How I run autonomous coding agents from my phone with OpenAI Symphony + Linear | Alessio Fanelli (Kernel Labs)

Alessio Fanelli, founder of Kernel Labs and co-host of Latent Space podcast, walks us through two very different AI workflows: (1) a fully autonomous coding setup using OpenAI Symphony + Linear, where Linear acts as a state machine and Symphony manages agents through the whole dev lifecycle with zero babysitting; (2) Codex with browser access searching eBay for underpriced Pokémon cards—autonomously browsing, extracting PSA certificate numbers, and flagging deals on $10K–$20K cards for his San Carlos card shop, Merlin Games. What you’ll learn: Why “agent manager” is a better mental model than “agent prompter”Why local Mac Minis don’t scale, and what a cloud VPS unlocksHow to wire Symphony and Linear together as an agent state machineHow to track token costs per task (and what 221 million tokens buys you)What Glimpse does, and why better agent senses extend autonomous runsWhy your CLAUDE.md probably needs a full purge, not more instructionsHow Codex scouts underpriced $10K Pokémon cards on eBay at scaleThe new category of small business that AI just made possible— Brought to you by: Firecrawl https://firecrawl.dev/?utm_source=newsletter&utm_medium=partner&utm_campaign=how_i_ai—Power AI agents with clean web data Jira Product Discovery https://atlassian.com/howiai—Prioritize with insights, build with confidence — In this episode, we cover: (00:00) Intro (02:24) Prompter vs. agent manager (04:31) Live demo: Symphony + Linear (09:31) Setting up Symphony (14:15) Purging your skills files (18:06) The benefits of this system (19:10) Demo: Using Codex to hunt for Pokémon cards (24:17) The benefit of AI for small businesses (28:23) Lightning round — Tools referenced: • OpenAI Codex: https://openai.com/codex • OpenAI Symphony (open-source framework): https://github.com/openai/symphony • Linear (project management/agent state machine): https://linear.app https://linear.app/ • PSA (Professional Sports Authenticator) grading: https://www.psacard.com https://www.psacard.com/ • TCGplayer (card pricing): https://www.tcgplayer.com https://www.tcgplayer.com/ • eBay (used for card price scouting): https://www.ebay.com https://www.ebay.com/ — Other references: • Meta Ray-Ban glasses: https://www.ray-ban.com/usa/ray-ban-meta-smart-glasses • The Monk and the Riddle by Randy Komisar: https://www.amazon.com/Monk-Riddle-Creating-Making-Living/dp/1578516447/ref=sr_1_1 • The Divine Comedy by Dante Alighieri: https://www.amazon.com/dp/0451208633 • AS Roma (football club Alessio and Claire are both fans of): https://www.asroma.com/en — Where to find Alessio Fanelli: X: https://x.com/FanaHOVA Latent Space podcast: https://www.latent.space/ — Where to find Claire Vo: ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo — Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [email protected].

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Claire Vo?

  This is my favorite positive outcome of AI, which is small business creation. Just the ability to intersect the human world in a way that has been historically very inefficient has been a quality of life improvement for me.

• 0:12Speaker 01

  You know, my dad, their business, they deliver fish to restaurants. They got like this freezer with the frozen stuff and like somebody's going out there with like the pen and paper every morning, kind of like writing down what's there. Sometimes they're like, oh my God, we're missing like three tuna, so like we're missing a box of shrimp. All of that work now can easily be automated, even just with the meta glasses.

• 0:31Claire Vo?

  And you have another use case, which is the use case that my nine-year-old wants to see. So let's do our Pokemon card by AI use case.

• 0:40Speaker 01

  So I use Codex for two things. The first one is like getting the PSA certificates to keep track of a specific number for each grade. Then the next thing I'm working on is when you go to like all these trade shows, people are coming to you, they're selling you cars and you gotta price them in real time. That whole process is super inefficient because people are like searching each car manually, like on eBay or like DZG Player, getting the number. You can actually use AI to save clock time for real people by doing these things autonomously.

• 1:09Claire Vo?

