
Claude Code + Obsidian: My family’s AI brain | Scott Farrar
Listen now on YouTube • Spotify • Apple Podcasts

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
Scott Farrar is a math educator and parent who built a shared household brain using Claude Code and Obsidian. In this episode, he shows how the system tracks appliances and warranties, compares insurance quotes, organizes family projects, and keeps household tasks moving through a shared to-do list and wall display. He also explains why persistent files work better for him than long AI chats, and how the same philosophy shapes his approach to using AI without taking the thinking away from students.
Biggest takeaways:
The problem with chat is not intelligence, but memory drift. Scott moved to Claude Code because it stores context in Markdown files he can inspect, correct, and reuse across sessions. His memory is no longer trapped inside an opaque conversation.
Let the AI tell you what context it needs. When Scott asked Claude how to document his home, it suggested photographing every appliance. Those photos became a searchable inventory of model numbers, serial numbers, and warranty details.
Unstructured input is fine when the system handles the organization. Scott gives Claude raw information and lets it maintain the underlying files. A custom linter prevents verbose agents from bloating documents such as his household to-do list.
Better context helps people ask better questions. Claude compares insurance quotes with detailed information about Scott’s home, identifies potential coverage gaps, and prepares specific follow-ups. He no longer has to rely entirely on the agent selling him the policy.
One master list can eliminate a house full of mental clutter. Scott and his wife captured every household task they could think of, then Claude organized them by priority, cost, and supporting information. The system now surfaces overdue work before it becomes another fire.
Multiplayer household systems require practical compromises. Claude recommended GitHub to avoid file conflicts, but that added more complexity than Scott’s wife wanted. They settled on GitHub for shared scripts and Dropbox for everyday files, matching the tools to how they actually work.
A household system becomes more useful when it leaves the laptop. Scott’s wall display shows upcoming trips, open tasks, recent wins, and small daily suggestions. It turns a private collection of files into something the whole family can see and use.
Scott rebuilt his father’s file cabinet as an AI system. His dad saved every receipt and warranty and could explain repairs from decades ago. Claude now gives Scott that same dependable household memory, only searchable through conversation.
AI should help children think, not think for them. Scott prefers tutors that ask students to explain their reasoning and work through productive struggle. He also believes some children may share unfinished ideas more comfortably with AI than with another person.
Infinite patience is not always good teaching. Scott wants AI to act as a “warm demander” that encourages students without doing the work for them. When his own agent goes off track, he starts fresh or investigates its reasoning before incorrect information reaches his memory files.
Blog and detailed workflow walkthroughs from this episode:
Claude Code and Obsidian: Scott Farrar’s Household Brain: https://www.chatprd.ai/how-i-ai/claude-code-and-obsidian-scott-farrar-s-household-brain
↳ Create a Live Household Dashboard with Claude and DAKboard: https://www.chatprd.ai/how-i-ai/workflows/create-a-live-household-dashboard-with-claude-and-dakboard
↳ Manage a Household Project Using an AI Knowledge Base: https://www.chatprd.ai/how-i-ai/workflows/manage-a-household-project-using-an-ai-knowledge-base
↳ Build a Household Knowledge Base with Claude and Obsidian: https://www.chatprd.ai/how-i-ai/workflows/build-a-household-knowledge-base-with-claude-and-obsidian
How I fight token fraud as a solo founder
Listen now on YouTube • Spotify • Apple Podcasts

Brought to you by:
In this solo episode, Claire explains how token fraud cost ChatPRD tens of thousands of dollars and consumed much of her engineering time. She walks through six forms of abuse, including farmed free trials, resold promo codes, card testing, product relays, and a custom MCP running as a 24/7 compute worker. She also shares the business and technical defenses she built, how Jev classifies suspicious activity in real time, and why she ultimately eliminated free trials.
Biggest takeaways:
Token fraud is a business risk most AI founders underestimate until the bill arrives. Unlike traditional SaaS abuse, every fraudulent model call costs real money. It cost Claire tens of thousands of dollars despite ChatPRD being SOC 2 compliant, regularly penetration-tested, and run by an experienced technical founder.
Free trials may no longer work for AI products. Fraudsters automated account creation and used ChatPRD’s most expensive models for unrelated work. Claire ultimately removed free trials, sacrificing a valuable source of product-led growth and enterprise leads after credit-card gates and paid trials also failed.
Promo codes have become a serious attack vector. Codes intended for partners were stolen, resold, and used to power other AI businesses. After discovering that roughly half of her promo codes had reached resellers, Claire stopped issuing them entirely.
MCP access creates a new category of abuse. One fraudster turned ChatPRD’s custom MCP support into a compute worker that ran around the clock. Claire responded by restricting approved hosts and blocking free tunnels and infrastructure that did not appear connected to legitimate companies.
Cheap decision models can classify fraud in real time. When a session crosses ChatPRD’s abuse threshold, a zero-data-retention Jev loop categorizes the activity. Confirmed fraud results in either a ban or a silent downgrade to a less expensive model.
AI support agents need firm boundaries around fraud. After mass bans, ChatPRD received both clumsy appeals and polished messages written by AI. Claire equipped her support agent with fraud tools and explicit rules preventing it from restoring accounts or distributing promo codes.
