How I AI

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.

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.

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, and

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.

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.

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.

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.

Brian Grinstead is a distinguished engineer at Mozilla, where he’s worked on Firefox and the web platform since 2013 (he joined to help launch Firefox DevTools). Recently he and his team pointed an agentic bug-finding pipeline at Firefox—a codebase with tens of thousands of files and tens of millions of lines of code—and shipped a record month of security fixes. The viral chart everyone saw gave the credit to Anthropic’s new Mythos model. Brian’s take is that the harness and pipeline did just as much of the work, and he walks through exactly how it runs and how anyone can build a starter versi

In this episode, I sit down with Ankur Goyal , founder and CEO of Braintrust, the AI evals and observability platform used by teams like Notion, Stripe, Vercel, and Zapier. This one is for the senior engineers, staff engineers, VPs of engineering, and CTOs in my audience. We get into how coding agents can take on deeply technical architecture and infrastructure work that no single human engineer could tackle before, and then we demystify evals so you can use them to make your AI products better without touching the implementation. What you’ll learn: How Ankur uses Codex to run week-long benchm

In this 30-minute episode, I walk through my favorite feature in Codex: the /goal command. I show how Goals transform AI from a turn-based assistant that needs constant ‘what’s next?’ prompting into an autonomous agent that can work for hours on complex, multi-step tasks. I share three real examples: eliminating thousands of Sentry errors, cleaning 3,900 emails down to 68, and organizing hundreds of Linear tasks. What you’ll learn: What Goals are and how they differ from standard prompts How I used /goal to eliminate hundreds of error logs in my codebase over a five-hour autonomous run The non

Jason Levin is the CEO and founder of Memelord, an AI-powered meme creation platform that helps brands and individuals create contextual, trending memes. He started Memelord as a $6.90-per-month newsletter sending subscribers to a Google Slides deck, grew it to $100K ARR on Bubble without hiring engineers, then raised $3M to build it into an API-first product. What you’ll learn: How Jason grew Memelord from a $6.90/month newsletter to $100K ARR without writing a single line of code Why “no UX is the best UX” and how agents are becoming Memelord’s primary users The mandatory vibe-coding rule fo

Claire breaks down the biggest announcements from Anthropic’s “Code with Claude” event and what they actually mean for builders shipping AI products today. From scheduled AI routines to outcome-based agents, multi-agent orchestration, and new memory systems, Claire walks through the features she’s most excited to use immediately—and how they could reshape the future of agentic software. What you’ll learn: How Claude Code routines let you automate recurring workflows on schedules or webhooks What “Outcomes” are and how rubric-based agent grading works How multi-agent orchestration enables speci

Ryan Nystrom is a software engineer at Notion. He joined in December 2024 after Notion acquired Campsite, the team communication platform he co-founded with Brian Lovin. At Notion, he’s been a core builder of Notion AI and the Custom Agents feature launched in February 2026. He manages a team of six to seven engineers while still writing code himself, currently running Project Afterburner, a push to cut Notion’s CI time to a quarter of its current duration. What you’ll learn: How to build a Notion AI custom agent that auto-generates your daily standup pre-read by pulling from Slack, GitHub, Ho

Nicole Ruiz is a writer and parent who has built a comprehensive AI-powered shopping system to help her family buy high-quality, long-lasting items while avoiding the noise of drop-shipping brands, paid ads, and poorly made products. She writes an interview series on Substack about how technology is changing the household. What you’ll learn: How to build a Claude Project with custom instructions for vetting brands based on heritage, craftsmanship, and return policies The shopping criteria that help surface century-old manufacturers over trendy direct-to-consumer brands How to use Claude to sea

Today is day one of Google I/O 2026, and I walk through every major announcement live—from the new Gemini 3.5 model family to Anti-Gravity 2.0, Google AI Studio, Gemini’s consumer redesign, the Omni video model, Flow, Stitch, and Pomelli. I test them in real time and tell you exactly which ones delivered. What you’ll learn: How Gemini 3.5 Flash benchmarks against Claude and GPT models on speed and agentic coding tasks How Anti-Gravity 2.0’s new features (projects, scheduled tasks, subagents, slash commands) compare to Codex and Claude Code Why the /grill-me slash command could be a more aggres