  Welcome back to How I AI. I'm Clairvo, product leader and AI obsessive here on a mission to help you build better with these new tools. Today I'm speaking with Alessio Finelli, founder of Kernel Labs and co-host of the Light and Space Podcast. He's going to show us how he uses OpenAI's Symphony plus Linear to automate all his engineering tasks and how he has Codex Goal shopping for very expensive Pokemon cards. Let's get to it. Quick word from today's sponsor, Firecrawl. If you're building with AI agents, you've probably hit the same wall. Your agent needs data from the web, but the right pages are difficult to find, buried in JavaScript or blocked behind logins.

• 1:51Claire Vo?

  Firecrawl is a web data API that lets agents search, scrape and interact with the web at scale and get that clean, structured data they can actually use. Over a million developers, including myself, build on it. It's open source and it's free to start. Stop fighting the web. Web for Data and start powering your AI agents and apps with FireCrawl at firecrawl.dev. Use code HOWIAI to get 10,000 free credits today. I'm excited about what you're going to show us because I think we have heard a lot of people talk about orchestrating many agents autonomously across a project. But we actually haven't seen many people do it.

• 2:36Claire Vo?

  I still see a lot of prompting, even if you're prompting into a loop or a goal or something that spawns subagents, people are really still human in the loop. And so I'd love for you to tell us how you came to this point of doing more autonomous management of your agentic tasks.

• 2:52Speaker 01

  I started this podcast called Lit in Space three and a half years ago. And my co-host, Wix, he had built this thing called Small Engineer at the time, which was kind of like the first autonomous coding thing. Over time, it's always been a cool demo, but I feel like the models were not quite as good to really do longer running tests. They definitely changed, you know, end up last year, and I think everybody kind of feels the same. And what really clicked for me was like starting to move away from being an agent prompter to kind of be an agent manager. And that is kind of taken a lot of different ways. So the first thing that everybody tried was kind of like the Kanban board. You would kind of put all these things in there, move them back and forth. What I found is that it was hard to get two, three, four turns through that.

• 3:35Speaker 01

  Like it was easy to get to the task and kick it off, but then it was hard to intervene on it. And also like having it local just didn't quite work. So the big thing for me was moving away from kind of like local runtime to having it in a VPS in the cloud and then having different channels to talk it to. So you can kind of like text the agents, you can use Linear to talk to them, you can prompt them directly in the shell. And this is also like something, I guess, like in the last month, you know, Codex also added, Codex Mobile, Claude is also adding kind of like the mobile management. But I'll kind of run you through what I do and then maybe people get some inspiration from it.

• 4:15Claire Vo?

  Great, and I will really benefit from this because I'm staring at my four Mac Minis over here. So I'm still running locally and I just come downstairs and like kick them alive every now and then.

• 4:26Speaker 01

  Right.

• 4:27Claire Vo?

  So I'm, you, maybe you'll convince me to move all this to the cloud. Let's see.

• 4:31Speaker 01

  Yeah, so I, I tried to use some more fun examples during like the meta one. So I own a car store in San Carlos called Merlin Games. And so one of my interests is trading cards. So my setup is I have this thing called Zill. Zill is basically like an agent plus a VPS. So this machine, for example, is like, you know, 32 gig of RAM for a course. I have all my coding agents pre-logged in in here. And you can also use some of the open source models if you want. And what I have here is kind of like the sourcing thing where you can basically use it as your own server. On this, I have the OpenAI Symphony setup. So Symphony is basically, I mean, you can kind of look it up for a better description,

• 5:14Speaker 01

  but it's kind of like a loop for turning issues into coding runtime and then having kind of like linear as a source of truth for it. So what I have on my linear, I basically have all these different projects. So this one is powered by air, for example. And I work on it sometimes in through Symphony. Sometimes I work on it through Codex directly or Clockcode directly. And if you go into any of these things, basically what you see is you have the original task. So this is what I wrote as the initial spec, which is, you know, pretty simple. Then I'll basically move it from here to to do. So this tells Symphony it needs to work on it. What Symphony does, it creates a Codex workpad.

• 5:57Speaker 01

  So the agent kind of makes a plan on how to implement it. And as a plan, and as a accepting criteria, different validations. And Symphony has a file called workflow.md where you basically explain how, what, what it should do for these. This will kind of go to work and then eventually move it to human review. So what you can do here is review it on GitHub and you can add, I'll reopen the PR and show you. You can add all these different comments, you know, I guess now.

• 6:27Claire Vo?

  They're resolved.

