Built This Week

(Sam Nadler and Jordan Metzner are back — and this week they’re joined by Amar Goel, CEO of BITO, the AI-powered code review agent transforming how engineering teams ship software.

Jordan kicks things off by unveiling a surprise build: a fully custom BITO Slack Bot that can run PR reviews, generate stats, crack developer jokes, write haikus, and even drop into Biddo Disco Mode. Amar reacts live and pulls back the curtain on how BITO’s deep codebase analysis works — revealing how enterprise teams are merging PRs 10× faster, reducing revert rates, and catching issues that “vibe coding” tools simply miss.

From multi-million-line monorepos to legacy systems held together by duct tape, BITO’s agents are surfacing performance bugs, security vulnerabilities, logic issues, and cross-service breakages before humans ever see them. Amar explains why code review is just the start — and why BITO’s deep code intelligence unlocks a new era of AI developer tooling.

Then the trio shifts into the biggest AI news stories of the week:
• OpenAI’s internal CODE RED and the escalating model war
• Google Gemini’s rise and the threat of distribution
• Amazon’s new AI chips and the GPU economics debate
• The global AI arms race — from TPUs to supply chains to trillion-dollar CapEx bets

It’s a lively, candid, highly technical conversation with one of the sharpest minds in AI dev tooling.

Episode 22: Let's do the Math!
—

Sam Nadler and Jordan Metzner return with one of the most mind-bending episodes yet. Joined by Carina, founder & CEO of Axiom Math, the startup is building a self-improving, formal-reasoning AI mathematician. The trio breaks down why math is the next AI frontier, how Lean formalization works, and why proving theorems is a completely different challenge than solving them.

Jordan also unveils his newest build: the LLM Math Roaster,  a tool that scores, compares, and even roasts large models on proofs, with a full leaderboard, custom problem submissions, and an API for automated evaluation. (Yes, it even benchmarked Gemini, GPT-5, Claude, and Grok head-to-head.)

In AI News, the hosts unpack Google’s massive Gemini 3 launch, Jeff Bezos stepping into the arena with Project Prometheus, and Suno’s $250M raise at a $2.45B valuation, plus what hyper-powerful AI means for creativity, coding, and even music composition.

It’s fast builds, deep math, big models, and a guest who’s literally building the future of reasoning.

—
 Show Notes:
 (0:00) Intro + welcoming our guest Carina
 (1:00) What Axiom Math is building
 (3:00) Jordan’s LM Math Roaster: how it works
 (5:00) Testing models on proofs (Gemini, GPT-5, Claude, Grok)
 (7:00) Why formal proofs beat natural-language reasoning
 (9:00) The data bottleneck: Lean scarcity & synthetic generation
 (12:00) How formal systems unlock “research-level” AI math
 (15:00) Comparing LLM math vs. Axiom’s approach
 (18:00) AI News: Gemini 3 hits the market
 (20:00) Jeff Bezos returns with Project Prometheus
 (22:00) Suno raises $250M — AI-generated music explodes
 (24:00) How math, code & creativity overlap
 (25:30) Episode wrap-up + what’s coming next
—

Built This Week – Episode #21

Not your STANDARD Market

Sam Nadler and Jordan Metzner are back! And this week, they’re joined by a special guest: Angie Westbrook, CEO of Standard AI. Together, they explore one of the most creative builds yet: an AI-powered retail DJ that uses computer vision and custom AI-generated music to adjust a store’s soundtrack based on real-time foot traffic. Think: mood lighting meets AI beats, but for shopping.

Angie then pulls back the curtain on Standard AI’s computer-vision platform, describing how their “Google Analytics for physical stores” is unlocking brand-new metrics like visual engagement, real-time shopper behavior, and rapid in-store experimentation. Later, the trio covers major AI news, including Gamma’s massive Series B, SoftBank’s pivot from Nvidia to OpenAI, and 11 Labs’ newly launched marketplace where brands can license iconic voices (yes, even Babe Ruth and Maya Angelou).

Store-scanning AI, predictive retail analytics, dynamic music engines, and a surprisingly heated debate about Michael Bublé, Episode 21 brings energy, innovation, and a fascinating look at how AI is reinventing brick-and-mortar retail from the ground up.

Show Notes:

