Claire Vo: This is my favorite positive outcome of AI, which is small business creation. 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.

Alessio Finelli: You know, my dad, their business, they deliver fish to restaurants. They got like this freezer with the frozen stuff and like some fresh fish 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 tunas or like we're missing a box of shrimp." All of that work now can easily be automated even with just with the magic glasses or something else.

Claire Vo: And we have another use case, which is the use case that my 9-year-old wants to see. So, let's do our Pokémon card by AI use case.

Alessio Finelli: 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 cards, and you got to price them in real time. The whole process is super inefficient because people are like searching each card manually like on eBay or like this DJ player getting the number. You can actually use AI to save clock time for real people by doing these things autonomously.

Claire Vo: Welcome back to How I AI. I'm Claire Vo, 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 Latent 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 Pokémon 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. 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 for data and start powering your AI agents and apps with Firecrawl at firecrawl.dev. Use code how I AI 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. I still see a lot of prompting, even if you're prompting into a loop or a goal or something that spawns sub agents. People are really 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.

Alessio Finelli: I started this podcast called Latent Space 3 and 1/2 years ago and my co-host works here. He 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 tasks. Um they definitely changed, you know, in the 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 a agent prompter to kind of be a agent manager. And that has kind of taken a lot of different ways. So, the first thing that everybody tried was kind of like the Kanban board. Uh you would kind of put all these things in there and move them back and forth. What I found is that it was hard to get two, three, four turns through that. 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 um 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 that I guess like in the last month, you know, Codex also added Codex mobile cloud is also adding kind of like the the mobile management, but I'll kind of run you through what I do. And then maybe people get some inspiration from it.

Claire 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.

Alessio Finelli: Right.

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

Alessio Finelli: Yeah. So, I tried to use some more fun examples for it than like the meta one. So, I own a car store in San Carlos called Merlin Games. And so, one of my interest is trading cards. So, my setup is I have this thing called Zoo. Zoo is basically like an agent plus a VPS. So, this machine, for example, is like, you know, 32 gig of RAM, four cores. 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 a I mean, you can kind of look it up for a better description, 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 power buyer, for example. And I work on it sometimes in through Symphony, sometimes I work on it through Codex directly or clock code 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've 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. So, the agent kind of makes a plan on how to implement it. And it has a plan, it has a acceptance criteria, different validations. And Symphony has a file called workflow.md, where you basically explain how what what it should do for this. Uh this will kind of go to work and then eventually we'll move it to human review. So, what you can do here is review it on GitHub, and you can add Let me open the PR. I'll show you. You can add all these different comments, you know, I guess now

Claire Vo: They're resolved.

Alessio Finelli: 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. And 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. I say clean up bring me stable. Let's remove the spread column. It's too noisy. Let's also make the set name clickable. So, I look at that other cards. And here I'll simply put it in to do. Create issue. And then each of these Symphonies has its own dashboard on it. So, this one is TCG bar buyer. These are previous tasks that are running. So, one of the things I'm also trying to do is trying to figure out how much is software going to cost to build. So, I think people understand the idea of like the agents write it, but sometimes it's hard ahead of time to know how many tokens it's going to take and so it's hard to price and understand what it's actually worth doing. So, as you can see most of these tasks are kind of like, you know, 15, 30, 60, but then this one is like 221 million tokens.

Alessio Finelli: And so you can kind of go back here and be like, okay, this task was how to make a deployable on Vercel. So, you know, this whole thing was just not working. It was originally built. It's kind of like a local thing. So, I had to like, you know, rewrite the storage, kind of like, you know, change all the request or handle, blah blah blah. So, this is like quite a big task. So, it kind of makes sense that it cost a lot of tokens. Um 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 is it just kind of went live. So, here you can kind of see, uh 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. Um maybe once they give us stable five back, um that'll be good enough. Um And 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. But I could be doing this here. I could be doing this on my phone. I could be doing this anywhere, really. Um and to kind of put it to the extreme I had um let me see if I I find it. Um I created this project called Pi Q, which was basically like putting your repo plus the Pi 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 of like request for prompt instead of like request for pull requests. Everything is just how do you transfer context between people?

Claire 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 of one of your code bases, you can integrate that with Zoe 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, 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 you 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?

Alessio Finelli: Yeah, I took the Elixir implementation. They're really like the core things to change are like the workflow that I'm doing 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 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 hardness you know it's pretty straightforward. I think like the reality is like how do you build tools for it to be more effective and that's kind of like one of the main things also kernel lives have been working on. So we built this other thing called glimpse which is a kind of like a playwright extension that coding agents can use to take screenshots to do visual diffs between screenshots take videos and so it's almost like how do you like 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 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 a 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.

Claire 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 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 and sort of the software development life cycle. Like it's very long, it's very detailed, but it's literally just a markdown file and I think people kind of over engineer at at first what these things can be and ultimately the power of LLMs, especially these newer models is you can 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.