• 6:28Speaker 01

  They've been resolved, this is like too long, blah, blah, blah. And then you just move it to rework. So once you move it to rework and then we'll do, we'll do, we'll kick one off while we record this. Uh, it creates a rework checklist. So it goes through all the comments and it's like, okay. Um, these are all the things that went wrong, kind of addresses them. It tells you how to address them line by line. Um, moves it back to rework, um, to, from rework to done, once it gets merged. And that's kind of like the flow. I don't really look at the traces one by one. I just kind of direct the, um, the agent to work on it. So whenever I'm, even if you're outside, right? Like I might be on, on my phone and I'm looking at something here.

• 7:10Speaker 01

  Uh, let's say here we're like, hey, this is kind of like noisy. Um, what I can do is like, I can create a new task. It's like cleanup, bringing stable. Let's remove the spread column. It's too noisy. Let's also make the set name applicable. Other cards. And here I'll simply put it in to do, create a shoe. And then each of these symphonies has its own dashboard on it. So this one is TCG var buyer. Uh, these are previous tasks that run. So one of the things I'm also trying to do is try and figure out. How much is software gonna cost to build?

• 7:54Speaker 01

  So I think people understand the idea of like the agents fried it. But sometimes it's hard ahead of time to know how many tokens it's gonna take. And so it's hard to price, um, and understand what it's actually worth doing. So as you can see, most of these tasks are kind of like, you know, fifteen, thirty, sixty. But then this one is like two hundred twenty-one million tokens. And so you can kind of go back here and be like, okay, this test was how to make it deployable in yourself. So, you know, this whole thing was just not working. It was originally built as kind of like a local thing. So I had to like, you know, rebrand the storage, kind of like, you know, change all the requests or handle, blah, blah, blah. So this is like. Quite a big task, so it kind of makes sense that it costs a lot of tokens.

• 8:39Speaker 01

  And so from here, you can kind of start to think about how in the future can I make these more efficient by either adding more checks or adding better descriptions or better tooling. So the task we just created, you see, just kind of went live. So here you can kind of see, you know, obviously, there's usually like, you know, four or five of these in different projects that are running. So I don't really want to see the whole thing, but I just want to glance. And I'm sure I can make this UI a little prettier. Maybe once they give us Fable5 back, that'll be good enough. But so this is working, right? And so in a little bit, this is going to go from from in progress to like human review. And once it goes to human review, then we can kind of look at the Vercel preview. And we can make comments on the code and on the front end and kind of move it back.

• 9:24Speaker 01

  But I could be doing this here, I could be doing this on my phone, I could be doing this anywhere, really. And to kind of put it to the extreme, I had, let me see if I can find it.

• 9:37Speaker 01

  I created this project called PyQ, which was basically like putting your repo plus the Py agent in a VPS and then anybody on the internet could send you, I think I put it in a different project, could send you like a coding task to your product. So it's almost like in the future, you know, and I think some people now have this idea like a request for prompt instead of like request for for requests. Everything is just how do you transfer context between people?

• 10:06Claire Vo?

  So before we move on to maybe another workflow, what you just showed me was, look, you can just create a linear project for any one of your code bases, you can integrate that with Zo and with Symphony. And then all you're doing is really tasking linear as sort of like your state machine for all the work that needs to happen in your code base. You can manage that on linear from your phone, you can manage that from your desktop, from the web. And you don't really have to worry about the framework of how that task gets, you know, broken down, how it gets implemented, even how your comments get reviewed. That's all set up. And I just wanted to share for people. Symphony is something that OpenAI open sourced as sort of a framework for autonomous runs.

• 10:51Claire Vo?

  So it's it's just a very opinionated way to do this work. And it basically does what you just showed. It monitors a linear board, spins up agents when it gets assigned something. And then, you know, you can can land it in a PR and it gets marked as done. How simple was it for you to like actually set up Symphony? Because I think people look at these things and they're like, okay, that makes sense. But what do I actually do with this GitHub repository? And I know they have these two options here, which is like basically tell your coding agent to build it for you. Or there's this reference implementation. How did you actually implement Symphony?

