Podcasts about linear

For Rod and Donut Rooter

The shift from traditional television to connected TV has accelerated rapidly, requiring publishers to offer both massive culture-shifting scale and ultra-precise targeting capabilities. In this deep dive, Netflix Advertising VP Nicolle Pangis pulls back the curtain on how the platform built an independent, proprietary ad server to give global brands the exact mix of automated programmatic buying and high-impact live events they need to drive measurable ROI. Key Highlights

Sinkende Umsätze fühlen sich oft an wie Scheitern. Aber vielleicht ist es nur Ebbe. In dieser Folge geht es darum, warum jedes Ende ein Zyklus ist und nicht der Tod deines Business.In dieser Folge geht es um:Geld ausgeben vs. Geld zirkulieren lassen: wie Worte dein System programmierenWarum wir gelernt haben, jedes Ende als Drama zu sehenDie Kuchen-Metapher: nichts geht verloren, es verändert nur die FormEbbe und Flut auf dem Konto, ohne Schuld und SchamWie du am Geburtshoroskop erkennst, in welcher Zyklusphase du gerade bistWichtige Links:

Dr. Al Grauer hosts. Dr. Albert D. Grauer ( @Nmcanopus ) is an observational asteroid hunting astronomer. Dr. Grauer retired from the University of Arkansas at Little Rock in 2006. travelersinthenight.org From March 2026. Today's 2 topics: - In 1892 the world's largest telescope, the Lick Observatory's 36 inch refracting telescope made the news when E.E. Barnard discovered, Amalthea, the 5th moon of Jupiter. In 2025 this historic telescope made the news again when on Christmas morning winds of 114 mph blew off a 3 ton piece of the shutter on its dome. The adaptive optics research pioneered at Lick Observatory helped in the creation of the twin giant 10 meter telescopes that sit atop Mauna Kea in Hawaii.   - Astronomers using the 8.1 m Gemini South Telescope in Chile were excited by the fact that 467P (LINEAR-Grauer)'s Centaur like orbit had been changed as the nucleus emitted rocket like bursts of gases as it was warmed by the Sun. Inert inactive asteroids orbit the Sun following the law of gravity whereas active asteroids can emit little rocket like bursts of gas which can change their path about the Sun in interesting ways. It is important to study objects like 467P (LINEAR-Grauer) to make sure their path about the Sun doesn't change to make them a threat to our home planet.   We've added a new way to donate to 365 Days of Astronomy to support editing, hosting, and production costs.  Just visit: https://www.patreon.com/365DaysOfAstronomy and donate as much as you can! Share the podcast with your friends and send the Patreon link to them too!  Every bit helps! Thank you! ------------------------------------ Do go visit http://www.redbubble.com/people/CosmoQuestX/shop for cool Astronomy Cast and CosmoQuest t-shirts, coffee mugs and other awesomeness! http://cosmoquest.org/Donate This show is made possible through your donations.  Thank you! (Haven't donated? It's not too late! Just click!) ------------------------------------ The 365 Days of Astronomy Podcast is produced by the Planetary Science Institute. http://www.psi.edu Visit us on the web at 365DaysOfAstronomy.org or email us at info@365DaysOfAstronomy.org.

Time is not a line. Time is a spiral. Prepare to get dizzy.

This podcast shows you how to fully recover from OCD.Each episode breaks down the exact techniques and nuances that stop rumination, reduce compulsions, and help you retrain your brain out of the OCD cycle. We cover every major OCD theme, including:Pure-O OCDRelationship OCDHarm OCDReal Event OCDSO-OCD / Sexuality OCDReligious / Scrupulosity OCDCleaning & Contamination OCDPhysical CompulsionsAll other OCD subtypesMy goal is simple: clear guidance that actually works, explained in a way that is calm, direct, and easy to apply immediately.You can fully recover from OCD. Don't give up — you're not stuck, and your brain can change.

Scott and Josh run down this week's questions! As mentioned in the pod, we've put this up early to make sure you get the chance to join the WCG Discord and get involved in a giveaway for free Kepler Interactive games like Clair Obscur: Expedition 33, Sifu, Pacific Drive and more! Join here: http://discord.gg/QRByaQaftN Hosted on Acast. See acast.com/privacy for more information.

Achieving true cross-channel attribution remains an uphill battle as walled gardens restrict access to critical log-level data. Georgia Pacific's Vice President of Integrated Media and Brand Analytics, Javier Bustillos, reveals how his team combats these fragmentation challenges by accelerating in-house Marketing Mix Modeling and adopting a disciplined, test-and-learn approach to automation. Key Highlights

In this episode of The Product Podcast by Product School, Carlos González de Villaumbrosia sits down with Cristina Cordova, Chief Operating Officer at Linear, the product development system built for teams and agents. Linear raised $82 million in a Series C round in June 2025 at a $1.25 billion valuation. The company has been profitable since 2021, and serves over 20,000 paid business customers, from seed-stage startups to Fortune 100 enterprises, with a team of just 140 people. Before Linear, Cristina joined Stripe as one of its first employees, and led Platform and Partnerships at Notion.What you'll learn:Why keeping headcount intentionally lean is a strategic advantageReplacing traditional interviews with paid two to five-day projectsWhy PMs are the fastest-growing power users of agentic toolsKey takeaways:A small team is not a small business. Revenue, customers, and growth rate matter more than headcount.If you fully delegate your AI thinking, you lose your native understanding of how these products actually workAgentic workflows are now the default, not a feature. The companies that treat them that way will pull ahead.Credits:Host: Carlos Gonzalez de VillaumbrosiaGuest: Cristina CordovaSocial Links:Find out more about Product School hereFollow our Podcast on TikTok hereFollow Product School on LinkedIn here

As television viewership shifts, NBCUniversal is proving that premium IP like live sports and reality television can compete with digital channels by integrating advanced programmatic ad tech. Through initiatives like real-time AI context-scanning and the Performance Insights Hub, they are closing the data loop to deliver immediate, measurable outcomes across the entire marketing funnel. Key Highlights

Episode #260 features Maxine Minter — Founder and General Partner of the Pre-Seed Venture Capital Fund, Co Ventures. Maxine reflects on growing up between Australia, Japan and Europe, speaking Japanese before English, and raised by a fiercely entrepreneurial single mother. Vidit and Maxine explore her childhood, the influence of her grandparents, executive coaching, the idea of “generative ambition”, and the lessons learned from building companies, backing founders and how and why she started her own VC fund, Co Ventures. They also discuss the specifics of how the best Aussie founders go global, the realities of venture capital, AI, partnership, importance of play, and why the biggest opportunities often come from stepping outside the boxes others expect you to fit into. Please enjoy exploring your curiosity. ________ Get in touch with us via email at contact@curiositycentre.com Join our stable of commercial partners including the Australian Government, Google, KPMG, Vanta, Allens, Macquarie Capital, City of Sydney and more.  Show notes and more episodes here Follow us on LinkedIn, Twitter and Instagram Get in touch with our Founder and Host, Vidit Agarwal directly here Contact us via our website ________ The High Flyers Podcast features in-depth interviews with the world's most influential figures in business, tech, finance, government and sport. Launched in 2020, it has ranked in the global top ten for past three years, with listeners in 27 countries and over 200+ episodes released, and featured in Forbes, Daily Telegraph, and at SXSW. Our guests include -- Malcolm Turnbull (Prime Minister of Australia), Jason Collins (Head of BlackRock, Asia Pacific), Brad Banducci (CEO, Woolworths), Michael Schneider (CEO, Bunnings), Elena Verna (Head of Growth, Lovable), David Haber (a16z Partner), Jodie Auster (Uber's Global Head of Travel), Rob Giglio (CCO, Canva), Jean-Michel Limieux (CTO, Shopify and Atlassian), Stevie Case (CRO, Vanta), John Haddock (CBO, Harvey), Mark Suster (Partner, Upfront Ventures), Niki Scevak (Partner, Blackbird), Craig Tiley (CEO, USA Tennis), Jeanne DeWitt Grosser (COO, Vercel), Paul Bassat (Partner, Square Peg), Bowen Pan (Creator, Facebook Marketplace), Peter Varghese (Secretary of Foreign Affairs, Australian Government), Sam Sicilia (CIO, Hostplus), Jack Zhang (CEO, Airwallex), Tim Doyle (CEO, Eucalyptus), Sukhinder Singh Cassidy (CEO, Xero), Sanjeev Gandhi (CEO, Orica), Philip Green (Australia's Ambassador/High Commissioner to India), Vivek Bhatia (CEO, MUFG), Cristina Cordova (COO, Linear) and more.