Alessio Finelli: Yeah, I think everybody just wants to have the magic skills file that does everything for them and like the magic MD that solves their 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 added and in every agent MD I was like, you have to use the work tree manager. And now sometimes I forget ahead in some projects and then I start a task and it's like reinstall I'm like, you don't need anymore. But like because I had a deadline every time it's not doing that. 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 of that 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 tree manager, instead of removing that line, it's going to add a line to say "But, 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. It's got the workspaces for each task. It's got logs, which include the token usage. And it's got got the state um 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 got to keep in mind. And then you kind of let the model work. Um 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 already registered here." 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. You know, those are like all examples of like, if you just let the models kind of do their own things, then you just end up with this like very weird things.

Claire Vo: Okay, so red diff your skills and red diff your markdown files and get some stuff

Alessio Finelli: Yeah, they're not out there. I feel like the create skill thing that the Codex app, for example, added, I think it's like a great idea, but it didn't for a lot of people, it just puts them in a lot of trouble because it's like they're 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 um themselves a disservice a lot of time.

Claire 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 road map'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 road map 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, 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?

Alessio Finelli: Um I think it's definitely I I don't know about the getting more done. I think it 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. Uh the thing that's really helpful is like having the full history of one task in one place.

Claire Vo: Yep.

Alessio Finelli: So, because it has the original spec, it has the first work pad, it has the rework work pad, 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 agents MD in the future like the Symphony workflow that MD versus if you're just using code X, it's kind of it's really hard to search through conversations, you know? Um and so everything is like, "How do you shape the context?" You know? Like Symphony's just a way to shape the context. 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.

Claire Vo: I I I love that. So, okay, you you've shown us how you're doing sort of this orchestration of 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 your your agents, especially around coding. And we have another use case, which this one was the use case that I wanted to see. This other one is the use case that my 9-year-old wants to see. So, let's do our Pokémon card by AI use case.

Alessio Finelli: People think there are a lot of startups. There are way more Pokémon cards than there are ever going to be startups to follow. Um 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. Um 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 so you can get them graded by PSA. Um 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. Um there's obviously no way to just download that. So, what I have is like, you know, I have Codex pursue goal, 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 just, you know, going on on the internet and it's looking at things and it's like downloading the images. And it's extracting the number from it. And then, what you can then do is like, you know, use the eBay PSA premium hunt. Let's find some underpriced cards from our you know, list.

Claire Vo: Okay, so that's Is that a skill?

Alessio Finelli: Yes. The 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 You don't want to get like, you know, captured by eBay or stuff like that.

Claire Vo: [laughter]

Alessio Finelli: Um and then there's also things, for example, there's different grading companies. So, you might have, uh you know, a PSA 10 is the same as like a PSA 9 is the same as like a um BGS or CGC 10. Uh and so all these different rules you might want to you might want to have in there. Um and so here just, you know, through the APIs looking on from our power buyers after the cards that we want to look at. 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, 10, 20, 50, $1,000 cards. Like, you don't really do this for um $5. Um 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 card this card this card is, you know, worth buying right now. Um and yeah, this is like, you know, uh a a good example of like you can build anything, but then at some point you got to have some business outcome or like some way to make money with the software that you built. 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 sell. Um and so having this to help us um automate looking for some of these like higher value cards, for example, is like super useful.

Alessio Finelli: 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 the kind of like Instagram Reels or whatnot. Uh where people are coming to you, they're selling you cards, and you got to price them in real time. That whole process is like super inefficient because people are like searching each card manually like on eBay or like TCGPlayer, 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 the for someone to use." Um so yeah, for example, we got this amplifier right here. Let's see. I guess it broke the link. See? Even the internet bends to the best of them. This is something actually, it's funny. People talk about software automation, but um Code X 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

Claire Vo: instead of a URL.

Alessio Finelli: You see like TCGPlayer, HTTP, so um yeah. That's a good That's a good example of like, you know, even these small things in software are sometimes broken.

Claire Vo: Yeah.

Alessio Finelli: Um but yeah, just um this is overall one trend where it's like there are a lot of businesses that are based on kind of like um highly heterogeneous data um 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. Um and so yeah, I think you're going to 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. Um some people are doing something similar for for desk stuff. Um 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 good in the Goodwill thing, and um this has always been kind of like a mismatch between like human bandwidth and like the information that is coming from them.

Claire 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 uh it clearly trading cards are 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, maybe I'll do a podcast on it, is a couple weeks ago I had a rage out about how much is in my house, and I I and 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 cuz Gemini's 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 physically are, find all the duplicates because, you know, I buy a book and then my husband buy a book, and 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 that's it's really important.

Alessio Finelli: 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 is not that you can release 5,000 features a week. There's some limit to which you can get leverage out of these models in 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 over with the frozen stuff and they have the fresh fish and 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 god, we're missing like three tuna." So they're like, "We're missing a box of shrimp." Uh and all of that work now can easily be automated, you know, even with just with the meta glasses or something else. Um and so you're kind of helping actually even at a small scale you can get a lot of leverage out of it. Um and yeah, I was you know, went for the first time to Japan last fall. Uh and I think that's uh a good example of like most things there kind of like smaller businesses that two or three people run. And they're very happy to do it. Um and I hopefully we see a lot more of that in the in the US, too.