• 11:26Speaker 01

  Yeah, I took the Elixir implementation that really like the core things to change are like the workflow that I'm the in the main in the main folder that kind of like explains how to do it. And then build the UI. So the Symphony itself doesn't have a visual UI for it. And I also don't think it has the same. It doesn't have by default the ledger for token usage. So it's only like a, yeah, a state monitor. It doesn't actually look at like, you know, how much have you spent per task and kind of like all these different things. But yeah, I think like overall the harness, you know, it's pretty straightforward. I think like the reality is like, how do you build tools for it to be more effective?

• 12:10Speaker 01

  And that's kind of like one of the main things also at Kernel Labs we've been working on. So we've built this other thing called Glimpse, which is a kind of like a playground extension that coding agents can use to take screenshots, to do visual dips between screenshots, take videos. And so it's almost like, yeah, how do you let these runs kind of go longer and longer? So it's less about the orchestration itself and like the tools you give it to keep going versus coming back to you with the human review. And I think that's also why it's so important to like, keep track of how many tokens and how much time it takes. Because it's usually like, directionally, it explains you how many issues it ran into, you know? So if you expect something, you should start to have at some point.

• 12:55Speaker 01

  Some idea of like how many tokens you think this will take. You know, is this like a 10 million token task? Is this like 100 million token task? And if the reality is very far away from your expectations, there's probably something in the tooling layer that you can do to improve. So that's really where most of the kind of like value comes from for people.

• 13:16Claire Vo?

  Yeah, one of the lessons I want people to take away from this is I get asked all the time like, Claire, how do we build our own agent orchestration platform? And like they they send me these like giant, very complicated documents and workflow diagrams. And, you know, pointing them to just like Symphony's spec MD, which just describes how the system is supposed to work. It's in natural language and it just is very prescriptive about what the primitives are of this workflow and what to store and record and how to move things forward in sort of the software development lifecycle. Like, it's very long, it's very detailed, but it's literally just a markdown file.

• 13:56Claire Vo?

  And I think people kind of over engineer at first what these things can be. And ultimately, the power of LLMs, especially these newer models, is you could just give them a spec for how they will work and they will, you know, they will lock to that spec when executing whatever you hand it.

• 14:16Speaker 01

  Yeah, I think everybody just wants to have the magic skills file that does everything for them on like the magic MD, the software business problems. I think the reality is like now more than ever, like small sentences of like very a lot of weight. You know, like, for example, I built this work tree manager before the coding agents themselves had it. And in every agent's MD, I was like, you have to use the word tree manager. And now sometimes I forget I had it in some projects and then I start a task and it's like, reinstall, I'm like, you don't need it anymore. But like, because I had deadline, every time it's now doing that.

• 14:58Speaker 01

  And I think a lot of folks have been talking about purging your markdown files now every few months. I think that's something that obviously makes sense. I think the models themselves also have this like tendency to like. Add rather than remove. So if you're like, hey, you don't need to always use the work through manager. Instead of removing that line, it's gonna add a line to say that you don't have to use it all the time though. You know, and now you're kind of getting more and more confused. So for example, my, the, the skill that I'm the, it's not super descriptive on what to do, but it's like, hey, this is where you put the, the symphony. This is how you should architect it. So every symphony instance has kind of like its own name. It's got the repo that you're working from.

• 15:43Speaker 01

  It's got the workspaces for each task. It's got logs, which include the token usage. And it's got the state of, of this run. And then these are the things that you need. So if you don't have them, ask me, otherwise don't ask for stuff. These are the exact commands. These are the flags, but I'm not really telling it what to do and what to use. I'm just saying, these are like things that you gotta keep in mind and then you kind of let the model work. See, this is like a good example. I think it just added this today when I was adding a new project. It's like, this one is a ready to register year. And it's like, this should not be in this file. Like it should look up every time. It should just search every time what's already there.

• 16:27Speaker 01

  You know, those are like all examples of like, if you just let the models kind of do their own things, that you just end up with this like very weird things.

• 16:37Claire Vo?

  Okay. So red diff your skills and red diff your markdown files and get some stuff.

• 16:41Speaker 01

  Yeah. I feel like the create skill thing that the Codex app, for example, added, I think is like a great idea. But I think for a lot of people, it just puts them in a lot of trouble. Because it's like, they are not very descriptive in the skill itself. And then the model is like very focused on following the skill. And so they're actually doing themselves for the service a lot of time.

