podcasts.

Rich: —a very big newsletter every day.

Paul: Well, but it’s a lot smaller than the news.

Rich: Mmm.

Paul: It’s really manageable and it’s kind of fun. It’s mine. It’s got the Product Improv Theater.

Rich: Yeah.

Paul: It just is, like, what can robots get up to?

Rich: Yeah.

Paul: And then it’s sort of, it always, I have it suggest something to write about and I’ve never, I will never take its advice. It’s terrible, but it always usually gives me, like, one or two ideas.

Rich: Lights a fuse.

Paul: Something that sucks is so much better than nothing.

Rich: Yeah.

Paul: And then it tries to pick a really good article. And then I have it make a cartoon.

Rich: Oh God.

Paul: I know. And the cartoons are always really weird and they never make any sense and they usually have little animals in them and I think it’s the dumbest thing. And every time I see it, it’s so absolutely vacuous and devoid of meaning that I crack up. It’s just…

Rich: I mean, it’s a little smile on your face.

Paul: Yeah, it’s just really good. And so anyway, multiple layers get brought together. They get reviewed in multiple steps. Used to take more than 30 minutes. Used to take almost an hour.

Rich: Yeah.

Paul: Got it to 30 minutes, and now I got it to about five. And I can do this—

Rich: Five to—so you spent a good amount of time optimizing this thing.

Paul: I had to, because it was getting expensive and it was eating up a lot of tokens, and I don’t like that. I don’t like inefficiency in general.

Rich: Okay, so let’s talk about that for a minute.

Paul: Yeah, sure.

Rich: And then I have a closing question.

Paul: Okay.

Rich: Did you say, “Claude, this is taking five minutes. Make it take 30 seconds. Go optimize and find shortcuts.”

Paul: You know what’s funny is it, I did…eh. It just doesn’t do the best. So then you go, “Hey, hold on a minute. We can do vectors in the database. Can you think of some ways that we could optimize?” And it’s like, “Yeah, yeah.” And then it actually would go do all this stuff for me, and it would often, it’s discovery, right? It’s essentially, it’s writing a query for me. At one point, it found that we had stopped segmenting news by industry, and so everything was getting kind of muddy, and it was kind of covering it up. It was like, actually, I was like, it’s very easy, this stuff is a black box. And it’s very easy for it to just create a big mess, and then it’ll kind of clean it up because it knows it’s supposed to deliver a newsletter.

Rich: Yeah.

Paul: But it was gathering way too much news, and, like, not—so you really got to go in there and you got to, like, you got to get it tightened up, and then you kind of have to go, you have to know.

Rich: Yeah.

Paul: Now, what’s different is you can say, “Hey, I’ve got the pgvector extension installed in my database.”

Rich: Yeah.

Paul: “Can you tell me a few things I might do this that would help me organize the news feeds for the newsletter?” And it will go away, and it will sort of stochastically come up with a list of 10.

Rich: Yeah.

Paul: And then you’ll go, like, “All right, let’s try that.”

Rich: Yeah.

Paul: And then the cost of trying is very, very low.

Rich: I have two closing questions.

Paul: Okay, go for it.

Rich: The first is, you learned a lot doing this.

Paul: A ton.

Rich: Do you think the next time you do a project like this, it’ll take half the time?

Paul: Oh, no, it takes five minutes.

Rich: No.

Paul: Yeah.

Rich: No.

Paul: Because—

Rich: You’re not gonna go from five months to five minutes.

Paul: No, you really do, because it’s a product now. It doesn’t look—

Rich: No, no, no. Forget this product. You’re gonna make another product to, like, manage your kids’ college applications.

Paul: Oh, okay. So the first thing—but just to close that point out, if I want to make a newsletter about the interest of a company?

Rich: Yeah.

Paul: I can give it the URL for the company. It will go read the company’s website, and—

Rich: Go through this process.

Paul: It will construct a newsletter for them that they can receive every day. We’re gonna do that for our clients.

Rich: Yeah.

Paul: Right.

Rich: Fair enough. Fair enough.