This is a recap of the top 10 posts on Hacker News on June 07, 2026. This podcast was generated by wondercraft.ai (00:30): LLMs are eroding my software engineering career and I don't know what to doOriginal post: https://news.ycombinator.com/item?id=48434312&utm_source=wondercraft_ai(01:57): Building from zero after addiction, prison, and a felonyOriginal post: https://news.ycombinator.com/item?id=48437406&utm_source=wondercraft_ai(03:25): Anthropic, please ship an official Claude Desktop for LinuxOriginal post: https://news.ycombinator.com/item?id=48434436&utm_source=wondercraft_ai(04:52): The 29th International Obfuscated C Code Contest (IOCCC) 2025 WinnersOriginal post: https://news.ycombinator.com/item?id=48432199&utm_source=wondercraft_ai(06:20): How's Linear so fast? A technical breakdownOriginal post: https://news.ycombinator.com/item?id=48437609&utm_source=wondercraft_ai(07:47): Scientists ejected from diabetes conference for distributing journal reprintsOriginal post: https://news.ycombinator.com/item?id=48433410&utm_source=wondercraft_ai(09:15): I design with Claude more than Figma nowOriginal post: https://news.ycombinator.com/item?id=48431981&utm_source=wondercraft_ai(10:42): Show HN: Lathe – Use LLMs to learn a new domain, not skip past itOriginal post: https://news.ycombinator.com/item?id=48433756&utm_source=wondercraft_ai(12:10): Major P2P issues in Israel and possibly other Middle East countriesOriginal post: https://news.ycombinator.com/item?id=48431461&utm_source=wondercraft_ai(13:37): Public Domain Image ArchiveOriginal post: https://news.ycombinator.com/item?id=48430539&utm_source=wondercraft_aiThis is a third-party project, independent from HN and YC. Text and audio generated using AI, by wondercraft.ai. Create your own studio quality podcast with text as the only input in seconds at app.wondercraft.ai. Issues or feedback? We'd love to hear from you: team@wondercraft.ai

Matt and Rob do some actual prep, but this time it's a linear adventure (boo! hiss!) We sketch out a quest to bring down a decadent nobleman who is cheating death and causing mayhem with his party that never ends! Can the intrepid DMs beat the odds and make a direct line a little bit more interesting? Listen and find out! Magnolia's Blog

After briefly de-emphasizing targeted TV ads during the Discovery merger, Warner Bros. Discovery has rapidly rebuilt its infrastructure to offer clients unprecedented transparency and accountability. In this live recording from the GoAddressable upfront breakfast, learn how premium IP content is joining forces with sophisticated data waterfalls to challenge the dominance of walled gardens. Key Highlights

The study you should read this week A 2016 meta-analysis from the CMAJ pulled together 46 prospective cohort studies — 1.2 million people, 78,000 deaths. The finding: for every 10 beats per minute higher your resting heart rate sits, your all-cause mortality risk goes up about 9 per cent. Linear from 45 bpm upward, no point where lower stops being better. Independent of blood pressure, smoking, BMI, cholesterol, diabetes, and physical activity. Resting heart rate is carrying its own signal. Plus what to do with this if you race, ride high volume, or train time-capped — and why the adaptations that lower your resting heart rate are the same adaptations that predict a longer, healthier life. Study: Zhang D, Shen X, Qi X. Resting heart rate and all-cause and cardiovascular mortality in the general population: a meta-analysis. CMAJ 2016;188(3):E53–E63. DOI: 10.1503/cmaj.150535 Links: YouTube companion: Cyclist Over 50? Your Fitness Can't Tell You This. Guided is live — two coaches, weekly review, my read behind every plan: https://go.semiprocycling.com/go/btsmfgDaily cycling intelligence from SEMIPRO CYCLING, produced with AI-assisted research, scripting, and synthetic voice.

Discover how the future of TV advertising is shifting toward outcome-based measurement and AI-driven optimization coming out of the 2026 upfronts . iSpot CEO Sean Muller joins the show to break down their fundamental "Creative + Audience = Outcome" equation, the integration of their new AI platform Sage, and why the industry must prioritize trusted, neutral data over ongoing currency debates. Key Highlights

In this episode of Talk Dizzy To Me, Dr. Dani Tolman, PT and Dr. Abbie Ross, PT, NCS welcome back Sarah Renberg for her third appearance on the podcast. Sarah shares an inspiring update on her journey after a traumatic brain injury (TBI), vestibular dysfunction, autonomic dysfunction, ocular motor challenges, and more — and how she is now navigating medical school while continuing to manage her health. Sarah offers a powerful patient perspective on recovery, self-advocacy, support systems, and redefining progress after brain injury.Episode Resources: -Instagram: @Sren20-Sarah's 1st TDTM Episode 2021-Sarah's 2nd TDTM Episode 2023 Sarah's Team on TDTM:-Dr. Appelbaum-Dr. KeiserHosted by:

Episode #258 features Cristina Cordova — employee number 28 at Stripe, an early hire at Notion, former Partner at First Round Capital, and now COO of Linear. This conversation is less about startup tactics and more about ambition, identity and operating inside some of Silicon Valley's most respected companies before they became obvious to everyone else. Cristina reflects on growing up in Los Angeles with a single mother, becoming fiercely independent from a young age, and navigating worlds that initially felt completely foreign to her own. She shares the emotional complexity of spending more than a decade inside elite tech environments, from joining Stripe in its earliest days to helping scale Notion during its breakout years. Vidit and Cristina explore what separates companies that become deeply loved from those that simply grow fast, why some people thrive in ambiguity while others struggle as organisations scale, and how her “run through walls” mentality became both a superpower and a source of tension as companies matured from dozens to thousands of employees. They also discuss partnerships and developer ecosystems at Stripe, community-led growth at Notion, building products with taste and quality, AI and modern software companies, founder psychology, career reinvention, and the challenge of building a meaningful life when work becomes such a large part of who you are. Please enjoy exploring your curiosity. ________ Get in touch with us via email at contact@curiositycentre.com Join our stable of commercial partners including the Australian Government, Google, KPMG, Vanta, Allens, Macquarie Capital, City of Sydney and more.  Show notes and more episodes here Follow us on LinkedIn, Twitter, Instagram, or YouTube Get in touch with our Founder and Host, Vidit Agarwal directly here Contact us via our website ________ The High Flyers Podcast features in-depth interviews with the world's most influential figures in business, tech, finance, government and sport. Launched in 2020, it has ranked in the global top ten for past three years, with listeners in 27 countries and over 200+ episodes released, and featured in Forbes, Daily Telegraph, and at SXSW. Our guests include -- Malcolm Turnbull (Prime Minister of Australia), Anil Sabharwal (Global VP, Product at Google), Jason Collins (Head of BlackRock, Asia Pacific), Jodie Auster (Uber's Global Head of Travel), Stevie Case (Chief Revenue Officer, Vanta), Brad Banducci (CEO, Woolworths),  David Haber (GP, a16z), Rob Giglio (CCO, Canva), Jean-Michel Lemieux (CTO, Shopify + Atlassian), Sweta Mehra (EGM, NAB; ex CMO, ANZ), Bowen Pan (Creator, Facebook Marketplace), Sam Sicilia (Chief Investment Officer, Hostplus), Craig Tiley (CEO, US Tennis), John Haddock (CBO, Harvey), Niki Scevak (Co-Founder, Blackbird Ventures), Mike Schneider (CEO, Bunnings), Trent Cotchin (3x Premiership Winning Captain, Richmond FC), Peter Varghese (Secretary of Foreign Affairs, Australian Government), Jack Zhang (CEO, Airwallex), Matteo Franceschetti (CEO, Eight Sleep), Vivek Bhatia (CEO, MUFG), Sanjeev Gandhi (CEO, Orica) and more. 

* You can get the sermon note sheet at: https://family-bible-church.org/2026Messages/26May24.pdf * Last week, we considered Remembering Your Creator in Your Labor. As we ended that study looking at a proper Biblical Perspective of Labor, we considered how much Scripture adjures us to be diligent in our labor by not being lazy, but rather redeeming the time knowing that the days are evil. * Today, we continue that line of thought considering the redemption of time. * In "Bob's Philosophy of Life," a fulfilled Christian life is found through "The redemption of that which cannot be saved in order to invest in the redemption of that which can be saved by laying all that I am on the altar in order that YHWH may alter all that I am!" * Lord willing, today we will have a study in Contrasts considering Time v. Events; Positive v. Negative Events; Cyclical v. Linear views of time ... and then a consideration of how the Sovereignty of God is intricately woven into a proper Biblical understanding of time, events, and our seasons of life. * This message was presented by Bob Corbin on May 24, 2026 at Family Bible Church in Martinez, Georgia.

When you're grieving or going through a major life change, practical decisions don't pause even when we need them to because we are overwhelmed. This panel facilitates a conversation exploring navigating healthcare decisions with our families, understanding health insurance options during transitions (e.g., between jobs) and preparing foundational documents like living wills or healthcare directives. ⚕️Yvonne Olusi‑Ogadi is a former nurse with 25 years of experience and a practicing attorney specializing in eldercare, estate planning, and healthcare directives bringing clinical insight, legal clarity, and deep compassion to families navigating life transitions.

Gen Alpha has completely fragmented away from traditional TV, leaving advertisers scrambling to connect with kids and parents across YouTube, FAST channels, and gaming platforms.  This week, Mike sits down with Emma Witkowski, VP of Media Solutions at WildBrain, to unpack the massive market disconnect in children's media, the power of nostalgia in family co-viewing, and how upcoming privacy regulations like COPPA 2.0 are rewriting the rules of digital targeting. Key Highlights:

➡️ Search OCD HELP app on App Store and Google PlayThis podcast shows you how to fully recover from OCD.Each episode breaks down the exact techniques and nuances that stop rumination, reduce compulsions, and help you retrain your brain out of the OCD cycle. We cover every major OCD theme, including:Pure-O OCDRelationship OCDHarm OCDReal Event OCDSO-OCD / Sexuality OCDReligious / Scrupulosity OCDCleaning & Contamination OCDPhysical CompulsionsAll other OCD subtypesMy goal is simple: clear guidance that actually works, explained in a way that is calm, direct, and easy to apply immediately.You can fully recover from OCD. Don't give up — you're not stuck, and your brain can change.

Apple lleva cuatro años construyendo la infraestructura para que eso ocurra: App Intents desde iOS 16, Assistant Schemas desde iOS 18, y ahora una Siri completamente rediseñada en iOS 27 que Gurman describió esta semana como "un agente siempre activo que toma acción en todas las apps". En este episodio explico qué significa eso en términos técnicos reales, por qué Apple lleva dos años sin conseguir que funcione bien, y cómo el acuerdo con Google y la destilación del modelo Gemini cambia la ecuación. Pero además: Google presentó ayer en el Android Show previo al Google I/O exactamente la misma arquitectura. Las dos plataformas móviles más grandes del mundo, la misma semana, construyendo lo mismo de forma independiente. En este episodio también hablo del HomePad, las gafas N50, el pendant y el robot de sobremesa: el ecosistema de hardware que hace inevitable que el agente de IA —Siri, Gemini, Claude— se convierta en la interfaz que gobierna todos tus servicios instalados. Y lo anclo en algo que ya está pasando hoy: llevo meses usando Linear sin haber abierto su app. Igual que mucha gente usa Notion, Obsidian o el correo a través de agentes sin tocar su interfaz. El agente es la nueva UI. El App Store no muere: crece en una nueva dimensión.