• 17:04Claire Vo?

  This episode is brought to you by Jira Product Discovery. AI has made individual PMs incredibly productive, but multiplayer mode is where it still breaks, getting everyone aligned on what should actually get built. Decisions live in a markdown file from last week. The roadmap's a spreadsheet no one's looking at. Jira Product Discovery is where teams actually decide what to build, capture ideas, prioritize them as a team, and share a living roadmap everyone works from. It's powered by Atlassian's teamwork graph, so it can pull in customer feedback, what your team shipped, plus your goals, and suggest what to build next. And when a decision is made, you can hand it off straight to Jira,

• 17:46Claire Vo?

  so a developer or even an agent can pick it up and start building. Teams at Canva, Deliveroo, and Toast already use Jira Product Discovery. Join more than 25,000 teams at atlassian.com/howiai. Start building the right things together. Do you feel like you're getting a lot more done on this orchestrator? Is it just like better ergonomics and that you can manage it on the go? What's the benefit you feel of using something like Symphony?

• 18:18Speaker 01

  I think it's definitely... I don't know about the getting more done. I think, you know, in the limit, you get more done, but in practice, it's like you can't really like stay on top of like 100 new things a day. The thing that's really helpful is like having the full S3 of one task in one place. So because it has the original spec, it has the first workpad, it has the rework workpad. Every time you're like, how did things go wrong? You can kind of pinpoint where that was. And then you can use that to inform, you know, your agent's MD in the future, like the Symphony workflow that MP. Versus if you're just using Kodak's, it's kind of, it's really hard to search through conversations, you know? And so everything is like, how do you shape the context? You know, like Symphony is just a way to shape the context.

• 19:03Speaker 01

  It's not, it's not giving you any new capability that you wouldn't have by using the coding agents directly. It's just helping you wield it.

• 19:10Claire Vo?

  I love that. So, okay, you have shown us how you're doing sort of this orchestration of agents, or at least like workflow management of agents. Again, like, let's make this much more accessible for people. This is just a workflow to manage your agents, especially around coding. And you have another use case, which this one is the use case that I wanted to see. This other one is the use case that my nine-year-old wants to see. So, let's do our Pokémon card by AI use case.

• 19:40Speaker 01

  People think there are a lot of startups. There are way more Pokémon cards than there are ever gonna be startups to follow. So, one thing, the reason why I built this power buyer thing is for us to kind of keep track of, you know, inventory we want to buy and things like that.

• 19:56Claire Vo?

  Yep.

• 19:57Speaker 01

  So, I use Codex for two things. The first one is like getting the PSA certificates to keep track of like, you know, basically Pokémon cards, you can get them graded by PSA, and then there's kind of like a specific number for each grade. And that's available through an API, but you need one certificate number here to start from. There's obviously no way to just download that. So, what I have is like, you know, I have Codex, Pursugal, fill out the certificate number for every card that costs more than $1,000. So, I give it browser access, for example, here, and it's just, you know, going on on the internet and it's looking at things and it's like downloading the images, it's extracting the

• 20:39Speaker 01

  number from it, and then what you can then do is like, you know, use the eBay PSA premium on it. Let's find some underpriced cards from our list.

• 20:53Claire Vo?

  Okay, so that's, is that a skill?

• 20:55Speaker 01

  Yes. The skill is basically telling you how to figure out which cards are worth looking for. And then it just says how to batch them, you know? So, just do five per batch. You don't want to get like, you know, captured by eBay or stuff like that. And then there's also things, for example, there's different grading companies. So, you might have, you know, a PSA 10 is the same as, like a PSA 9 is the same as like a BGS or CGC 10. And so, all these different rules you might want to, you might want to have in there. And so, here, just, you know, through the APIs, looking up. From our power, buy your software, the cars that we want to look at.

• 21:37Speaker 01

  Um, and then it's using the in-app browser for for eBay. Let's see if I can open it here. So now it's going here and it's like looking at just searching some of the, and these are all like, you know, ten, twenty, fifty thousand dollar cards. Like you don't really do this for um five dollars. And so now it kind of goes in here and you know, you'll see it then um tell us, you know, this card is underpriced or uh this is hard, this card is, you know, we're buying right now. And yeah, this is like, you know, uh a a good example of like, you can build anything. But then at some point, you gotta have some business outcome or like some way to make money with the software that you built.

