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

> Source: <https://www.lennysnewsletter.com/p/how-i-run-autonomous-coding-agents>
> Published: 2026-07-06 12:03:37+00:00

**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.

**Listen or watch on YouTube, Spotify, or Apple Podcasts**

### 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 unlocks

How to wire Symphony and Linear together as an agent state machine

How to track token costs per task (and what 221 million tokens buys you)

What Glimpse does, and why better agent senses extend autonomous runs

Why your CLAUDE.md probably needs a full purge, not more instructions

How Codex scouts underpriced $10K Pokémon cards on eBay at scale

The new category of small business that AI just made possible

### Brought to you by:

** Firecrawl**—Power AI agents with clean web data

** Jira Product Discovery**—Prioritize with insights, build with confidence

### In this episode, we cover:

([00:00](https://www.youtube.com/watch?v=KtmaWUVdnx4)) Intro

([02:24](https://www.youtube.com/watch?v=KtmaWUVdnx4&t=144s)) Prompter vs. agent manager

([04:31](https://www.youtube.com/watch?v=KtmaWUVdnx4&t=271s)) Live demo: Symphony + Linear

([09:31](https://www.youtube.com/watch?v=KtmaWUVdnx4&t=571s)) Setting up Symphony

([14:15](https://www.youtube.com/watch?v=KtmaWUVdnx4&t=855s)) Purging your skills files

([18:06](https://www.youtube.com/watch?v=KtmaWUVdnx4&t=1086s)) The benefits of this system

([19:10](https://www.youtube.com/watch?v=KtmaWUVdnx4&t=1150s)) Demo: Using Codex to hunt for Pokémon cards

([24:17](https://www.youtube.com/watch?v=KtmaWUVdnx4&t=1457s)) The benefit of AI for small businesses

([28:23](https://www.youtube.com/watch?v=KtmaWUVdnx4&t=1703s)) Lightning round

### Tools referenced:

• OpenAI Codex: [https://openai.com/codex](https://openai.com/codex)

• OpenAI Symphony (open-source framework): [https://github.com/openai/symphony](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](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](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](https://www.amazon.com/dp/0451208633)

• AS Roma (football club Alessio and Claire are both fans of): [https://www.asroma.com/en](https://www.asroma.com/en)

### Where to find Alessio Fanelli:

Latent Space podcast: [https://www.latent.space/](https://www.latent.space/)

### Where to find Claire Vo:

ChatPRD: [https://www.chatprd.ai/](https://www.chatprd.ai/)

Website: [https://clairevo.com/](https://clairevo.com/)

LinkedIn: [https://www.linkedin.com/in/clairevo/](https://www.linkedin.com/in/clairevo/)

Production and marketing by [https://penname.co/](https://penname.co/). For inquiries about sponsoring the podcast, email [[email protected]](/cdn-cgi/l/email-protection).