Disney's streaming business looks healthier, while the company argues its old linear networks are better treated as content brands than businesses to spin off. Meanwhile, Netflix has the year's biggest show so far, AMC is bringing live concerts to theaters, and everyone keeps turning movies and TV into expanded universes.This week on The FULL Experience: Magnum, P.I. (708 - "Novel Connection")Next week: Murder, She Wrote (308: "Magnum on Ice")Subscribe, get expanded show notes, and past episodes at http://Cordkillers.comSupport Cordkillers at http://Patreon.com/CordkillersYouTube: https://youtu.be/pP_M6B9iPqg Hosted on Acast. See acast.com/privacy for more information.

Disney's streaming business looks healthier, while the company argues its old linear networks are better treated as content brands than businesses to spin off. Meanwhile, Netflix has the year's biggest show so far, AMC is bringing live concerts to theaters, and everyone keeps turning movies and TV into expanded universes.This week on The FULL Experience: Magnum, P.I. (708 - "Novel Connection")Next week: Murder, She Wrote (308: "Magnum on Ice")Subscribe, get expanded show notes, and past episodes at http://Cordkillers.comSupport Cordkillers at http://Patreon.com/CordkillersYouTube: https://youtu.be/pP_M6B9iPqg Hosted on Acast. See acast.com/privacy for more information.

Disney's streaming business looks healthier, while the company argues its old linear networks are better treated as content brands than businesses to spin off. Meanwhile, Netflix has the year's biggest show so far, AMC is bringing live concerts to theaters, and everyone keeps turning movies and TV into expanded universes.This week on The FULL Experience: Magnum, P.I. (708 - "Novel Connection")Next week: Murder, She Wrote (308: "Magnum on Ice")Subscribe, get expanded show notes, and past episodes at http://Cordkillers.comSupport Cordkillers at http://Patreon.com/CordkillersYouTube: https://youtu.be/pP_M6B9iPqg Hosted on Acast. See acast.com/privacy for more information.

Send us Fan MailOver $42 Billion is still on the table. Claim it?The business is shifting, but the money hasn't disappeared— On this episode of Film Hustlers, we're breaking down the cable movie - 15 days, 10 locations, and 8 or so characters. High-concept hooks lift eyebrows. Let's talk about a strategy to stay relevant.Key Highlights:The Outline is King: Why you should stop writing scripts and start perfecting the 21-page outline.The Cable Shift: How to make a $500k movie look like $5M.

How Replit's VP of Ops Runs an AI-Native Company (And Why Most Enterprises Are Still Getting It Wrong) Jonathan Eide has built and scaled operations at Meta, Coinbase, and now Replit, the company that's quietly become one of the fastest-growing AI-native businesses on the planet. In this conversation, he breaks down what's actually different about running a company where every function builds their own software, why "vibe coding" is too lightweight a term for what's coming, and the hiring shift every CXO will face in the next 24 months. If you're a CXO trying to figure out how to move your org from "we use Copilot" to genuinely agentic operations, this is the playbook. What we get into: The two archetypes Replit hires for, and why the "perfect candidate" has both Why Jon hasn't written a Linear ticket by hand in months (and what replaced it) The internal AI analyst tool that replaced an entire junior analyst function How Replit killed Google Slides internally with a self-updating, self-populating weekly wins deck Why measuring AI productivity by tokens or time saved is the wrong move (Theory of Constraints, applied) The hiring shift: from screening interviews to "build me a demo before we talk" What enterprise adoption actually looks like at Zillow, Atlassian, and old-school PE-backed manufacturers Why Replit's "plan" is to not have a plan, and why vision/mission still has to be rock solid The single-person companies hitting tens of millions in ARR Rapid fire: the deeply held belief about AI that Jon thinks will be gone by 2028 Chapters: 00:00 Intro 01:16 Jonathan Eide  02:00 What's fundamentally different about running ops at an AI-native company 04:20 How every function at Replit is building its own tools 07:35 Killing PowerPoint: the internal weekly wins deck built in Replit 11:35 Source of truth, guardrails, and avoiding the "everyone builds an app" sprawl 14:20 Can large or legacy companies actually adopt this operating model? 18:15 Why measuring tokens and time saved is the wrong way to track AI productivity 22:20 How Jon redesigned his interview process for AI-native hiring 25:35 Are AI-native companies hiring fewer people, or different people? 28:25 Why "AI native" will disappear as a hiring filter 29:15 Growing at Replit's pace: planning when the market resets every two weeks 32:24 Replit's three user segments: hobbyists, prosumer entrepreneurs, enterprise 34:41 Surprising businesses being built on Replit (and the single-person unicorn thesis) 37:30 The plan is to not have a plan: vision vs short-term flexibility 40:36 Rapid fire: the belief about AI that will be destroyed by 2028 41:32 Rapid fire: the one AI buzzword Jon would ban from Replit meetings 42:27 Rapid fire: what Jon is most optimistic about About Jonathan Eide: Jonathan is VP of Operations at Replit. Prior to Replit, he held senior operating roles at Coinbase and Meta, leading data and operations functions through hypergrowth phases at both. About the AI CXO Podcast: The AI CXO Podcast helps CXOs get actionable insights into how to navigate AI's reshaping of the business landscape. New episodes drop weekly. Subscribe for more conversations with operators building the AI-native enterprise. https://www.youtube.com/@productfaculty  #AI #Replit #CXO #VibeCoding #EnterpriseAI #AINative #AIAgents #FutureOfWork #ProductLeadership #Operations

In this episode, Zack Proser and Nick Nisi from WorkOS share what they've learned from building real-world AI tools and running high-impact workshops for AI engineers. We talk about finding "developer balance" by feeding biometric data into LLMs, the evolution of "skills" as a software primitive, and how to build seamless agentic loops that connect Slack, Linear, and Notion to eliminate context switching.Links:- WorkOS - Zack Proser - Nick Nisi 

This week, Paul starts with an update on how much broadcast viewership numbers have skewed to live sports since 2005. Next, they discuss Tupac's step-brother's wrongful death action against those involved in the killing of Tupac. Finally, Paul and Jess reflect on and reminisce about Kaufman Astoria studios, the iconic NYC film studio at the center of a $360M foreclosure. Learn more about your ad choices. Visit megaphone.fm/adchoices

"For the beautiful Section 4 of Flow, I wanted to celebrate the rewilding projects that took place between 2016 and 2022 under the LIFE Lech “Dynamic River System Lech” at Elmen-Nussau and Vorderhornbach."I was immediately inspired by the photo of the sound being recorded at the bridge. Imagining being in that moment, overlooking the meandering turquoise braids of water, the gravel beds and the dark green forests and wondering what the ecology of this area would be like and that I'd need to hike here one day. So I wanted to bring together an ecological sonic landscape."The river is played using a rainwater-filled glass harp, guided by the geomorphic imagery. Using a recurring motion of playing the top of a wine glass, I wanted to embody the water movement of the River Lech. Moving not as a straight line but more in swirls, spirals and circles, flowing left and right."Varying the level of rainwater in each glass created a scale of resonating frequencies that formed individual braids of the river. I found joy in playing the glasses in the imagery of this section of the River Lech. Occasionally, using a particular resistance when playing the glass to give a sense of friction against the gravel beds and under the bridges, sometimes slowing the pace of the river down afterwards."I used the field recording of the river to create artistic interpretations of ten animal vocalisations from birds, amphibians, fish, and insects. By selecting out the matching spectral vocal range of these species. Many of which were on the LIFE Lech's target list."A low D whistle creates the feel of a riparian forest. Researching the rewilding projects, I discovered the number of important plants in the area, such as Dwarf Bullrush and German Tamarisk, and that, in the summer months, over 6,000 Lady's-slipper Orchids inhabit the forest on the upper left side of this section of the river. Botanical drawings of these plants were turned into sonic spectrograms, which were blended into the piece."At the Elmen-Nussau location, 10 groynes on the left riverbank were shortened by a total of 280 m. Included as 10 slightly intrusive faded notes panned to the left at their rough positioning of where they once sat on the riverbed, before the first rewilding melody of the piece."At the Vorderhornbach location, Linear and cross constructions were shortened or removed over a 2 km length on both banks. A particularly forested section, here I have made this section of the piece fuller and wilder before the sounding of the “Hornbach” tributary line, which joins the River Lech, moves us into the melody for the second time."I loved the idea of connection with other parts of the river, with the river being an important corridor between different habitats. I incorporated 6 seconds of a sound bite called 'Dusty Stem' that Bill McKenna kindly donated from section 1. I have taken the sound bite down by 3 semitones, imagining it carried down the river through sections 2 and 3, and into 4."Section of the river Lech reimagined by Rachel Larsen-Jones. -------Flow is a creative exploration telling the story of a river through the power of sound. The project is a collaboration between the University of Padova and the University of Würzburg, with support from Cities and Memory. Explore the full project at https://citiesandmemory.com/flow.