(0:00) AI-generated retail music demo + how the “store DJ” works
(0:55) Welcome + introducing guest Angie Westbrook, CEO of Standard AI
(1:27) Angie’s background and Standard AI’s mission
(1:49) This week’s agenda: AI DJ, Standard AI deep dive, and AI news
(2:35) Why AI never slows down + early thoughts heading into the demo
(2:55) The build: AI DJ for retail using computer vision + custom tracks
(3:38) Bringing music, mood, foot traffic, and AI together
(4:13) How stores currently choose music (spoiler: zero data)
(4:50) Five custom AI-generated tracks from 90–130 BPM
(5:42) Can music drive sales? The team’s hypothesis
(6:04) Demo: welcome music + dynamic BPM changes based on occupancy
(7:09) Angie reacts — why music + behavior data could transform retail
(8:13) Using engagement metrics to improve music and optimize store layouts
(9:14) Holiday music reinvented: AI-generated Christmas playlists
(9:58) Transition: What Standard AI actually does
(10:32) Standard AI explained: “Google Analytics for physical stores”
(11:01) Why sales data is a lagging indicator (and too slow for real insights)
(11:54) How AI enables rapid in-store experimentation
(12:51) Traditional A/B tests vs. AI-powered retail testing
(13:55) Faster experiments → faster revenue lift
(14:45) Privacy-first computer vision (26-point body labeling)
(16:04) What the system “sees” — digital stick figures, not faces
(16:43) Visual Engagement Score: a new metric for product discovery
(17:52) Why most new products fail (and how AI fixes it)
(18:47) Predictive modeling + simulating store changes with AI
(19:58) The future of AI-driven retail experiences
(20:46) Fun fact: 85–90% of retail sales still happen in-store
(21:12) AI News #1: Gamma raises $68M at a $2.1B valuation
(22:21) 70M users + 30M decks/month — Gamma’s explosive growth
(23:03) Why incumbents (Google, Microsoft) didn’t beat them
(23:56) AI News #2: SoftBank sells Nvidia stake, pivots to OpenAI
(24:52) AI News #3: 11 Labs launches the Iconic Voice Marketplace
(28:02) Historical icons, celebrity voices, and licensing in the AI era
(29:12) Consent, rights, and the new economics of synthetic voices
(30:09) Fatman Scoop as your in-store DJ? The team imagines the future
(30:25) Closing thoughts + a huge thanks to Angie
(31:05) Teaser: Next week’s guest — Axiom Math

—

Platforms / Tools Mentioned:

Built This Week – Episode #20

Episode 20: Compliance, Pomelli, and the Rise of the Robots

Sam Nadler and Jordan Metzner are back for a landmark 20th episode of Built This Week!  This time, the duo breaks down how Ryz Labs used AI to build a full compliance and education platform, complete with video-based lessons, automated tests, and certificates: all powered by Video 3.1, React, and Supabase. They also explore Google’s new AI-powered marketing tool, which auto-generates on-brand social campaigns in seconds (seriously, it’s like having a creative team in your browser). In AI News, the hosts discuss Amazon’s robot-run Whole Foods stores, the growing home robotics market, and what a $20,000 “household robot” really means for the future of everyday automation. Fun, fast builds. Real AI demos. And a glimpse into how AI is quietly reshaping how we work, market, and even shop for groceries.

Show Notes:

(0:00) Intro + hitting 15,000 subscribers
(1:00) What’s on deck this week
(3:00) The rise of AI-powered compliance training
(4:00) Demo: AI-generated videos + exam builder
(6:30) Building with Supabase + React + Video 3.1
(8:30) Why we built (not bought) our education platform
(10:00) Google’s new social marketing tool demo
(12:30) Creating full brand campaigns with AI
(15:00) Sponsor: Ryz Labs – build faster with world-class teams
(16:00) AI News: Amazon’s robotic Whole Foods
(18:00) The $20K home robot – hype or reality?
(22:00) What robots can (and can’t) do yet
(24:00) Reflections on episode 20 + what’s next
(25:30) Teaser: Next week’s guest – Angie Westbrook, CEO of Standard AI

Platforms / Tools Mentioned:

Episode 19: Mirror, Mirror on the Wall… Who Built the Smartest AI of All?

It’s a spooky special! Sam Nadler (a.k.a. Bad Bunny) and Jordan Metzner (the resident vampire) celebrate Halloween with a pair of AI-powered builds that bring equal parts fun and fright. First, they unveil Mirror, Mirror on the Wall, a poetic, Gemini-powered “talking mirror” built in Google’s new AI Studio. Then, they conjure up a “Trick-or-Treat Route Optimizer,” a playful demo that uses Maps and AI to find the best candy streets in your city.
In Tool of the Week, they explore Google’s Build Studio, a fresh entry into the “vibe coding” space, and explain why it’s a step-function improvement over other no-code tools. Gemini comes baked right in. Finally, in AI News, they break down Nvidia’s record-breaking $5 trillion valuation and Elon Musk’s Grok-a-pedia, a controversial AI-powered rival to Wikipedia.
Fun, fast builds. Real AI demos. And a whole lot of Halloween spirit.

—

Show Notes:
 (0:00) Intro + Halloween costumes
 (1:00) Mirror, Mirror on the Wall – the spooky AI build
 (3:20) How it works – Gemini, speech-to-text, and text-to-speech
 (5:00) Building with Google’s new AI Studio
 (8:00) Guess the Costume app demo
 (9:00) Trick-or-Treat Route Optimizer with Maps + Gemini
 (13:00) Why Google’s “vibe coding” tool feels like a leap forward
 (15:20) News: Nvidia hits $5T valuation
 (18:00) Elon Musk launches Grok-a-pedia
 (21:40) Halloween wrap-up + what’s next week

—