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

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

July 6, 2026 · 36 min

About this episode

Alessio Fanelli discusses autonomous coding agents and AI workflows using OpenAI Symphony and Linear.

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 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…

Sponsors

Firecrawl, Jira Product Discovery

More episodes of How I AI

Explore listener stats, chart rankings, contacts and more on the How I AI podcast page.