Utilities are under pressure to deliver generation that is dispatchable, affordable, and clean enough to satisfy increasingly stringent environmental rules, notoriously hard to do in one asset. As renewables grow, the gas turbines and engines that have historically filled the gap come with a NOx problem, a CO2 problem, or both. Hydrogen offers a path through, but the supply isn't there yet. So what do you build today?Host Bridget van Dorsten is joined by Shannon Miller, CEO of Mainspring Energy, and Will Hazelip of National Grid Ventures, to dig into a technology most listeners haven't heard of and the first commercial hydrogen-powered deployment of it. Mainspring's 250-kilowatt linear generator is being installed at National Grid's 1,500 MW North Port facility on Long Island, in partnership with NYSERDA, the Long Island Power Authority, and Stony Brook University.Shannon explains how Mainspring redesigned the generator using the power electronics that drive solar inverters, batteries and EVs, replacing mechanical systems with software, eliminating the flame, and operating at temperatures low enough to take NOx out of the equation. An adaptive pressure cycle, software-controlled in real time, runs the same hardware on hydrogen, compressed natural gas, biogas, propane or blends, with no hardware change. The 250 kW form factor matters too: efficiency holds across the full load range, fleet redundancy replaces single-asset reliability risk, and deployment is a concrete pad plus electrical and fuel hookups rather than a multi-year build.Will frames the project against the regulatory backdrop. Long Island sits in a non-attainment zone for NOx, and New York's path to a carbon-free grid requires what the state calls a dispatchable emissions-free resource. The unit will run for 12 months on green hydrogen and on compressed natural gas, with Stony Brook measuring emissions and efficiency, NYSERDA watching for regulatory design, and National Grid building operational experience for the rest of its ageing fleet.The economic case rests on the alternative. New-build hydrogen-capable gas turbines run $3,500–$4,000/kW on capex (per Wood Mackenzie), with delivered power costs reaching $300–$900/MWh once hydrogen is layered in. Shannon's point is that committing to a single-fuel turbine only pays off if the fuel actually arrives at the scale and price you assumed. With hydrogen supply uncertain, that's a stranded-asset risk linear generators avoid by running on whatever fuel is available today. Will adds the carbon-market angle saying that as carbon pricing develops, real-time fuel switching becomes an optimisation lever, not just a hedge.Then there's the supply reality. Total US hydrogen production today isn't enough to fuel a single 500 MW power plant, and with 45V tax credit requirements tightening and federal climate policy in flux, the gap between hydrogen ambition and supply isn't closing fast. Will's suggests starting with the fuels that exist today and scale into hydrogen as supply grows.The episode closes on demand. Mainspring's factory produces 325 MW a year today and can roughly double in 12–15 months, with pull from industrial customers, data centres and AI infrastructure, and utilities at once, driven by the same problem: nobody can get power fast enough.This episode is sponsored by GridBeyond. Energy asset owners face a critical challenge: how to optimize performance and drive new revenue in competitive, fast-moving markets. GridBeyond solves this through AI-powered forecasting, energy trading and optimization. GridBeyond's platform delivers: Precision forecasting to anticipate market opportunities Intelligent market access across multiple revenue streams Real-time control that responds instantly to market conditions Optimization that combines AI insights with expert oversight Whether you're managing batteries, gas peakers, hybrid sites, or complex multi-asset portfolios, GridBeyond helps you turn assets into high-performance revenue machines. The proven platform has helped businesses across the energy sector maximize returns and accelerate their energy transition. Want to learn more? Visit go.gridbeyond.com/recharged https://go.gridbeyond.com/recharged See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Have you ever thought, “I was doing better, so why am I falling apart again?” In this episode, I want to reassure you that you are not back at the beginning, you are not failing, and you are not doing grief wrong. Grief was never meant to move in a straight line. Tune in this week to learn why grief isn't linear, why the traditional idea of “stages” can make us judge ourselves, and why recurring grief waves do not mean something has gone wrong. Instead, I'll show you how to think about grief as a spiral: layered, human, and always meeting you from a new place. Get full show notes, transcript, and more information here: https://www.coachingwithkrista.com/362 Follow me on Instagram: https://www.instagram.com/lifecoachkrista/Mentioned in this episode:Join Grief Essentials!Designed especially for widows, Grief Essentials offers the perfect combination of powerful tools and support, along with accurate information about grief, so widowhood gets easier. Click here to find out more: https://the-widowed-mom-podcast.captivate.fm/griefessentialsJoin Grief Essentials!

In this episode of Automation Ladies, we step away from the technology and talk about something just as important: the people behind it.From nonlinear career paths to the pressure of “doing everything right,” this conversation dives into what work really looks like in today's world, especially in industrial automation and manufacturing.Our guest shares her journey from engineering to technical writing and media, proving that careers don't have to follow a straight line to be meaningful. Along the way, we explore how skills evolve, why curiosity matters more than rigid plans, and how combining different strengths can open unexpected doors.We also get into the realities we don't talk about enough at work: – Managing stress while staying professional – Balancing personal life with career demands – Navigating uncertainty in a rapidly changing industry – Learning to lead, grow, and stay human in the processThis episode is a reminder that behind every job title is a real person, figuring things out, adapting, and trying to make an impact.If you've ever questioned your path, felt stuck, or wondered what's next in your career, this conversation is for you.Support the show__________________________________________________________________

(VIDEO PODCAST)We talk a lot about momentum in voiceover, but what happens when life interrupts that momentum?In this episode of Speechless VO, Aimee Gironimi shares her journey navigating a voiceover career while facing ongoing health challenges, multiple surgeries, and a diagnosis of Ehlers-Danlos Syndrome.This conversation explores what it means to stay relevant, productive, and connected when your path isn't linear, and why redefining success may be the most important shift you can make.If you've ever felt like you're falling behind, this episode offers a different perspective. You may not be behind at all! You may just be building your career in a different way.Sign up for our show takeaways, resources, and drink recipes before episodes air here: ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ https://www.speechlessvo.com/⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠RESOURCES mentioned in this episode:Disabled Voice Actors DatabaseNAVA – National Association of Voice ActorsAimee's Demo Services (“VO Demos à la Carte”)Ehlers-Danlos Syndrome awarenessCONTACT INFO:⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Podcast Home⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Website⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠YouTube⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Instagram⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Email: SpeechlessVO@gmail.comPRODUCTION CREDITS:Music: Rick WilsonEditing: Hamza LatifWritten and Produced by ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Kim Wilson⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠ and ⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Natasha Marchewka⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠⁠Production Assistant: Carolyn Robson

Send us Fan MailWhat do you know about “trans time?” I had never heard the term before my interview with poet and educator, Alexis N. Garcia, but in this episode of Dem Bois Podcast, Alexis teaches all about this concept and more! In this episode, Alexis also discusses their identity, exploring themes of gender, ancestry, and the importance of community. They reflect on the role of play and imagination in our lives, the journey of writing and creativity, the significance of support systems, and the essence of freedom. We talk:2:44 - Exploring identity and ancestry18:26 - The journey of gender and transition33:21 - Healing generational trauma40:05 - Understanding “Trans Time” and nonlinear existence54:35 - Support systems and community connectionsEpisode References:Octavia ButlerCaro De RobertisTina Aguirre The Hips on the Drag Queen Go Swish, Swish, SwishRead more about Alexis is their bio below:Alexis N. Garcia is a t-boy poet & educator dreaming against the state. Their cross-discipline experiments glitch traditional poetic form to construct trans time & non-linear meaning-making. You can find their work in The Hopkins Review, Poets.org's “Poem-A-Day” series, The Slowdown, The Best of the Net Anthology 2022, among others. Aceves Garcia has received fellowships from The Outpost Foundation, Jack Jones Literary Arts, and the Tin House Summer Workshop. Their latest callings include bringing plant offerings to the ocean and escaping linear time. Instagram loveloaf_ alexisacevesgarcia.comCelebrate 10 years of Dem Bois Inc.!2026 marks ten years of Dem Bois Inc. To honor this milestone, we invite you to join our 10 for 10 campaign by giving $10 a month to help sustain the care, leadership, and visibility that trans men of color deserve.Your support helps build a future rooted in care, visibility, and possibility.Donate today!Donate today to support Transmasc Gender Affirming Grants and Community Wellness Packages for Trans Men of Color!The  Visibility = Possibility™️ Merch is here! - Not just merch, but a movement! Dem Bois Community Voices Facebook Group is a safe, moderated sanctuary where trans men of color can connect authentically, discuss podcast episodes, share powerful experiences, and build support networks. Dem Bois YouTube Channel! - @demboisinc - Exclusive content you won't find anywhere else!

Host Kevin Gormley is joined once again by Alex Whelan from Kaplan to help candidates prepare for the May Operational Case Study (OCS) exam. Whether you're early in your preparation or refining your technique, Kevin and Alex provide practical insights to help you focus on what matters most: applying your knowledge to the case with confidence. Good luck to all candidates! Building on the popularity of their February episode, Kevin and Alex focus on the May case study scenario featuring SOPA, a family‑owned restaurant business operating in a competitive market. The discussion provides practical guidance on how students should interpret the pre‑seen, identify exam‑relevant issues, and approach answers across all OCS core activities.  This episode is especially valuable for candidates sitting their first CIMA Case Study exam and transitioning from Objective tests to a fully integrated, scenario‑based assessment. It  offers a concise but comprehensive roadmap for tackling the May 2026 OCS exam.  Key Topics Covered Case Study Overview: SOPA SOPA is a family‑owned restaurant chain operating across nine locations. The business operates in a highly competitive hospitality sector with tightening margins. Strong revenue growth and profitability, but operational and strategic risks are emerging. Heavy reliance on customer reviews, staff morale, and brand reputation. Industry themes include: Rising labour and food costs Low consumer confidence Staffing shortages Cost‑of‑living pressures   Strengths and Risks in the Pre‑Seen: Positives Strong revenue and gross margin growth (outperforming the market) Healthy cash position and working capital Loyal customer base and sustainability credentials Standardised menus and processes   Strengths and Risks in the Pre‑Seen: Risks & Weaknesses Declining customer reviews High staff turnover and morale concerns High fixed‑cost base Dependence on single suppliers Potential over‑expansion risks   Expansion & Strategic Decisions Potential exam‑relevant initiatives discussed in the pre‑seen included: Opening new restaurants Launching a ghost kitchen Developing a branded dips product line Entering a new foreign market Exploring AI and digital ordering technology The move from B2C to B2B activities is highlighted as a significant operational and financial risk area that candidates should prepare to address.   Exam Focus: Core Activities Breakdown Alex walks through all six OCS core activities, highlighting what candidates should expect and where SOPA‑specific issues may arise: Core Activity A – Costing Marginal costing vs absorption costing New syllabus focus: Environmental and quality costing Digital vs traditional costing (apps, online ordering, IT support costs) Cost of quality (prevention, appraisal, internal & external failure) Core Activity B – Budgeting & Forecasting Incremental vs zero‑based budgeting (ZBB) Forecasting and seasonal trends Rolling budgets and beyond budgeting Importance of clearly explaining ZBB steps Core Activity C – Performance Management KPIs (occupancy rates, sustainability, quality, staff metrics) Variance analysis (including mix variances) Use of attachments and data in answers Core Activity D – Accounting & Reporting Reduced weighting but still examinable PPE decisions (buy vs lease) Inventory valuation (IAS 2) Capitalisation and depreciation Implications of sustainability investments (e.g. vertical farming) Core Activity E – Decision Making Relevant and incremental cash flows Outsourcing vs in‑house production (dips, ghost kitchen) Decision trees and expected values Linear programming and constraints Weighted average benefit analysis Core Activity F – Risk & Working Capital Inventory management (EOQ vs JIT) Working capital cycle (negative cycle at SOPA) Receivables emergence from B2B expansion Factoring and invoice discounting Cash surplus management and over‑trading risks How the Exam Is Marked Alex explains CIMA's four assessment pillars: Technical understanding Communication & professional tone Use of information provided (attachments) Application to the scenario   Key advice Refer to SOPA frequently — name the company, people, products, and locations. Use clear sub‑headings and structured answers. Justify recommendations clearly. Use planning time effectively. No calculations required — focus on explanation and application. Exam Tips & Final Advice Expect questions around ghost kitchens, expansion, and B2B risks Practice with mock exams and review model answers Focus on structure, relevance, and professionalism Remember: you must advise SOPA, not write generic theory Useful Links Finance Leadership Program: https://enroll.cgma.org CGMA Hub with Case Study Resources & Mock Exams Thanks for listening. It takes just a couple of minutes to share your feedback here. About Us The CGMA Finance Leadership Programme (FLP) is the online pathway to the prestigious Chartered Institute of Management Accountants' Professional Qualification. Find out more about the FLP at https://enroll.cgma.org/ Get in touch with show host Kevin Gormley via LinkedIn. Contact the podcast team at podcast@aicpa-cima.com This is a podcast from AICPA & CIMA, together as the Association of International Certified Professional Accountants. To enjoy more conversations from our global community of accounting and finance professionals, explore our network of free shows here.  