Bryce Rattner Keithley has spent her career in talent and recruiting, working with technical leaders but never writing a line of code herself. Yet she managed to build Daily Hundred—a fitness app featuring custom AI-generated videos of anthropomorphic animals demonstrating exercises—and ship it to the App Store before her software engineer friends. Using Replit, Claude, Gemini, and a relentless beginner’s mindset, Bryce proves that in the AI era, execution is no longer the constraint on good ideas. What you’ll learn: How to build and ship an iPhone app using Replit without any coding knowledge

Claude Fable 5 is the first Mythos-class intelligence model to be generally available, and I got early access to test it before launch. In this episode, I walk through what Anthropic is promising, what actually stood out when I used it on real work, and where I think it fits in your AI stack. — In this episode, we cover: (00:00) Introduction: Fable 5 is finally here (00:31) What Anthropic says about the model (05:14) Token-intensive by design (06:28) Safety classifiers and the new fallback concept (07:46) Is this or is this not Mythos? (08:30) New product launches: Managed Agents and more (09:

John Kim is the co-founder and CEO of Delight.ai, a customer experience platform that’s transforming how companies deploy AI. But what makes John’s story fascinating isn’t just his product; it’s how he’s turned his entire company into an AI-native organization. His marketing team built a fully functional e-commerce swag store with Stripe integration in days. His sales team built their own CRM tools. His recruiting team automated their entire workflow. And it’s all tracked, measured, and celebrated through an internal platform called Automators. What you’ll learn: How Sendbird’s marketing team

In this mini episode, I break down OpenAI’s new GPT 5.5 and GPT 5.5 Pro after weeks of early testing. I walk through three real jobs I threw at the model: building an app for me to teach my second grader more advanced subtraction concepts, tackling a tech debt problem in the ChatPRD codebase, and hacking into a proprietary Bluetooth pixel display that every other model had failed me on. My verdict: higher intelligence, better efficiency, and genuinely autonomous long-running loops that change what I think is worth tackling. What you’ll learn: How I think about GPT 5.5 Pro’s pricing vs engineer

Felix Rieseberg is the engineering lead for Claude Cowork and Claude Code Desktop at Anthropic. He previously spent five years at Slack building developer tools. In this episode, Felix demonstrates how he uses Claude to solve real-life problems: analyzing floor plans to build interactive 3D house walkthroughs, automatically tracking promises he makes on Twitter, and building a $20 hardware device that physically approves Claude actions with a button press. What you’ll learn: How to use Claude Cowork to turn a 2D floor plan into an interactive 3D walkthrough where you can move furniture around

Thariq Shihipar is an engineer at Anthropic working on the Claude Code team. He’s spent the past several months experimenting with HTML as a replacement for Markdown in planning and implementation workflows, discovering that richer visual formats lead to better human engagement—and, ultimately, better products. In this episode, filmed at Anthropic’s Code with Claude event in San Francisco, Thariq demonstrates how to use HTML artifacts to create interactive plans, build throwaway UIs for specific problems, and maintain living design systems that travel with your codebase. What you’ll learn: Why

I got a few hours of early-access testing with Anthropic’s newly released model Opus 4.8. I walk through real coding, design, and strategy tasks across Claude Code and Claude Cowork, and give you my unfiltered view on what impressed me and what didn’t. — What you’ll learn: Where Opus 4.8 excels: greenfield prototypes, one-shot features, and fast execution Where it struggles: the last 10%, edge cases in existing codebases, and hallucinations How Opus 4.8 compares to Opus 4.7 on business strategy work Why I’m still reaching for Opus 4.7 on data-heavy strategy and roadmap work The new features sh

In this experimental episode, I document my real-time attempt to create an AI avatar of myself using Google Flow and the new Gemini Omni video generation model. I walk through the entire process—from scanning my face with my phone to generating a complete one-minute hype video for the podcast, all in about 15 minutes. What you’ll learn: How to create an AI avatar using Google Flow in under five minutes Why video AI tools unlock creative possibilities for people with zero video production skills The step-by-step process of generating a full storyboard using AI as your creative producer How to u

Owen Williams is a design manager at Stripe who built Protodash, an internal AI-powered prototyping platform that lets designers and PMs create high-quality Stripe dashboard prototypes without writing code. What started as a bundle of Cursor rules and React components evolved into a full web-based prototyping studio that runs in dev boxes, complete with design review modes, variant testing, and AI-powered iteration. Surprisingly, PMs now use Protodash just as much as designers, fundamentally changing how Stripe approaches prototyping, design reviews, and engineering handoffs. What you’ll learn