• 22:20Speaker 01

  Um, and trading cards is actually a great example of like, the more money you can put to work, the more money you can make because it's like an inventory-based business. So you can only make as much as you can tell. Um, and so having this to help us um automatically looking for some of these like higher value cars, for example, is like super useful. Um, and then the next thing, you know, I'm working on is um, and this is, I guess, getting in the weeds of the business, but uh when you go to like all these trade shows, you might have, people might see them on kind of like Instagram reels or whatnot, uh where people are coming to you, they're selling you cars and you gotta price them in real time. The whole process is like super inefficient because people are like searching each car manually,

• 23:02Speaker 01

  like on eBay or like TCG player, getting the number, blah, blah, blah. Um, and so you're actually losing a lot of money. Uh, so when people talk about um, you know, AI response time, I think for these long-running tasks, it's actually not that useful, but you can actually use AI to save clock time for real people by doing these things autonomously. Um, so yeah, it's just been fun to try and apply it outside of like, hey, I'm building the tool for you to build the tool to build the tool so that hopefully somebody down the line does something that is worth it for someone to use. Um, so yeah, for example, we got this amplifier right here.

• 23:43Speaker 01

  Let's see, I guess it broke the link, see, even the, it happens to the best of them. This is something actually, it's funny. People talk about software automation, but Codex has this kind of like the dollar sign. It's like tied to skills. So sometimes when you're like linking with the dollar on the thing, it pre fills it to a skill. So right now, right now it's looking for a skill.

• 24:05Claire Vo?

  Instead of a URL.

• 24:06Speaker 01

  You see like TCG power buyer, HTTPS. Yeah, so yeah, that's a good, that's a good example of like, you know, even these small things in software are sometimes broken.

• 24:16Claire Vo?

  Yeah.

• 24:17Speaker 01

  But yeah, just, this is overall one trend where it's like, there are a lot of businesses that are based on kind of like

• 24:27Speaker 01

  highly heterogeneous data that have been impossible to scale with software. Because before you have kind of like something as malleable as an LLM that can go through these things, it's really hard to use even like text or image classification for these things. And so, yeah, I think you're gonna see a lot more of, of these businesses. Like, I think the same, I, I forget who it was, but the same thing is happening with like vintage clothing, for example. Some people are doing something similar for, for desktop. Because again, you see it all the time, right? Oh my God, I went to Goodwill and I saw this, I don't know, Prada bag that was like in the Goodwill tank. And this has always been kind of like a mismatch between like human bandwidth

• 25:11Speaker 01

  and like the information that is coming from them.

• 25:14Claire Vo?

  This is my favorite one in that I, I think it enables what a very positive outcome of AI, which is small business creation. And I think, you know, this business of, clearly trading cards are a huge business. But no, what, what you're able to create this bigger business because you have the leverage of AI. And this is something that a human would have to manually do. And just the limits of time, space and human cognitive capacity means you're probably unable to capture as much of this business as you are today. I also think, I love this use case because it shows where AI helps you intersect the physical world in a really effective way. And an example.

• 25:56Claire Vo?

  Maybe I'll do a podcast on it is a couple of weeks ago, I had a rage out about how much is in my house and I, most of it is books. Most of what's in my house is piles of books. And so I placed a bet with my children and my husband. I said, how many books do you think we have in this house? And I went around with a camera and I took pictures of every, like every pile of books. There's books everywhere. And I had Gemini go through it. I think Gemini is like particularly good at this. And I had, we have 600 books in this house. It's like more, it's a hun- more than 100 books per person in this house. But I was able to catalog all these books, put them into categories, mark where they

• 26:39Claire Vo?

  physically are, find all the duplicates because, you know, I buy a book and my husband buy a book. And just the ability to like intersect the human world in a way that has been historically very inefficient has been a quality of life improvement for me with AI. And that's on a personal level, but I also think as a small business owner, it's, it's really important.