Paul: Okay? So that we can all be—oh, the other thing I forgot to say, you can reply to this and it will do research based on the news that’s in the database, so it doesn’t go off and LLM it up.

Rich: That’s very cool.

Paul: Yeah. You’ve seen it. It’s pretty cool.

Rich: Yeah, it’s very cool. I’ve seen it.

Paul: Okay. So that was question one.

Rich: Second question—

Paul: So wait, the answer ultimately is like, no, it’s still really hard to build software. You can get a lot done in a week, but then you got to tweak every subsystem for months.

Rich: Yeah, but, which leads me to my second question, which is you don’t think you’re technical. You don’t call yourself an engineer. You call yourself a quote-unquote journalist.

Paul: Mmm.

Rich: Whatever. But you’re highly technical.

Paul: Well, I am a developer. I want to develop—

Rich: You are a developer. I mean, this is, we nerded out probably more than any other podcast ever on this podcast today. Do you think that in 6 months, 12 months, 24 months, 4 years from now, that someone without your technical know-how will be able to do this?

Paul: Yeah. Here’s what I—okay, I’ve given this a lot of thought. It depends on the kind of human. Here’s what’s different. Getting to execution of something with a computer in an LLM-assisted environment, like Claude Code or whatever. I’m seeing people who have pretty light technical skills pull off things that are way beyond their abilities.

Rich: Today?

Paul: Yes.

Rich: Yeah.

Paul: Now, the funny thing is that this—newsletter aggregation was never beyond my abilities. I’ve always been good at that kind of thing. But I’m doing stuff like programming FPGA chips, which always was outside of my ability. So everybody can—

Rich: Hardware…

Paul: Everybody can take a step up. You got to know the step you want to take. And frankly, that goes—

Rich: Do you, in four years?

Paul: Yeah, you do, because you got—

Rich: Why can’t I just say, “I really like this…reprogram my remote control. I want to use it to manage my, to control my air conditioner.”

Paul: Yes, you will be able to say that, but it won’t mean anything because absolutely anybody can do it. You’re asking kind of two questions. Will the LLMs allow you to do all sorts of programming things even if you aren’t a programmer and don’t care, and it can be really casual and kind of lazy? The answer is yes.

Rich: Mmm hmm.

Paul: Will the LLMs allow you to build really great products that integrate with lots of different systems that let people have really great experiences?

Rich: Yeah.

Paul: Sometimes.

Rich: It takes work.

Paul: But ultimately what I’m finding is that… You know what I’m looking for here? I’m building a product and it has to have novelty and it has to meet my standards.

Rich: Yeah.

Paul: And I have a goal in mind. The first person to make happy was me. I’m very patient.

Rich: Yeah.

Paul: Then the next group is the people in the company.

Rich: Yeah.

Paul: Because they have to do things, because we’re the president and CEO. And I’m sorry about that.

Rich: Yeah. No need to apologize.

Paul: But the next level is our clients, who we have to do the things that they tell us to do.

Rich: And make them happy.

Paul: And they have to be really kind of excited and motivated.

Rich: That’s right.

Paul: We’re not quite there with this yet, but I got to tell you, I showed it to a client a week ago, and they were like, “Yeah, please send me that.”

Rich: Yeah.

Paul: And they might get bored with it in a week, and I would really welcome that. Right?

Rich: Yeah.

Paul: But what I’m saying is, like, months to get to that phase.

Rich: Yeah.

Paul: Now, I could also have hacked it together in a week and shown it to them if they really wanted this specific product.

Rich: Yeah.

Paul: But to make a truly good product that they would lean in on and be like, “Hey, actually I am curious about that.” As opposed to them asking me for it and I build it quickly?

Rich: Yeah.

Paul: That’s still a lot of work.

Rich: Yeah. Here’s my read on it that.

Paul: Okay.

Rich: Yes, these tools are going to be very capable and they’re going to infer a lot. But in my experience, today—and I don’t think it’ll change in four years—is that these tools punish laziness.

Paul: Yeah, they do.

Rich: What they essentially do—

Paul: No, it’s worse. They reward it, but it’s actually a punishment.