Blunt defenses are sometimes the most effective. Blocking traffic from certain countries using Vercel Firewall significantly reduced abuse and forced Claire to reconsider ChatPRD’s international strategy. Her new default is simple: trust must be earned rather than assumed.
Token fraud is affecting companies of every size. Claire found the same people abusing ChatPRD through rotating proxies across several major AI products. She has started discussing the problem publicly and filed FBI cybercrime reports with help from Codex.
If a company sells AI, it is ultimately selling compute. Founders should track dollars instead of requests, monitor model spending continuously, close every free entry point, and verify the client rather than only the account. Claire also learned that fraud disappears quickly when expensive models are no longer available to steal.
Blog and detailed workflow walkthroughs from this episode:
Token Fraud Is Eating AI Margins. Here’s How Claire Vo Is Fighting It: https://www.chatprd.ai/how-i-ai/token-fraud-is-eating-ai-margins-here-s-how-claire-vo-is-fighting-it
↳ Detect Automated Abuse on AI Routes with Vercel BotID: https://www.chatprd.ai/how-i-ai/workflows/detect-automated-abuse-ai-routes-botid
↳ Use an AI Assistant to Create Payment Fraud Rules: https://www.chatprd.ai/how-i-ai/workflows/use-an-ai-assistant-to-create-payment-fraud-rules
I was a Claude hater. Fable 5.2 changed my mind.
Listen now on YouTube • Spotify • Apple Podcasts
In this solo episode, Claire tests Claude Fable 5.2 to see whether Anthropic has finally built a model she enjoys using. She turns a tweet into an animated marketing video, creates assembly instructions from photos of unboxed furniture, reworks a complex ChatPRD pipeline, and builds a fully functional 3D typewriter. She also explains where Fable fits alongside Opus 5.5, why its creative work impressed her, and why she still would not trust it to design a website on its own.
Biggest takeaways:
Fable 5.2 turned Claire from a Claude skeptic back into a fan. She found the original Fable difficult to understand and unpleasant to use, with Opus 5 offering little improvement. Fable 5.2 feels fast, capable, creative, and dramatically easier to work with.
Fable 5.2 complements Opus 5.5 rather than replacing it. Opus remains the better default for most coding and knowledge work. Fable is the model Claire would choose for greater complexity, broader scope, or tasks that demand more creativity.
Its speed changes how the model feels to use. Many benchmark tasks finished in under a minute, and even a complex animation took only 16 minutes. Fable also communicates sparingly during autonomous work, surfacing only the moments that require input.
Fable 5.2 made AI video feel animated instead of assembled. From one tweet and the CXO.dev brand guidelines, it created a narrated story featuring custom invader-bot sprites that walk, jump, and cheer. No other model Claire tested produced anything comparable, so the task is becoming a permanent benchmark.
Its spatial reasoning solved a real-world problem every other model failed to. Claire gave Fable low-resolution photos of an unassembled piece of furniture with no instructions. It identified the parts, created a diagram, and produced the correct assembly sequence, which her household successfully followed.
Fable 5.2 is unexpectedly funny. It designed a bug-fighting game around real engineering tradeoffs, then made a trailer in which finance sees the token bill and downgrades the team to a cheaper model. The humor felt intentional enough to make Claire genuinely laugh.
It also holds up on serious engineering work. Fable created a sensible migration plan for ChatPRD’s messy product-intelligence pipeline and aligned closely with Claire’s own roadmap. It worked autonomously and paused at appropriate moments, though the migration is still underway.
Fable needs strong direction for visual design. It follows an existing brand system well, but its unguided web and storybook designs were unattractive. Claire expects to pair it with Opus 5.5 for frontend work and use a separate image model when original visuals are needed.
The 3D typewriter was Claire’s “AGI moment.” Fable built a working keyboard in one shot, then added white-out, music, weather, timers, writing prompts, and multiple immersive settings. It turned an idea Claire never imagined building into a tool she wants to use every day.
Fable 5.2 is available now, with an even faster mode coming. It is launching across the Claude API, cloud platforms, Claude apps, and Claude Code. Claire plans to compare it with the other new models in a full How I AI benchmark.
Blog and detailed workflow walkthroughs from this episode:
Fable 5.2 Review: Creative Enough to Build a Typewriter, Still Bad at Web Design: https://www.chatprd.ai/how-i-ai/fable-5-2-review-creative-enough-to-build-a-typewriter-still-bad-at-web-design
↳ Animate Brand Characters for Marketing Videos with Fable 5.2: https://www.chatprd.ai/how-i-ai/workflows/animate-brand-characters-for-marketing-videos-with-fable-5-2
↳ Create Flat-Pack Furniture Assembly Instructions from Photos: https://www.chatprd.ai/how-i-ai/workflows/create-flat-pack-furniture-assembly-instructions-from-photos
↳ Build an Interactive 3D Application Using a Reference Project: https://www.chatprd.ai/how-i-ai/workflows/build-an-interactive-3d-application-using-a-reference-project
If you’re enjoying these episodes, reply and let me know what you’d love to learn more about: AI workflows, hiring, growth, product strategy—anything.
Catch you next week,
Lenny
P.S. Want every new episode delivered the moment it drops? Hit “Follow” on your favorite podcast app.