• 26:59Speaker 01

  Yeah, I think that's like the thing about AI that most people don't want to look at just because every previous technology was like, so like the economies of scale will help you get more leverage out of it versus even the software factories, right? At some point, even if you're like Salesforce, it's not like you can release 5,000 features a week. There's some limit to which you can get leverage out of these models and specific tasks versus, you know, my dad, their business back in, I grew up in Rome, they deliver fish to restaurants and they got like this freezer with the frozen stuff and they have the fresh fish. And it's kind of like somebody's going out there with like the pen and paper every morning, kind of like writing down what's there. Sometimes they're like, oh my

• 27:40Speaker 01

  God, we're missing like three tuna. So like we're missing a box of shrimp. And all of that work now can easily be automated, you know, even with just with the Meta glasses or something else. And so you're kind of helping actually, even at a small scale, you can get a lot of leverage out of it. And yeah, I was, you know, I went for the first time to Japan last fall. And I think that's a good example of like most things there. Kind of like smaller businesses that two, three people run and they're very happy to do it. And I hopefully we see a lot more of that in the in the US too.

• 28:15Claire Vo?

  Yep. Well, that's that's the life that I live. I'm very, I'm very happy to be a small business of one, one and a half people and a bunch of agents. Well, this has been awesome. I really appreciate you showing us the range of, you know, coding all the way to sort of more like physical or inventory based. AI will do a quick lightning round question and then we will get you out of here. You know, my first question is, what are you excited about that you think most people aren't doing with AI? That you are either starting to do, or you think people will start to do in the next couple of months?

• 28:48Speaker 01

  For me, recently has been personal finances. I mean, chat G P T just added the connectors for for all your accounts. We just sold our house and so I was like, what should I do with the money? And it's actually pretty good because it keeps you on track. I think for me in the past, the thing has been like, I don't want to like re-figure out what am I doing right now, where I have invested my money, should invest somewhere else. It's the SpaceX thing, real blah, blah, blah. I think having AI is kind of like an offloading thing. Because in the past, sometimes people are like, I'm looking to make sure I'm not fucking it up. You know, it's not like I'm actually adding a lot to it. I'm just kind of stressed. I'm gonna mess it up.

• 29:32Speaker 01

  And so if you can have AI be the safety net, it kind of frees you from a lot of things. I do the same, like, I was using this thing called Wafer, which is like a weekly unlimited tokens on the open source models. They just shut it down sadly. But I was having to read my Gmail every five minutes. And I was like, just read, is there any email I should actually respond or look at? Before I was always like, oh, maybe I'm missing something. I should like check my inbox, blah, blah, blah. Now I know 100% that if something important comes in, I'll know about it. And that kind of removes a lot of stress from it. So it kind of being this kind of like context offloading. I think people should do more of that.

• 30:10Claire Vo?

  I I completely, completely agree. Okay. My second question, because we were talking about books and I'm going to make you laugh, which is I'm going to turn off portrait mode. We have, we have this new book. Look at us.

• 30:24Claire Vo?

  Yeah.

• 30:25Speaker 01

  Yeah, yeah.

• 30:25Claire Vo?

  I mean, we have, I, I think we have a lot of the same books, you know, we're very, very typical.

• 30:31Speaker 01

  Or a farming, you know, with my page markers.

• 30:34Claire Vo?

  Love that. What's a book that you always recommend to people?

• 30:38Speaker 01

  Oh, what's a book? I, I think it depends. I feel like in different times of your life, you need different books. Uh, one thing I actually always recommend is called The Monk and the Riddle, um, which is kind of like, based on startups and venture capital, but uh, it's basically this VC meeting with this founder and the founder is like, I'm gonna do this startup for like funeral homes. And I don't really like funeral homes, but it nick it's a big market. And then once I sell the company, I'll be able to do what I like.

• 31:06Speaker 01

  And the VC is kind of like, well, why don't you just do what you like now? And it's like, well, I don't know. It's kind of risky. It's like, I'd rather just do this thing that is like big and like, then I'll do what I like. And I think I see it a lot in founders where it's like, I should do the thing that people want me to do versus like doing the thing you're passionate about. I think that's, that's one that I always recommend to people. It's, it's very short. Um, people like it.

• 31:30Speaker 01

  Outside of that, yeah, I don't, I, I mean, Divine Comedy by Dante. Honestly, like I grew up in Italy and in Italy for three years, you have to study the Divine Comedy. The one year, uh, you know, Inferno, Purgatory, Heaven. It's just a reminder of like, how great the human mind can be, like, you know, in the, in the middle of the 1200s.

