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

More from How I AI

1. 

   13 Jul 2026 · 36 min

   This solo builder runs 24/7 local AI on his own hardware | Alex Finn

   Alex Finn is an AI builder, YouTuber, and the creator of Vibe Code Academy, a community for people learning to build with AI tools. He runs one of the most ambitious local AI setups I’ve come across: three Mac Studio 512 GB machines, a DGX Spark, and a custom RTX 5090 build, all coordinated through a fleet dashboard he built himself. He’s spent five months figuring out which local models belong on which machines, how to wire them to Claude Code loops, and how to get a software factory running without babysitting it. What you’ll learn: How Alex chose between a Mac Studio (512 GB unified…

2. 

   9 Jul 2026 · 37 min

   GPT-5.6 Sol vs. Claude Fable: Why OpenAI’s new model crushes my benchmark

   GPT-5.6 Sol is back, and I ran it through my full How I AI vibe benchmark against GPT-5.6 Terra, Luna, Claude Fable 5, and Sonnet 5 across five categories: PRDs, prototypes, wireframes, debugging, and agentic voice. Sol won by a meaningful margin on my Claire Weighted Index (70% my taste, 30% Terminal Bench 2.1), and I also tested two use cases I can't stop thinking about: building a gamified homework tracking app for my kids in one shot with Codex, and browser automation with Chrome that burned through 500 LinkedIn replies while I did literally nothing. What you’ll learn: How I scored five…

3. 

   8 Jul 2026 · 25 min

   What a harness is and how to build one with Claude Agent SDK

   Everybody is saying, “It’s not the model, it’s the harness,” but almost nobody stops to explain what a harness actually is. So I did. I built one live on the show: a Sentry bug-debugging harness for my company ChatPRD, using the Claude Agent SDK, a custom terminal UI built with the Ink library, and opinionated adapters for Sentry, Linear, GitHub, and Vercel. The harness handles evidence gathering, root-cause analysis, and follow-up artifact creation, all without me needing to type “dear agent, please fix this bug” ever again. I also walk through the architecture, share the code structure,…

4. 

   30 Jun 2026 · 26 min

   Sonnet 5 review: I ran 64 generations to find out if it's worth it

   I’ve been testing every major frontier model release since the start of the year, and when Anthropic dropped Sonnet 5, I wanted more than a vibe check. I got tired of one-off tests I couldn’t repeat or compare over time, so I built something better: the How I AI Bench, a repeatable eval harness I constructed live using Claude Code while recording this episode. I ran Sonnet 5 blind against four other frontier models (Sonnet 4.6, Opus 4.8, GPT-5.5, and Gemini 3 Pro) across PRD quality, prototype generation, agentic task completion, and agent personality. The results were not what I expected.…

5. 

   29 Jun 2026 · 52 min

   No Figma. No Jira. No docs. How Gusto built a new product line with Claude Code | Eddie Kim (CTO)

   Eddie Kim is the co-founder and CTO of the payroll and HR platform Gusto, which just crossed $1 billion in revenue and serves more than 500,000 small businesses. Recently he did something most CTOs don’t: he went back to writing code. With three other engineers and one designer, Eddie built Gusto Cofounder, a net-new AI product, from zero code to a tier-one launch in 10 weeks. He walks through how that team actually worked, why they threw out nearly every process, and how anyone can copy the approach. What you’ll learn: The trash-can method: how to write, review, and delete a full PR as a…

6. 

   24 Jun 2026 · 27 min

   GLM 5.2: why I’m replacing Opus in Claude Code with this new model

   I put GLM 5.2, the open-weight coding model from Z.AI, through four real tasks inside my actual codebase: a codebase architecture audit, a UI redesign, and a 45-minute autonomous bug-hunting session pulling from Sentry and Vercel logs. Total cost: $3.36 for roughly 6 million tokens, a prioritized bug-fix dashboard I’m actually shipping from, and a landing page redesign that matched Chat PRD’s design system on the first try. What you’ll learn: What “open-weight” actually means and why it matters for cost and vendor independence How to connect GLM 5.2 to Cursor and Claude Code How it performs…

7. 

   5 Oct 2026 · 36 min

   How OpenAI uses ChatGPT Sites (live at DevDay!) | Kath Korevec (Product Lead)

   Kath Korevec is a member of the Product staff at OpenAI working on Codex, and she spent over a year building and using ChatGPT Sites internally before its public launch. She’s been on the front lines of shipping Plugin Insights, MCP plugin hosting, and the connector ecosystem, which now includes around 60 integrations. What you’ll learn: What Plugin Insights actually does, and why it changes who can use a site The incident command site Kath built for her OpenAI team, and how it uses live Slack and Notion connectors The one phrase that tells Codex to wire up connectors for you The…

8. 

   30 Sep 2026 · 46 min

   Jev: 8 real use cases for the fastest, cheapest model I’ve ever used | John Lindquist

   John Lindquist created egghead.io, a developer education platform used by hundreds of thousands of working engineers. These days he’s building mega.dev, a hands-on program specifically for developers who want to do real work with AI agents, not just prototype them. What you’ll learn: Why Jev is a decision engine, not a chatbot, and what that distinction actually changes about how you build How John built a real-time voice to-do app that classifies and executes commands with no visible pause The data deduplication pattern that merges messy records in milliseconds using confidence scores Why…

9. 

   30 Sep 2026 · 24 min

   OpenAI Dev Day 2026: The releases that actually matter

   I spent the day at OpenAI’s DevDay in San Francisco, and I have good news and bad news: OpenAI released a lot of stuff. In this episode, I break down the announcements worth paying attention to - and show you what happened when I tested some of them early. We’ll meet my Dot, explore why Spaces and Sites could matter for how teams work, and get into the model and API updates I’m most excited about as a developer. I use the Decisions API to find podcast thumbnails where nobody looks awkward, build a collaborative sketchpad with Astra ultrafast, and let my kids redesign a 3D world in real time.…

10. 

    28 Sep 2026 · 26 min

    Jev for beginners: how to use it and what to build

    Jev is TypeSafe AI’s new decision model. It returns type-safe structured values (a choice, a score, a probability) instead of generated text, at 4 cents per million input tokens with no output charge. This week I ran it on five real projects: PR categorization, a meta-analysis of my own Claude and Codex sessions, Gmail triage, the ChatPRD product insights graph, and a live audience dashboard built from 4,500 YouTube comments. What you’ll learn: What makes Jev fundamentally different from every other model I’ve used How I analyzed 1,700 PRs for 9 cents and what I found out about where my…

Every episode of How I AI →