In a market that hadn't changed in decades, Linear didn't win by being faster. They won by being more thoughtful.Karri Saarinen helped shape design at Airbnb and Coinbase before building Linear around small teams and high standards.On Grit, he shares how Linear is building for a new era of software development.Guest: Karri Saarinen, co-founder and CEO of LinearConnect with Karri SaarinenXLinkedInConnect with Josh Coyne:XLinkedInConnect with Joubin:XLinkedInEmail: grit@kleinerperkins.comFollow on LinkedInFollow on X​Learn more about Kleiner Perkins

In this episode, Tyler Clark and Coleman Ayers sit down with Vitor to dive deep into the realities of player development, coaching philosophy, and what it actually takes to build high-level athletes. The conversation explores how development is rarely linear, emphasizing the importance of adaptability, long-term thinking, and understanding each athlete as an individual rather than forcing them into a rigid system. Vitor shares insights from his own experiences working with players, highlighting how context, environment, and decision-making shape real growth far more than isolated drills or traditional methods.The discussion also touches on practice design, communication, and the balance between structure and freedom in training. Vitor breaks down how coaches can better create environments that encourage problem-solving, ownership, and creativity, while still maintaining standards and accountability. From rethinking skill development to building more effective learning environments, this episode offers practical and philosophical insights for coaches looking to elevate both their players and their approach.00:00 – Introduction to Vitor and his coaching background 02:10 – Early influences and approach to player development 05:30 – Why development isn't linear 08:15 – Individualizing training vs. system-based coaching 12:00 – The role of environment in shaping players 15:40 – Common mistakes coaches make in development 19:20 – Balancing structure and freedom in practice 23:10 – Encouraging decision-making and player ownership 27:00 – Moving away from rigid, drill-based training 31:45 – Communication and building trust with players 36:20 – Creating competitive and engaging practice environments 40:10 – Adapting to different types of athletes 44:30 – The importance of long-term development over short-term results 48:00 – How coaches can continue to improve and evolve 52:10 – Final thoughts and key takeawaysCoaching ResourcesBAM Coaches Platform: https://byanymeanscoaches.com/BAM Blueprint Book: https://byanymeanscoaches.com/blueprint-bookIf you enjoyed this episode, share it with another coach who's serious about player development. Make sure to subscribe, leave a review, and stay connected with By Any Means Basketball for more insights on coaching, training, and building better athletes.

RockShox Zeb fork is all-new for model year 2027. They've taken what they learned developing the latest Boxxer, and have applied many of the same technologies and tuning ideologies to their single-crown, gravity fork.Vital editor, Jason Schroeder, has spent the past few months testing the fork and runs you through everything that's new, and how it's performed so far.More info - https://www.vitalmtb.com/forums/hub/2027-rockshox-zeb-fork-tech-info-impressions-discussion 0:00 - Intro0:25 - Chassis Updates0:46 - New fenders1:05 - New pressure relief valves1:16 - Linear XL air spring details1:42 - AirAnnex chamber2:01 - new Adjustable Bottom Out (ABO) feature2:51 - New stanchions detail3:08 - ButterWagon Tech - divots in the stanchion3:31 - Charger 3.2 damper updates3:38 - Oil, seals, grease updates4:20 - Zeb Product Line5:06 - Setting up the new Zeb5:25 - Damper settings6:10 - Air pressure settings6:56 - Linear XL air spring positives7:49 - Linear XL air spring negatives8:34 - ABO impressions 10:05 - Zeb's versatility 10:46 - Bottom Line on the new Zeb

Many brands treat Connected TV like another form of digital advertising. That's a mistake.This week, we're sharing a bonus episode with a special presentation from Shoptalk. Catherine Walstad, Chief Media Officer at Marketing Architects, breaks down the most common CTV myths and explains what smarter TV buying actually looks like. From frequency management to targeting accuracy to ad fraud, Catherine covers the traps brands fall into and the strategies that get results.Topics covered: [01:00] Why CTV is not just another digital channel [03:00] How frequency becomes waste faster than you think [04:00] Why premium inventory doesn't guarantee better performance [05:00] Ad fraud, poor supply, and wasted CTV impressions [06:00] The limitations of IP-based targeting [07:00] Why CTV measurement produces conflicting answers To learn more, visit marketingarchitects.com/podcast or subscribe to our newsletter at marketingarchitects.com/newsletter.   Resources: Watch: TV Like Digital and Other CTV Myths Catherine's LinkedIn  

In this original What the Dementia episode, we will discuss why dementia progression is not always linear and why caregivers may notice good days, bad days, or sudden changes in a partner's abilities. Understanding these patterns can help caregivers better interpret changes and respond more effectively as needs shift over time.This episode will cover:— Why dementia progression is not always predictable— How different types of dementia may progress— Why abilities can fluctuate from day to day— Factors that can temporarily worsen dementia symptoms— How caregivers can adapt when abilities changeMENTIONED IN EPISODE | Newsletter | ⁠https://letsbambu.com/newsletter⁠CONNECT, GET RESOURCES, LEARN MORE, + SIMPLIFY YOUR CARE JOURNEY:LinkTree | ⁠⁠⁠⁠⁠https://www.letsbambu.com/b/linktree⁠⁠⁠⁠⁠MUSIC CREDIT: Listen To SpillageVillage - Tropical Landing Pop Songs At Looperman.com DISCLAIMER: The information contained in Bambu Care LLC's website, blog, emails, programs, services and/or products is for educational and informational purposes only. While we draw on our prior professional expertise and background in other areas, you acknowledge that we are supporting you in our role exclusively as a Dementia Care Consultant. By participating in Bambu Care, LLC's website, blog, emails, programs, services and/or products, you acknowledge that we are not a licensed psychologist, professional counselor, or medical doctor. We in no way, diagnose, treat, or cure any illnesses or diseases. Dementia Care Consulting is in no way to be construed or substituted as psychological counseling or any other type of therapy or medical advice. The information provided by Bambu Care, LLC also does not constitute legal or financial advice nor is intended to be. Dementia Care Consulting is not a substitute for the services of a CPA or attorney.

Today, I'm sharing a simple truth that often goes unspoken: life is not linear. We're conditioned to believe that progress should be a steady, upward journey, but what if our lives actually operate in cycles, not straight lines? I'm unpacking the "momentum cycle" and exploring why your energy, creativity, and focus naturally ebb and flow through distinct seasons—surges of expansion, hard stops of crisis, the uncertainty of transitions, and the necessity of recovery—and why striving to always be at your peak can actually hinder your progress. If you're tired of measuring your life against an unfair expectation of nonstop achievement, tune in for fresh insights on honoring your energy, matching your actions to your current season, and finding power, even in the pauses.  Show Highlights: Details of Kate Northrup's upcoming money workshop. [00:59] The fallacy that life is linear vs. the "momentum cycle." [03:44] The highs and gradual low of growth and expansion. [07:31] Navigating crisis periods with focus. [09:40] How transition and change can become accelerators. [12:49] Do you allow yourself time to recover and heal? [16:59] Suffering due to misaligned output and capacity. [21:00] How can you honor your human limits? [24:57] The power and opportunity in pausing. [26:24] Find out whether you're in sync with your phase. [28:53] The joy of trusting the cycle and celebrating others' wins. [30:00] To register for Good with Money click here: https://thefreefam.ontraport.net/t?orid=497195&opid=170 Subscribe to the Brilliant Balance Weekly: www.brilliant-balance.com/weekly Follow Cherylanne on Instagram: www.instagram.com/cskolnicki

I am back. After a year of silence on this platform, I am returning with one of the most honest, most personal, and most powerful episodes I have ever recorded. 2025 brought a series of events that no one plans for and no one sees coming. My business was closed without warning, I navigated a difficult personal transition, and I lived through the kind of year that tests everything you say you believe about resilience, leadership, and growth.This episode is not a recap. It is a reckoning and an invitation. I am unpacking why I chose to pause rather than perform, what I learned in the silence, and why I believe the hardest seasons of our lives are also the most clarifying ones. If you have ever found yourself in a chapter you did not choose, starting over when you were not ready, or wondering whether the pause you are in means you are falling behind, this episode was made for you.ABOUT MEI am a former educator turned entrepreneur, leadership developer, and mentor who has spent over a decade coaching people toward lives and businesses they are genuinely proud of. I have had the privilege of working alongside world-renowned leadership authority Dr. John C. Maxwell, contributing to leadership conferences, digital courses, and educational materials.  I created the Brewing Success Podcast because I believe that meaningful growth happens in conversation, and that the right idea at the right moment can change the entire trajectory of a life.CONNECT WITH MEFind me on Instagram, join the Brewing Success Community, and get your copy of the ABC's of Leadership Mentoring Journal at leadlikeandreagebhardt.com.