• 31:54Claire Vo?

  Yep. Okay. We're gonna do, we're gonna do a behind the scenes, how AI, my son, Henry is over here in the corner, listening to the podcast. Henry, just say really loudly, are we making you learn about Dante's Inferno as well? Dante's Inferno, I told you about going to H E double L, hell.

• 32:15Claire Vo?

  You don't remember? Yeah. Yeah, I'm teaching you about that? Yeah. And the stuff that you know, I also, quick aside, are you an AS Roma fan?

• 32:25Speaker 01

  Of course.

• 32:26Claire Vo?

  We're, we're, we're a, we're a Roma family.

• 32:32Speaker 01

  I only do this so that I can buy one in the future.

• 32:35Claire Vo?

  My six-year-old is like, three days out of the week, wearing a Roma kit. He's got like, three different ones. Um, so my, my husband and my boys are Italian citizens. I am not, but they are.

• 32:47Speaker 01

  Nice. No, I ju- I literally swear to God, I just reached out to like, the president of Roma. Like, last week, I was like, hey, I can do, anything I can do to help you use AI and be a better club, I'll do it.

• 33:00Claire Vo?

  Oh my gosh.

• 33:00Speaker 01

  I'll be, I'll come out there.

• 33:02Claire Vo?

  Put us in too. My husband and I will sign up for the AS Roma AI transformation workshop. I love it. Okay. Uh, my last lightning round question, which is, when you're prompting and AI is going off the rails, what's your strategy? What do you do?

• 33:20Speaker 01

  Oh, man, it's hard. Uh, so after, I swear that a couple of times, uh, I usually, so one, like, you know, I have the subscription to all the providers, so maybe I'll just try another one. Yeah, restarting conversations, I think that's obviously like, a great example, kind of like tweaking the prompt to put things in there. Try and break down the problem in smaller pieces, maybe. Um, that's been another one. You know, sometimes you're being too ambitious. I think that's great. I think in general, if you're not getting enough failures, you're probably not trying hard enough. You know, you're not being ambitious enough on what you're doing. Yeah. And then, yeah, try, remember to be, that's why sometimes I use, I usually like,

• 34:00Speaker 01

  start and I type something, and then once I get frustrated, I go back and I just like, use speech to text.

• 34:06Claire Vo?

  Yep.

• 34:06Speaker 01

  Longer prompt.

• 34:07Claire Vo?

  Yep.

• 34:08Speaker 01

  I'm like, alright, I can't, I can't like, keep typing these things. Uh, that helps sometimes because like, once it starts talking, you maybe just add a few more details that help.

• 34:17Claire Vo?

  Yep.

• 34:17Speaker 01

  Um, but I think it really depends on, on the task, sometimes.

• 34:21Claire Vo?

  My, my friend Hillary came on the podcast, she's actually been on twice, very popular guest. She calls it the Yappers API, which is, she, she just goes, you just go like this, until you've gotten it all out and you press enter, you don't even look at it, and that is usually the most, the most effective thing. Well, this has been super fun. Thank you so much for joining. Where can we find you and how can we be helpful?

• 34:43Speaker 01

  I'm on Twitter at FanaHova, F A N A H O V A. And then, yeah, you can subscribe to the Late in Space podcast. What else? Well, I also run a space and a staff called Kernel. So if you want to come work from here, we have an open coworking. We do like fifteen, twenty events every month. We just did a Matt Pelakis class yesterday with somebody from OpenAI as the teacher. So yeah, just come and say hi. Yeah, and if you're building anything interesting in this kind of like, you know, software factory space, I'm always happy to chat.

• 35:14Claire Vo?

  And remind us where the store is.

• 35:17Speaker 01

  San Carlos, called Merlin Games.

• 35:19Claire Vo?

  Okay, we got it all. Thank you so much for joining How I AI.

• 35:24Speaker 01

  Thank you.

• 35:26Claire Vo?

  Thanks so much for watching. If you enjoyed this show, please like and subscribe here on YouTube, or even better, leave us a comment with your thoughts. You can also find this podcast on Apple Podcasts, Spotify, or your favorite podcast app. Please consider leaving us a rating and review, which will help others find the show. You can see all our episodes and learn more about the show at howiaipod.com. See you next time.