How I AI

Scott Farrar is a math educator and parent who got tired of AI chats that drift and forget. So he built a household brain in Claude Code: a folder of Markdown files, viewed in Obsidian, that knows his appliances, warranties, insurance documents, and everything on his family’s to-do list. In this episode, Scott shows how he uses it to shop for car insurance, plan repairs, share the system with his wife, and put priority tasks and recent wins on a wall display. We also talk about AI and math learning, and why he wants AI to keep kids doing the thinking.

What you’ll learn:
Why he moved his home life from AI chat to Claude Code
What Claude told him to photograph first
How AI made him a sharper insurance shopper
The to-do file he keeps coming back to
How he and his wife share one household brain
Why his wall display has a “recent wins” section
How a flipped tutor gets kids to teach the AI
—
Brought to you by:
WorkOS—Make your app enterprise-ready, with SSO, SCIM, RBAC, and more
Jira Product Discovery—Prioritize with insights, build with confidence
—
In this episode, we cover:
(00:00) Teaser
(02:41) The problem (and solution)
(06:05) Demo: shopping for car insurance
(08:05) Building a household brain
(12:37) Type A vs. type B AI organization
(14:40) His shared household to-do list
(19:07) Household DAKboard wall display
(21:36) Does it actually change behavior?
(22:40) Household tasks to hand to AI
(26:00) AI, kids, and student agency
(31:16) When AI gets out of sync
(32:49) Where to find Scott
—
Tools referenced:
• Claude Code: https://www.claude.com/product/claude-code
• Obsidian: https://obsidian.md/
• GitHub: https://github.com/
• DAKboard: https://dakboard.com/
—
Other references:
• I Built My Home’s AI Assistant (Scott’s write-up): https://sfxmath.com/work/homeai-household-knowledge-base/
• Algebuds: Student Tutors Chatbot: https://sfxmath.com/work/algebuds/
—
Where to find Scott Farrar:
Website: https://sfxmath.com/
LinkedIn: https://www.linkedin.com/in/farrarscott
—
Where to find Claire Vo:
ChatPRD: https://www.chatprd.ai/
Website: https://clairevo.com/
LinkedIn: https://www.linkedin.com/in/clairevo/
X: https://x.com/clairevo

—
Have a really cool use case of how you use AI in your work? Let us know:
https://docs.google.com/forms/d/e/1FAIpQLSfP8wYCeDo5K0DxscDmoqgkxYY8ngA3B2anUDDvC4xadGTerg/viewform
—
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email jordan@penname.co.

Anthropic just released Fable 5.2, their new frontier model, and I spent two days actually building things with it before recording this. I made an animated marketing video from a single tweet, assembled a pile of unboxed furniture using only blurry floor photos, and extended our CXO brand sprites into a full bug-defense game complete with a trailer. In this episode I walk through what impressed me, what fell down, and how I’m thinking about routing tasks between Fable 5.2 and Opus 5.5 going forward.

What you’ll learn:
What Anthropic launched with Fable 5.2 and Mythos 5.2, and when to reach for Fable instead of Opus 5.5
My pros and cons after a couple of days of hands-on testing
How Fable 5.2 turned a tweet and a brand book into an animated video that doesn’t look like slides
The geometry test every other model failed: assembly instructions for flat-pack furniture with no manual
How it handled a real re-architecture of ChatPRD’s product intelligence pipeline
Why I still wouldn’t let it design a website on its own
The 3D typewriter it built me, and how you can get access to the model
—
In this episode, we cover:
(00:00) Confessions of a Claude hater
(02:54) What Anthropic launched: Fable 5.2 and Mythos 5.2
(03:16) When to use Fable 5.2 vs. Opus 5.5
(03:30) Black holes, coding claims, and benchmarks
(04:40) Guardrails and anti-distillation safeguards
(05:12) My high-level pros and cons
(07:23) Video generation: turning a tweet into an animated film
(09:47) Animating the invader bots
(11:29) Flat-pack furniture with no instructions
(13:09) The bug factory game and its trailer
(15:16) Real engineering: re-architecting ChatPRD’s product intelligence pipeline
(16:57) Where it falls down: web design
(18:08) Claire’s typewriter
(23:02) How I AI bench preview
(23:34) How to get it: availability, fast mode, and Fable resets
(24:13) Final take
—
Tools referenced:
• Claude Fable 5.2: https://www.anthropic.com/claude-fable-and-mythos-5-2
• Claude Opus 5.5: https://www.anthropic.com/claude-opus-5-5
• Claude Code: https://claude.com/claude-code
• HyperFrames: https://hyperframes.heygen.com/
• typed.page: https://typed.page/
—
Other references:
• Guillermo Rauch’s 3D record player: https://vinyl-gl.vercel.app/
• The bug factory game: https://www.cxo.dev/games/bug-factory
—
Where to find Claire Vo:
ChatPRD: https://www.chatprd.ai/
Website: https://clairevo.com/
LinkedIn: https://www.linkedin.com/in/clairevo/
X: https://x.com/clairevo
—
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email jordan@penname.co.

