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

**Claire Vo** (0:00)
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.

**Alessio Fanelli** (0:12)
My dad, their business, they deliver fish to restaurants. They got this freezer with the frozen stuff, and somebody's going out there with the pen and paper every morning, writing down what's there. Sometimes they're like, oh my God, we're missing three tuna, we're missing a box of shrimp. All of that work now can easily be automated, even just with the Meta glasses.

**Claire Vo** (0:31)
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.

**Alessio Fanelli** (0:40)
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 street shows, people are coming to you, they're selling you cars, and you got to price them in real time. That whole process is super inefficient because people are like searching each card manually, like on eBay or like TCGplayer, getting the number. You can actually use AI to save clock time for real people by doing these things autonomously.

**Claire Vo** (1:10)
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 Fanelli, founder of Kernel Labs and co-host of the Latent Space Podcast. He's going to show us how he uses OpenAI 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. Firecrawl is a web data API that lets agents search, scrape and interact with the web at scale, and get that clean structure 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 HOWIAI to get 10,000 free credits today.
I'm excited about what you're gonna show us because I think we have heard a lot of people talk about orchestrating many agents autonomously across a project. 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 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 Fanelli** (2:52)
I started this podcast called Latent 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 in the last year, and I think everybody feels the same.
What really clicked for me was starting to move away from being an agent prompter to be an agent manager, and that has taken a lot of different ways. The first thing that everybody tried was the Kanban board. You would 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. It was easy to get to the task and kick it off, but then it was hard to intervene on it. And also having it local just didn't quite work. So the big thing for me was moving away from local runtime to having it in a VPS in the cloud and then having different channels to talk it to. So you can text the agents. You can use linear to talk to them. You can prompt them directly in the shell. And this is also something, I guess, in the last month, Codex also added, Codex Mobile, Cloud is also adding the mobile management. But I'll run you through what I do and then maybe people get some inspiration from it.

**Claire Vo** (4:15)
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 kick them alive every now and then.