We're proud to release this ahead of Ryan's keynote at AIE Europe. Hit the bell, get notified when it is live! Attendees: come prepped for Ryan's AMA with Vibhu after.Move over, context engineering. Now it's time for Harness engineering and the age of the token billionaires.Ryan Lopopolo of OpenAI is leading that charge, recently publishing a lengthy essay on Harness Eng that has become the talk of the town:In it, Ryan peeled back the curtains on how the recently announced OpenAI Frontier team have become OpenAI's top Codex users, running a >1m LOC codebase with 0 human written code and, crucially for the Dark Factory fans, no human REVIEWED code before merge. Ryan is admirably evangelical about this, calling it borderline “negligent” if you aren't using >1B tokens a day (roughly $2-3k/day in token spend based on market rates and caching assumptions):Over the past five months, they ran an extreme experiment: building and shipping an internal beta product with zero manually written code. Through the experiment, they adopted a different model of engineering work: when the agent failed, instead of prompting it better or to “try harder,” the team would look at “what capability, context, or structure is missing?”The result was Symphony, “a ghost library” and reference Elixir implementation (by Alex Kotliarskyi) that sets up a massive system of Codex agents all extensively prompted with the specificity of a proper PRD spec, but without full implementation:The future starts taking shape as one where coding agents stop being copilots and start becoming real teammates anyone can use and Codex is doubling down on that mission with their Superbowl messaging of “you can just build things”.Across Codex, internal observability stacks, and the multi-agent orchestration system his team calls Symphony, Ryan has been pushing what happens when you optimize an entire codebase, workflow, and organization around agent legibility instead of human habit.We sat down with Ryan to dig into how OpenAI's internal teams actually use Codex, why the real bottleneck in AI-native software development is now human attention rather than tokens, how fast build loops, observability, specs, and skills let agents operate autonomously, why software increasingly needs to be written for the model as much as for the engineer, and how Frontier points toward a future where agents can safely do economically valuable work across the enterprise.We discuss:* Ryan's background from Snowflake, Brex, Stripe, and Citadel to OpenAI Frontier Product Exploration, where he works on new product development for deploying agents safely at enterprise scale* The origin of “harness engineering” and the constraint that kicked off the whole experiment: Ryan deliberately refused to write code himself so the agent had to do the job end to end* Building an internal product over five months with zero lines of human-written code, more than a million lines in the repo, and thousands of PRs across multiple Codex model generations* Why early Codex was painfully slow at first, and how the team learned to decompose tasks, build better primitives, and gradually turn the agent into a much faster engineer than any individual human* The obsession with fast build times: why one minute became the upper bound for the inner loop, and how the team repeatedly retooled the build system to keep agents productive* Why humans became the bottleneck, and how Ryan's team shifted from reviewing code directly to building systems, observability, and context that let agents review, fix, and merge work autonomously* Skills, docs, tests, markdown trackers, and quality scores as ways of encoding engineering taste and non-functional requirements directly into context the agent can use* The shift from predefined scaffolds to reasoning-model-led workflows, where the harness becomes the box and the model chooses how to proceed* Symphony, OpenAI's internal Elixir-based orchestration layer for spinning up, supervising, reworking, and coordinating large numbers of coding agents across tickets and repos* Why code is increasingly disposable, why worktrees and merge conflicts matter less when agents can resolve them, and what it really means to fully delegate the PR lifecycle* “Ghost libraries”, spec-driven software, and the idea that a coding agent can reproduce complex systems from a high-fidelity specification rather than shared source code* The broader future of Frontier: safely deploying observable, governable agents into enterprises, and building the collaboration, security, and control layers needed for real-world agentic workRyan Lopopolo* X: https://x.com/_lopopolo* Linkedin: https://www.linkedin.com/in/ryanlopopolo/* Website: https://hyperbo.la/contact/Timestamps00:00:00 Introduction: Harness Engineering and OpenAI Frontier00:02:20 Ryan's background and the “no human-written code” experiment00:08:48 Humans as the bottleneck: systems thinking, observability, and agent workflows00:12:24 Skills, scaffolds, and encoding engineering taste into context00:17:17 What humans still do, what agents already own, and why software must be agent-legible00:24:27 Delegating the PR lifecycle: worktrees, merge conflicts, and non-functional requirements00:31:57 Spec-driven software, “ghost libraries,” and the path to Symphony00:35:20 Symphony: orchestrating large numbers of coding agents00:43:42 Skill distillation, self-improving workflows, and team-wide learning00:50:04 CLI design, policy layers, and building token-efficient tools for agents00:59:43 What current models still struggle with: zero-to-one products and gnarly refactors01:02:05 Frontier's vision for enterprise AI deployment01:08:15 Culture, humor, and teaching agents how the company works01:12:29 Harness vs. training, Codex model progress, and “you can just do things”01:15:09 Bellevue, hiring, and OpenAI's expansion beyond San FranciscoTranscriptRyan Lopopolo: I do think that there is an interesting space to explore here with Codex, the harness, as part of building AI products, right? There's a ton of momentum around getting the models to be good at coding. We've seen big leaps in like the task complexity with each incremental model release where if you can figure out how to collapse a product that you're trying to.Build a user journey that you're trying to solve into code. It's pretty natural to use the Codex Harness to solve that problem for you. It's done all the wiring and lets you just communicate in prompts. To let the model cook, you have to step back, right? Like you need to take a systems thinking mindset to things and constantly be asking, where is the Asian making mistakes?Where am I spending my time? How can I not spend that time going forward? And then build confidence in the automation that I'm putting in place. So I have solved this part of the SDLC.swyx: [00:01:00] All right.[00:01:03] Meet Ryan swyx: We're in the studio with Ryan from OpenAI. Welcome.Ryan Lopopolo: Hi,swyx: Thanks for visiting San Francisco and thanks for spending some time with us.Ryan Lopopolo: Yeah, thank you. I'm super excited to be here.swyx: You wrote a blockbuster article on harness engineering. It's probably going to be the defining piece of this emerging discipline, huh?Ryan Lopopolo: Thank you. It is it's been fun to feel like we've defined the discourse in some sense.swyx: Let's contextualize a little bit, this first podcast you've ever done. Yes. And thank you for spending with us. What is, where is this coming from? What team are you in all that jazz?Ryan Lopopolo: Sure, sure.Ryan Lopopolo: I work on Frontier Product Exploration, new product development in the space of OpenAI Frontier, which is our enterprise platform for deploying agents safely at scale, with good governance in any business. And. The role of VMI team has been to figure out novel ways to deploy our models into package and products that we can sell as solutions to enterprises.swyx: And you have a background, I'll just squeeze it in there. Snowflake, brick, [00:02:00] stripe, citadel.Ryan Lopopolo: Yes. Yes. Same. Any kind of customerswyx: entire life. Yes. The exact kind of customer that you want to,Vibhu: so I'll say, I was actually, I didn't expect the background when I looked at your Twitter, I'm seeing the opposite.Stuff like this. So you've got the mindset of like full send AI, coding stuff about slop, like buckling in your laptop on your Waymo's. Yes. And then I look at your profile, I'm like, oh, you're just like, you're in the other end too. Oh, perfect. Makes perfect.Ryan Lopopolo: I it's quite fun to be AI maximalist if you're gonna live that persona.Open eye is the place to do it. And it'sswyx: token is what you say.Ryan Lopopolo: Yeah. Certainly helps that we have no rate limits internally. And I can go, like you said, full send at this stay.swyx: Yeah. Yeah. So the Frontier, and you're a special team within O Frontier.Ryan Lopopolo: We had been given some space to cook, which has been super, super exciting.[00:02:47] Zero Code ExperimentRyan Lopopolo: And this is why I started with kind of a out there constraint to not write any of the code myself. I was figuring if we're trying to make agents that can be deployed into end to enterprises, they should be [00:03:00] able to do all the things that I do. And having worked with these coding models, these coding harnesses over 6, 7, 8 months, I do feel like the models are there enough, the harnesses are there enough where they're isomorphic to me in capability and the ability to do the job.So starting with this constraint of I can't write the code meant that the only way I could do my job was to get the agent to do my job.Vibhu: And like a, just a bit of background before that. This is basically the article. So what you guys did is five months of working on an internal tool, zero lines of code over a mi, a million lines of code in the total code base.You say it was cenex, more like it was cenex faster than you would've. If you had done it by end. SoRyan Lopopolo: yeah, thatVibhu: was the mindset going into this, right?Ryan Lopopolo: That's right.[00:03:46] Model Upgrades LessonsRyan Lopopolo: Started with some of the very first versions of Codex CLI, with the Codex Mini model, which was obviously much less capable than the ones we have today.Which was also a very good constraint, right? Quite a visceral feeling to ask the [00:04:00] model to build you a product feature. And it just not being able to assemble the pieces together.Which kind of defined one of the mindsets we had for going into this, which is whenever the model just cannot, you always pop open at the task, double click into it, and build smaller building blocks that then you can reassemble into the broader objective.And it was quite painful to do this. Honestly, the first month and a half was. 10 times slower than I would be. But because we paid that cost, we ended up getting to something much more productive than any one engineer could be because we built the tools, the assembly station for the agent to do the whole thing.[00:04:43] Model Generations, Build Systems & Background ShellsRyan Lopopolo: But yeah, so onward to G BT 5, 5, 1, 5, 2, 5, 3, 5 4. To go through all these model generations and see their kind of corks and different working styles also meant we had to adapt the code base to change things up when the model was revved. [00:05:00] One interesting thing here is five two, the Codex harness at the time did not have background shells in it, which means we were able to rely on blocking scripts to perform long horizon work.But with five, three and background shells, it became less patient, less willing to block. So we had to retool the entire build system to complete in under a minute and. This is not a thing I would expect to be able to do in a code base where people have opinions. But because the only goal was to make the Asian productive over the course of a week, we went from a bespoke make file build to Basil, to turbo to nx and just left it there because builds were fast at that point.swyx: Interesting. Talk more about Turbo TenX. That's interesting ‘cause that's the other direction that other people have been doing.Ryan Lopopolo: Ultimately I have. Not a lot of experience with actual frontend repo architecture.swyx: You're talking that Jessica built the sky. So I'm like, I know the NX team. I know Turbo from Jared [00:06:00] Palmer.And I'm like, yeah, that's an interesting comparison.