William Imoh is the founder of Hackmamba, a developer marketing company, and the creator of Mural, a real-time voice app he built to learn Norwegian after moving from Dubai to Norway. He has a chemical engineering degree, taught himself to code, and spent four years as a product manager, but he had never written a line of Swift. In this episode, William shows how he used Codex and GPT-Live to build Mural natively for iOS and Android, then walks through the Lord of the Rings–themed Grok Bot “fellowship” that helps him run a team of about 25 as a solo founder.

What you’ll learn:
The design prompt that made Mural look nothing like any other language app
Why 1,000 days of Duolingo left him unable to hold a conversation in Norwegian
What GPT-Live-1 costs per session and the latency threshold that makes or breaks a voice tutor
How he assigned every solo founder role to a Lord of the Rings character in Grok
Why he gave his agents access to everything across 15 open tabs, except one thing
What he still has to do himself after the models improved
Why the fear that keeps him up isn’t replacement—it’s dependency
—
Brought to you by:
WorkOS—Make your app enterprise-ready, with SSO, SCIM, RBAC, and more
Vanta—Automate compliance and simplify security
—
In this episode, we cover:
(00:00) Teaser
(02:52) Introduction to William and his language learning app
(05:58) William’s tech background and how he started building
(08:07) The first prompt
(11:09) The importance of design language and articulation
(14:38) Live demo: a Norwegian conversation
(21:11) Having a growth mindset
(22:48) Why GPT Live works for this
(23:34) What it costs to run
(24:50) Running Hackmamba with agents
(26:58) Codex projects for organization
(28:47) His Lord of the Rings Grok Bot fellowship
(34:05) Recap
(34:54) Prompting strategies
(37:21) Where to find William
—
References:
• Mural on GitHub: https://github.com/Chuloo/mural
• Codex: https://chatgpt.com/codex
• GPT-Live: https://openai.com/index/introducing-gpt-live/
• Grok Bot: https://grokbot.com/
• Cursor: https://cursor.com/
• Boki: https://boki.io/
• Notion: https://www.notion.com/
—
Where to find William Imoh:
X: https://x.com/iChuloo
LinkedIn: https://www.linkedin.com/in/william-imoh
Hackmamba: https://hackmamba.io/
Hackmamba Podcast: https://hackmamba.io/eoc-podcast/
Mural: https://mural.chat/
—
Where to find Claire Vo:
ChatPRD: https://www.chatprd.ai/
Website: https://clairevo.com/
LinkedIn: https://www.linkedin.com/in/clairevo/
X: https://x.com/clairevo
—
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email jordan@penname.co.

Ezra Mechaber is a growth product manager at Figma whose goal is to be “lazy in the right places.” When he joined Figma, he found almost no one outside engineering using AI to get real work done, so he and a couple of fellow PMs turned his personal Claude Code setup into PM OS, a shared repo of 31 skills that every PM at Figma now uses. In this episode, Ezra walks me through his favorite skills, how he bug bashes with Codex, AutoXP—an automated growth PM that found a huge win on its very first experiment—and a real-time writing assistant he built with Jev.

