This week on How I AI: “Vibe analysis” with Faire + vibe coding a kid-friendly AI fortune teller

Hey friends 👋,

Here’s a weekly recap of new podcast episodes across Lenny’s Podcast Network:

Every Monday, host Claire Vo shares a 30- to 45-minute episode with a new guest demoing a practical, impactful way they’ve learned to use AI in their work or life. No pontificating—just specific and actionable advice.

“Vibe analysis”: How Faire’s data team uses AI to investigate conversion drops, analyze experiment results, and convert raw data into executive-ready insights

Brought to you by:
Zapier—The most connected AI orchestration platform
Brex—The intelligent finance platform built for founders

Guests: Tim Trueman, Strategy and Operations at Faire, and Alexa Cerf, Strategy and Analytics at Faire

Biggest takeaways:

1. The most difficult part of analysis isn’t manipulating data—it’s gathering the right context to ask meaningful questions. AI tools can search across Slack, Notion, Jira, and code repositories to quickly build context that would take hours or days manually.

2. Semantic layers dramatically improve AI’s ability to understand your data. Faire’s data team created a structured JSON file that defines business terms, tables, fields, and metrics. This allows AI to understand questions in natural language and translate them to the correct SQL queries, making zero-shot analysis possible.

3. Over-commented AI code is valuable for non-engineers. While engineers may dislike heavily commented code, these comments help non-technical team members understand the reasoning behind implementation choices. For data analysis, comments on SQL queries help analysts verify that the AI correctly understood their intent.

4. GitHub access should be standard for all team members, not just engineers. As code becomes a critical data source for business analysis, product managers and analysts need read access to repositories from day one. This represents a fundamental shift in how organizations should approach onboarding.

▶️ Listen now on YouTube | Spotify | Apple Podcasts

🔮 Vibe coding a kid-friendly AI fortune teller for your Halloween festivities | Marco Casalaina

Biggest takeaways:

1. Simple AI tools can create holiday magic in minutes. Marco transformed from Star Trek’s Captain Picard by day to neighborhood fortune teller in five minutes using GitHub Spark and some creative prompting—an easy and fun way to bring extra delight to trick-or-treaters.

2. Hyper-personalized software is here. Whether it’s entertaining neighborhood kids as a fortune teller or helping his daughter study chemistry with flashcards, Marco reaches for AI to solve little problems that would otherwise require a manual workaround.

3. Use a PRD or spec for everything! For big or small projects, Marco starts with a PRD—even if the output eventually requires more-detailed prompting. Spec Kit is a structured method for generating specs for more-complex projects than a one-off fun app.

4. AI development is becoming increasingly accessible. Tools like GitHub Spark have lowered the barrier to entry for creating functional applications for hyper-specific use cases. What once required significant development time can now be built with just a few prompts.

▶️ Listen now on YouTube | Spotify | Apple Podcasts

More shows coming soon. . . 👀
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.