[00:06:02] One Minute Build LoopRyan Lopopolo: The hill we were climbing right, was make it fast.swyx: Is there a micro front end involved? Is it how how complex reactRyan Lopopolo: electron base single app sort of thingswyx: And must be under a minute. That's an interesting limitation. I'm actually not super familiar with the background shelf stuff.Probably was talked about in the fight three release.Ryan Lopopolo: BA basically means that codex is able to spawn commands in the background and then go continue to work while it waits for them to finish. So it can spawn an expensive build and then continue reviewing the code, for example.swyx: Yeah.Ryan Lopopolo: And this helps it be more time efficient for the user invoking the harness.swyx: And I guess and just to really nail this, like what does one minute matter? Like why not five, okay, good. We want no. WeRyan Lopopolo: want the inner loop to be as fast as possible. Okay. One minute was just a nice round number and we were able to hit it.swyx: And if it doesn't complete, it kills it or some something,Ryan Lopopolo: No.We just take that as a signal that we need to stop what we're doing, double click, decompose a build graph a bit to get us to high back under so that we [00:07:00] can able the agent continue to operate.swyx: It's almost like you're, it's like a ratchet. It's like you're forcing build time discipline, because if you don't, it'll just grow and grow.That's right. And you mentioned that my current, like the software I work on currently is at 12 minutes. It sucks.Ryan Lopopolo: This has been my experience with platform teams in the past, where you have an envelope of acceptable build times and you let it go up to breach and then you spend two, three weeks to bring it back down to the lower end of the average low bed stop.But because tokens are so cheap Yeah. And we're so insanely parallel with the model, we can just constantly be gardening this thing to make sure that we maintain these in variants, which means. There's way less dispersion in the code and the SDLC, which means we can simplify in a way and rely on a lot more in variance as we write the software.[00:07:45] Observability, Traces & Local Dev StackVibhu: Lovely.[00:07:46] Humans Are BottleneckVibhu: You mentioned in your article, like humans became the bottleneck, right? You kicked off as a team of three people. You're putting out a million line of code, like 1500 prs, basically. What's the mindset there? So as much as code is disposable, you're doing a lot of review. A lot [00:08:00] of the article talks about how you wanna rephrase everything is prompting everything, is what the agent can't see.It's kind of garbage, right? You shouldn't have it in there. So what's like the high level of how you went about building it, and then how you address okay, humans are just PR review. Like how is human in the loop for this?Ryan Lopopolo: We've moved beyond even the humans reviewing the code as well.[00:08:19] Human Review, PR Automation & Agent Code ReviewRyan Lopopolo: Most of the human review is post merge at this point.But post, post merge, that's not even reviewed. That's justswyx: Oh, let's just make ourselves happy by YouRyan Lopopolo: haven't used fundamentally. The model is trivially paralyzable, right? As many GPUs and tokens as I am willing to spend, I can have capacity to work with my hood base.The only fundamentally scarce thing is the synchronous human attention of my team. There's only so many hours in the day we have to eat lunch. I would like to sleep, although it's quite difficult to, stop poking the machine because it makes me want to feed it. You have to step back, right?Like you need to take a systems thinking mindset to things and [00:09:00] constantly be asking where is the agent making mistakes? Where am I spending my time? How can I not spend that time going forward? And then build confidence in the automation that I'm putting in place. So I have solved this part of the SDLC, and usually what that has looked like is like we started needing to pay very close attention to the code because the agent did not have the right building blocks to produce.Modular software that decomposed appropriately that was reliable and observable and actually accrued a working front end in these things, right?[00:09:35] Observability First SetupRyan Lopopolo: So in order to not spend all of our time sitting in front of a terminal at most, doing one or two things at a time, invested in giving the model that observability, which is that that graph in the post here.swyx: Yeah. Let's walk through this traces and which existed firstRyan Lopopolo: we started with just the app and the whole rest of it. From vector through to all these login metrics, APIs was, I dunno, half an [00:10:00] afternoon of my time. We have intentionally chosen very high level fast developer tools. There's a ton of great stuff out there now.We use me a bunch, which makes it trivial to pull down all these go written Victoria Stack binaries in our local development. Tiny little bit of python glue to spin all these up. And off you go. One neat thing here is we have tried to invert things as much as possible, which is instead of setting up an environment to spawn the coding agent into, instead we spawn the coding agent, like that's the entry point.It's just Codex. And then we give Codex via skills and scripts the ability to boot the stack if it chooses to, and then tell it how to set some end variables. So the app and local Devrel points at this stack that it has chosen to spin up. And this I think is like the fundamental difference between reasoning models and the four ones and four ohs of the past, where these models could not think so you had to put them in [00:11:00] boxes with a predefined set of state transitions.Whereas here we have the model, the harness be the whole box. And give it a bunch of options for how to proceed with enough context for it to make intelligent choices. SoVibhu: sales, so like a lot of that is around scaffolding, right? Yes. Previous agents, you would define a scaffold. It would operate in that.Lube, try again. That's pivoted off from when we've had reasoning models. They're seeming to perform better when you don't have a scaffold, right? That's right.[00:11:28] Docs Skills GuardrailsVibhu: And you go into like niches here too, like your SPEC MD and like having a very short agent MG Agent md.swyx: Yes. Yes.Vibhu: Yeah. So you even lay out what it is here, but I likeswyx: the table contents.Vibhu: Yeah.swyx: Like stuff like this, it really helps guide people because everyone's trying to do this.Ryan Lopopolo: This structure also makes it super cheap to put new content into the repository to steer both the humans and the agents.swyx: You, you reinvented skills, right?Vibhu: One big agents andswyx: skills from first princip holdsRyan Lopopolo: all skills did not exist when we started doing this.Vibhu: You have a short [00:12:00] one 100 line overall table of contents and then you have little skills, right? Core beliefs, MD tech tracker. Yeah. Yeah. The scale is overRyan Lopopolo: The tech jet tracker and the quality score are pretty interesting because this is basically a tiny little scaffold, like a markdown table, which is a hook for Codex to review all the business logic that we have defined in the app, assess how it matches all these documented guardrails and propose follow up work for itself.Before beads and all these ticketing systems, we were just tracking follow up work as notes in a markdown file, which, we could spa an agent on Aron to burn down. There's this really neat thing that like the models fundamentally crave text. So a lot of what we have done here is figure out ways to inject textswyx: intoRyan Lopopolo: the system right when we get a page, because we're missing a timeout, for example.I can just add Codex in Slack on that page and say, I'm gonna fix this by adding a timeout. Please update our reliability documentation. To require that all network calls have [00:13:00] timeouts. So I have not only made a point in time fix, but also like durably encoded this process knowledge around what good looks like.swyx: Yeah.Ryan Lopopolo: And we give that to the root coding agent as it goes and does the thing. But you can also use that to distill tests out of, or a code review agent, which is pointed at the same things to narrow the acceptable universe of the code that's produced.swyx: I think one of the concerns I have with that kind of stuff is you think you're making the right call by making, it's persisted for all time across everything.Yes. But then you didn't think about the exceptions that you need to make, right? And that you have to roll it back.Vibhu: Part of it isswyx: also sometimes it can follow your s instructions too.Vibhu: It's somewhat a skill, right? So it determines when it uses the tools, right? Like it's not like it'll run outta every call.It'll determine when it wants to check quality score, right?Ryan Lopopolo: Yeah. And we do in the prompts we give these agents, allow them to push back,[00:13:51] Agent Code Review RulesRyan Lopopolo: When we first started adding code review agents to the pr, it would be Codex, CLI. Locally writes the change, pushes up a PR on [00:14:00] those PR synchronizations of review agent fires.It posts a comment. We instruct Codex that it has to at least acknowledge and respond to that feedback. And initially the Codex driving the code author was willing to be bullied by the PR reviewer, which meant you could end up in a situation where things were not converging. So yeah, we had to,swyx: he's just a thrash.Ryan Lopopolo: We had to add more optionality to the prompts on both of these things, right? The reviewer agents were instructed to bias toward merging the thing to not surface anything greater than a P two in priority. We didn't really define P two, but we gave it, youswyx: did define P two.Ryan Lopopolo: We gave it a framework within which to score its outputswyx: and then greater than P zero is worse, right?Yes. P two is very good.Ryan Lopopolo: P zero is you will mute the code place ifswyx: you merch thisRyan Lopopolo: thing, right?swyx: Yeah.Ryan Lopopolo: But also on the code authoring agent side, we also gave it the flexibility to either defer or push back against review feedback, right? This happens all the time, right? Like I happen to notice something and leave a code review, [00:15:00] which.Could blow up the scope by a factor of two. I usually don't mean for that to be addressed Exactly. In the moment. It's more of an FYI file it to the backlog, pick it up in the next fix it week sort of thing. And without the context that this is permissible, the coding agents are gonna bias toward what they do, which is following instructions.swyx: Yeah.