Rich: It’s actually a punishment. And the truth is, high-quality output is hard. That isn’t changing. Now, will these things have more taste and be more thoughtful? Probably. But the truth is, what you had conceived in your head, that wasn’t real yet, for a long time? You needed to hold its hand to get there. That is a reality of good product thinking and good design thinking. That isn’t going to change.

Paul: I’m going to leave you with a thing I deeply believe. I’ve talked about this a lot. I’ve shared it with you. But I’m going to ask it to you as a question. What is talent?

Rich: Being good at something.

Paul: No. Talent is being annoyed at something. And you are annoyed with it enough that you will go back to it and you will do it again and again until it is at a level of quality that gives you comfort and control.

Rich: Yeah.

Paul: If you watch a professional pianist, their standard is so unbelievably high, and that little finger goes over and they’re like, that is the end of my year. I am so frustrated. People are talented because they need to work something out. Okay? And humans connect to that because we want to see someone do that work so we can understand the world.

Rich: Yeah.

Paul: Anyone can slop together a fake TikTok in an hour, in four years from now.

Rich: Yeah.

Paul: But nobody will ever care.

Rich: Yeah.

Paul: So even though it looks really scary right now, just know that everything that looks scary is going to be a matter of enormous indifference in the future. And new talents will be emerging about how to get that newsletter to be really good, not a person—

Rich: And interesting and creatively fresh, somehow,

Paul: in a reflective mirror way. I don’t want it to be—you know what? And I’ll leave you with this. At one point, the little strategy section, I tried to make it have the voice of an arrogant CEO who would only talk about wine and his annoying stoner children and his five daughters.

Rich: That’s fun.

Paul: It was fun. It was exactly fun once. I laughed out loud. And the second time, the joke was so dead that I was ashamed and embarrassed that I had put it forward. [laughter] This thing should produce stats and weird images and call it a day.

Rich: Yeah. I get it.

Paul: And so that’s where we are. So, look, this is a product in this new world, but underneath, it is a software platform like I have built for 25 years. And it took months.

Rich: Yeah.

Paul: But now it can scale, and I can deliver it to any client.

Rich: Yeah.

Paul: The only real major difference between how we used to build things is that I was able to do it in my spare time from my phone.

Rich: It’s crazy.

Paul: That’s the real difference here.

Rich: Yeah.

Paul: But I had to learn—

Rich: You’re not hunched over a laptop.

Paul: I had to learn an enormous amount of stuff. I had to get really caught up on my pgvector extensions, all that stuff.

Rich: There’s a lot of learning in there.

Paul: That is correct. And so I just like, I thought it would be good to show people a thing. Like, we are building nonstop here and we’re probably not talking about it enough. But I’m going to say something else that I think is really important. I do believe it is very, very possible now to fully de-risk building with these tools.

Rich: 100%.

Paul: There was a long period of time where everybody was like, the last mile is just too long and you got to get back in there, you got to type the code—

Rich: We built tools that make that happen without risk.

Paul: And they are secure and they are safe and they work like software used to work. And I think, like, we have to get past that part of the conversation where they’re like, it’s not real until blah, blah, blah. It’s real. This is a real tool that I use and it is very useful for me in doing my work.

Rich: Yeah.

Paul: It’s not a newsletter that I would go out and—I wouldn’t pay to subscribe to it from someone else, but for me, it’s very, very useful. And it’s very easy to adapt that to any organization.

Rich: Sure.

Paul: There we are.

Rich: You’re having fun and I’m a little jealous.

Paul: I’m going to subscribe you to the Property and Casualty newsletter.

Rich: Ooh!

Paul: Yeah. Insurance.

Rich: Good stuff in my inbox.

Paul: It tends to draw a lot of tornadoes, when it does the image.

Rich: Yeah. We take a different approach to leveraging AI for your company. We study, understand, get a full context, and then bring these amazing tools and amazing people to deliver solutions for you. We are Aboard. Check us out at aboard.com, or reach out. We love to talk, we love to give advice in this crazy, crazy time. Hello@aboard.com.

Paul: if you’re really nice, I’ll make you a newsletter.

Rich: Ooh! Have a great week.

Paul: Bye.

[outro music]