Claire Vo: Yeah, 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. We'll do quick lightning round question and then we will get you out of here. Um 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 months?

Alessio Finelli: For me recently has been personal finances. Um I I mean ChatGPT just added the connectors for for all your accounts. Um we just sold our house and so I was like, what should I do with the money? Um and it it's actually pretty good because it keeps you on track. I think for me in the past I think has been like I don't want to like refigure out what am I doing right now, where do I have invested my money, should I invest somewhere else, is the SpaceX thing real, blah blah blah. Um I think having AI is kind of like a offloading thing. Um because in the past sometimes people are like I'm looking to make sure I'm not [__] it up. You know, it's not like I'm actually adding a lot to it. I'm just kind of stressed I'm going to mess it up. And so if you can have AI be that 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 suddenly. Uh but I was having it read my Gmail every 5 minutes. And I was like, just read is there any email I should actually respond or look at? Um 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. Um I think people should do more of that.

Claire 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 the same book. Look at us.

Alessio Finelli: The

Claire Vo: Yeah. Yeah, I got it. I mean we have I I think we have a lot of the same books, you know, we're very very similar. Bigger or a farmer, you know, with my page of marketers. Love that. So what's a book that you always recommend to people?

Alessio Finelli: Oh, what's a book I I think it depends. I feel like in different times of your life you need different books. 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 is basically this VC meeting with this founder and the founder is like, "I'm going to do this startup for like funeral homes." And I don't really like funeral homes, but I think it's a big market. And then once I sell the company, I'll be able to do what I like. Um and the VC is kind of like, "Well, why don't you just do what you like now?" And so he said, "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. Um I think that's that's one that I always recommend to people. It's It's very short. Um people like it. Um Outside of that, yeah, I don't I I mean the Divine Comedy by Dante. I would say like I grew up in Italy and in Italy for 3 years you have to study the Divine Comedy. Do one year, uh you know, Inferno, Purgatory, Heaven. Um 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. Um

Claire Vo: Yeah. Okay, we're going to do we're going to do a behind the scenes how AI um 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. You don't remember? Yeah. Yeah. Yeah, I'm teaching you about that. Yeah. And the seven deadly sins. You know, I also quick aside, are you an AS Roma fan?

Alessio Finelli: Of course.

Claire Vo: Oh, we're we're we're a we're Roma family.

Alessio Finelli: I only do this so that I can buy you one in the future.

Claire Vo: My 6-year-old is like 3 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.

Alessio Finelli: Nice. No, I I literally swear to god, I just reached out to like the president of Roma like last week. I was like, "Hey, I'm I can do anything I can do to help you use AI and be a better club, I'll do it. I'll be I'll come out there."

Claire Vo: Put us into My husband and I will sign up for the AS Roma AI transformation work.

Alessio Finelli: Perfect.

Claire Vo: I love it. Okay, uh my last lightning round question, which is when you're prompting and AI's going off the rails, what's your strategy? What do you do?

Alessio Finelli: Oh, man, it's hard. So, after I swear at it a couple times, uh I usually So, one like, you know, I have this subscription to all the providers. So, I maybe I'll just try another one. Yeah, restarting conversations. I think that's obviously like a great example and 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 really the 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 in what you're doing. Yeah, and then yeah, try remember to be That's why sometimes I use I usually like start and I type something.

Claire Vo: Yeah.

Alessio Finelli: And then once I get frustrated, I go back and I just like use speech-to-text

Claire Vo: Yeah.

Alessio Finelli: for a longer prompt.

Claire Vo: Yep.

Alessio Finelli: I'm like, "All right, I can't I can't like keep typing these things." That helps sometimes because like once you start talking, you maybe just add a few more details that help.

Claire Vo: Yep. Um but I think it really depends on on the task sometimes. Yeah. My my friend Hillary came on the podcast. She's actually been on twice, very popular guest. She calls it the yapper's 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 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?

Alessio Finelli: I'm on Twitter at fanahova, f a n a h o v a, and then yeah, you can subscribe to the Leading Space podcast. Um What else? Well, I also run a space and a sub called Kernel. So, if you want to come work from here, we have a open co-working. We do like 15 20 events every month. We just did a mat Pilates class yesterday with somebody from Open AI as the teacher. Um so, yeah, just come hang, say hi. Um yeah, and if you're building anything interesting in this kind of like, you know, software factory space, I'm always happy to chat.

Claire Vo: And remind us where the the store is.

Alessio Finelli: Uh San Carlos, called Merlion Games.

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

Alessio Finelli: Bye-bye.

Claire Vo: Thank you. Thanks so much for watching. If you enjoyed the 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 howiaiipod.com. See you next time.