What you’ll learn:
Why PM OS is a repo, not a product
The skill Ezra runs six times a day to tame Slack
How one repo keeps 60 to 70 PMs in sync
Why his bug-bash agent catches things he never would
How AutoXP runs experiments with one human checkpoint
Why Jev took over every meeting he was in for two weeks
What to do when you want to yell at your AI
—
Brought to you by:
Optimizely—Your AI agent orchestration platform for marketing and digital teams
Jira Product Discovery—Prioritize with insights, build with confidence
—
In this episode, we cover:
(00:00) Episode preview
(00:51) Introduction to Ezra Mechaber
(02:04) The origin story of Figma’s PM OS
(06:30) PM OS demo: the “chief of staff” setup
(10:28) How the repo works: skills, hooks, and private sub-repos
(12:00) How the skills got built, roasted, and whittled down
(14:15) Build artifact, FigJam MCP, and coaching skills
(17:33) Transitioning from the terminal to a local web front end
(19:30) Bug bashing with Codex
(22:08) AutoXP: an automated growth PM
(26:26) Claire’s Experiment Engine backstory
(26:58) Building a real-time writing assistant with Jev
(33:15) Lightning round and final thoughts
—
Tools referenced:
• Figma: https://www.figma.com/
• FigJam: https://www.figma.com/figjam/
• Figma MCP server: https://developers.figma.com/docs/figma-mcp-server/
• Claude Code: https://www.claude.com/product/claude-code
• Codex: https://openai.com/codex/
• Cursor Automations: https://cursor.com/docs/cloud-agent/automations
• Jev: https://typesafe.ai/
• Marker: https://marker.page/
• Instinct: https://instinct.com/
• Dots: https://openai.com/index/introducing-dots/
—
Other reference:
• Jev for beginners: how to use it and what to build: https://www.lennysnewsletter.com/p/jev-for-beginners-how-to-use-it-and
—
Where to find Ezra Mechaber:
X: https://x.com/ezramechaber
LinkedIn: https://www.linkedin.com/in/ezra-mechaber
Website: https://ezramechaber.com/
—
Where to find Claire Vo:
ChatPRD: https://www.chatprd.ai/
Website: https://clairevo.com/
LinkedIn: https://www.linkedin.com/in/clairevo/
X: https://x.com/clairevo
—
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email jordan@penname.co.

I have personal-agent fatigue, so I ran the first How I AI personal-agent benchmark: Grok Bot, Dot, Muse, and Claude Duet across nine real tasks, from a Slack reply and a Sentry bug to a Figma thumbnail, inbox triage, a family newspaper, physics homework for a fourth grader, shoe shopping, and a ChatPRD launch video. I used computer use to operate them: Claude ran Dot, Codex ran the rest and scored the results live. Here’s the scoreboard—and which agent I’d actually trust for work vs. life.
—
Brought to you by:
WorkOS—Make your app enterprise-ready, with SSO, SCIM, RBAC, and more
Firecrawl—Give your AI agents web data and beyond
—
In this episode, we cover:
(00:00) Introduction
(02:13) The personal-agent benchmark setup
(05:00) The nine tasks and the prompts I used
(07:20) Scoreboard overview
(10:06) Task 1: Draft a Slack reply as me
(11:39) Task 2: Cut a short-form video from raw Dropbox footage
(14:56) Task 3: Fix a bug from Sentry
(17:30) Task 4: Build a How I AI thumbnail in Figma
(19:25) Task 5: Triage my inbox for to-dos
(21:06) Task 6: Build a family newspaper
(23:30) Task 7: Explain a physics homework question to a fourth grader
(24:54) Task 8: Shop for shoes
(26:46) Task 9: Make a ChatPRD Product Intelligence launch video
(30:01) Final scores
(32:38) My takeaways
—
Tools referenced:
• Grok Bot: https://x.ai/bot
• Dot: https://chatgpt.com/features/dots/
• Meta Muse: https://ai.meta.com/muse/
• Claude Duet: https://claude.com/product/claude-duet
• Codex: https://openai.com/codex
• ElevenLabs: https://elevenlabs.io/
• Figma: https://www.figma.com/
• Sentry: https://sentry.io/
• Linear: https://linear.app/
• Dropbox: https://www.dropbox.com/
—
Where to find Claire Vo:
ChatPRD: https://www.chatprd.ai/
Website: https://clairevo.com/
LinkedIn: https://www.linkedin.com/in/clairevo/
X: https://x.com/clairevo
—
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email jordan@penname.co.