[00:15:19] Autonomous Merging Flowswyx: I do wanted to check in on a couple things, right? Sure. All the coding review agent, it can merge autonomously. I think that's something that a lot of people aren't comfortable with. And you have a list here of how much agents do they do Product code and tests, CI configuration and release tooling, internal Devrel tools, documentation eval, harness review, comments, scripts that manage the repository itself, production dashboard definition files, like everything.Yes. And so they're just all churning at the same time, is there like a record that, that any human on the team pulls to stop everythingRyan Lopopolo: Because we are building a native application here. We're not doing continuous deploy. So there's still a human in the loop for cutting the release branch.I see. We require a blessed [00:16:00] human approved smoke test of the app before we promote it to distribution, these sort of things.swyx: So you're working on the app, you're not building like infrastructure where you have like nines of reliability, that kinda stuff?Ryan Lopopolo: That's correct. That's correct. Okay. And also like full recognition here that all of this activity took in a completely greenfield repository.There's. Should be no script that this applies generally toswyx: this is a production thing, you're gonna shipRyan Lopopolo: toswyx: customers. Of course. Yeah, of course. So this is realVibhu: And like one of the things there is, you mentioned you started this as a repo from scratch. The onboarding first month or so was pretty, it was like working backwards, right?Yeah. And then you had to work with the system and now you're at that point where you know, you're very autonomous. I'm curious like, okay, so what, how human in the loop is it? So what are the bottlenecks that you wish you could still automate? And part of that is also like, where do you see the model trajectory improving and offloading more human in the loop?We just got 5.4. It's a really good,Ryan Lopopolo: fantastic model, by the way.Vibhu: Yeah. Yeah. It's the first one that's merged. Top tier coding. So it's codex level coding and reasoning. So general reasoning both in one model. SoRyan Lopopolo: andVibhu: computer [00:17:00] use vision.Ryan Lopopolo: Now we now with five four, I can just have Codex write the blog post, whereas for this one I had to balance between chat.swyx: Oh, I need to, I might be out of a job. Oh my God.Ryan Lopopolo: Oh,swyx: I know. You just gave me an idea for a completely AI newsletter that five four could do. Yeah, I get it Now.Ryan Lopopolo: This sort of thing is just one example of closing the loop, right? Like the dashboard thing you mentioned. We have Codex authoring the Js ON, for the Grafana dashboards and publishing them and also responding to the pages, which means when it gets the page, it knows exactly which dashboards are defined and what alerts.What alert was triggered by which exact log in the code base. ‘cause all of this stuff is collated together.swyx: It has to own everything.Yes. Yeah. Yeah.Ryan Lopopolo: And it means that if we have an outage that did not result in a page. It has the existing set of dashboards available to it. It has the existing set of metrics and logs and can figure out where the gaps in the dashboard are or [00:18:00] in the underlying metrics and fix them in one go.In the same way, you would have a full stack engineer be able to drive a feature from the backend all the way to the front end.Vibhu: So it, it seems like a lot of the work you guys had to do was you as a small team are fully working for a way that the model wants the software to be written. It's like less human legible for better. Code legibility, agent legibility. How do you think that affects broader teams? So one at OpenAI, do liaison, like this is how software should be written. Like I can imagine, say you join a new team with this methodology, this mindset there's ways that, teams do code review, teams write code, like teams are structured and a lot of it is for human legibility.So should we all swap? Like how does this play back one broader into OpenAI and then like broader into the software engineering, right? Is it like teams that pick this up will it's pretty drastic, right? You have to make a pretty big switch. Should they just full send Yeah.Ryan Lopopolo: The mindset is very much that I'm removed from the process, right? I can't really have deep code level opinions about [00:19:00] things. It's as if I'm. Group tech leading a 500 person organization.Vibhu: Yeah.Ryan Lopopolo: Like it's not appropriate for me to be in the weeds on every pr. This is why that post merge code review thing is like a good analog here, right?Like I have some representative sample of the code as it is written, and I have to use that to infer what the teams are struggling with, where they could use help, where they're already moving quickly and I can pivot my focus elsewhere.Vibhu: Yeah.Ryan Lopopolo: So I don't really have too many opinions around the code as it is written.I do, however, have a command based class, which is used to have repeatable chunks of business logic that comes with tracing and metrics and observability for free. And the thing to focus on is not how that business logic is structured, but that it uses this primitive ‘cause I know that's gonna give leverage by default.Vibhu: Yeah.Ryan Lopopolo: Yeah, back to that sort of systems stinking,Vibhu: and you have part of that in your blog post, enforcing architecture and ta taste how you set boundaries for what's used. There's also a section on redefining [00:20:00] engineering and stuff, but yeah, it's just, it's interesting to hear,Ryan Lopopolo: and as the models have gotten better, they have gotten better at proposing these abstractions to unblock themselves, which again, lets me move higher and higher up the stack to look deeper into the future on what ultimately blocked the team from shipping.swyx: Yeah. You mentioned so you, this is primarily a, it is like a 1 million line of code base electron app. But it manages its own services as well, so it's like a backend for front end type thing.Ryan Lopopolo: We do have a backend in there, but that's hosted in the cloud.Yeah. This sort of structure is actually within the separate main and render processesWithin theswyx: electric.That's just how electronic works.Ryan Lopopolo: Yeah, of course. So have also treated like. MVC style decomposition with the same level of rigor, which has been very fun.swyx: I have a fun pun. This is a tangent, NVC is model view controller. Any sort of full stack web Devrel knows that.But my AI native version of this is Model view Claw, the clause the harness.Ryan Lopopolo: That's right. That's right. I do think that there is an interesting space to [00:21:00] explore here with Codex, the harness as part of building AI products, right? There's a ton of momentum around getting the models to be good at coding.We've seen big leaps in like the task complexity with each incremental model release where if you can figure out how to collapse a product that you're trying to build, a user journey that you're trying to solve into code, it's pretty natural to use the Codex Harness to solve that problem for you. It's done all the wiring and lets you just communicate and prompts to let the model cook.Yeah. It's been very fun. And there's also a very engineering legible way of increasing capabil. It's fantastic, right? Yeah. Just give you, just give the model scripts, the same scripts you would already build for yourself.swyx: Yeah.Yeah. So for listeners, this is Ryan saying that software engineering or coding against will eat knowledge work like the non-coding parts that you would normally think.Oh, you have to build a separate agent for it. No, start a coding agent and go out from there. Which open Claw has like it's pie Underhood.Ryan Lopopolo: [00:22:00] Yes.Vibhu: Basically define your task in code. Everything is a codingswyx: agent by the way. Since I brought it up, it's probably the only place we bring it up. Is any open claw usage from you?Any?Ryan Lopopolo: No. No. Not for me. I don't have any spare Mac Minis rattling around my house.swyx: You can afford it? No. I just, I'm curious if it's changed anything in opening eye yet, but it's probably early days. And then the other, the other thing I, I wanna pull on here is like you mentioned ticketing systems and you mentioned prs and I'm wondering if both those things have to go away or be reinvented for this kind of coding.So the git itself and is like very hostile to multi-agent.Ryan Lopopolo: Yeah. We make very heavy use of work trees.swyx: But like even then, like I just did a, dropped a podcast yesterday with Cursors saying, and they said they're getting rid of work trees ‘cause it still has too many merge conflicts.It's still un too un unintuitive. But go ahead.Ryan Lopopolo: The models are really great at resolving merge conflicts. Yeah. And to get to a state where I'm not synchronously in the loop in my terminal, I almost don't care that there are mergeswyx: with disposable.[00:23:00] Yeah.Ryan Lopopolo: We invoke a dollar land skill and that coaches codex to push the PR Wait for human and agent reviewers Wait for CI to be green.Fix the flakes if there are any merged upstream. If the PR comes into conflict, wait for everything to pass. Put it in the merge queue. Deal with flakes until it's in Maine. End. This is what it means to delegate fully, right? This is in a, very large model re probably a significant tax on humans to get PRS merged, but the agent is more than capable of doing this and I really don't have to think about it other than keep my laptop open.swyx: Yeah. I used to be much more of a control freak, but now I'm like, yeah, actually you could do a better job of this than me. Yeah. With the right context. Yes.[00:23:47] Encoding Requirementsswyx: Anything else in harness in general? Just this piece, I just wanna make sure we,Ryan Lopopolo: I think one thing that I maybe didn't make super clear in the article that I heard on Twitter as an interesting, that's respond [00:24:00]swyx: to them.What's the chatter and then what's your response?Ryan Lopopolo: Ultimately, all the things that we have encoded in docs and tests and review agents and all these things are ways to put all the non-functional requirements of building high scale, high quality, reliable software into a space that prompt injects the agent.We either write it down as docs, we add links where the error messages tell how to do the right thing. So the whole meta of the thing is to basically tease out of the heads of all the engineers on my team, what they think good looks like, what they would do by default, or what they would coach a new hire on the team to do to get things to merch.And that's why we pay attention to all the mistakes, mistakes that the agent makes, right? This is code being written that is misaligned with some as yet not written down, non-functional requirement.swyx: Sorry, what? Did the online people misunderstand orRyan Lopopolo: No,swyx: whatyouRyan Lopopolo: responded to? Somebody just literally said that.I was like, oh yeah,swyx: okay,Ryan Lopopolo: This is the [00:25:00] thing. This is what I've been doing. Oh, youswyx: agree? Yeah. I see. Interesting.Ryan Lopopolo: One other neat thing, which I did totally did not expect is folks were just. Taking the link to the article and giving it to pi or Codex and say, make my repo this,Vibhu: you achi a whole recursion.Ryan Lopopolo: And it was wildly effective. Really? It was wildly effective. NoVibhu: way. It just actually is something I tried with five, four yesterday. I didn't have time. Last time I was like out speaking of something, and this is one of my things, I was like, okay, I have this article. Can we just scaffold out what it would be like to run this?And I, I did it first as that and then I was like, okay, let me take another little side repo and say okay, if I was to fully automate this like this because I haven't written a line of code, it'sRyan Lopopolo: like over full, setVibhu: it right. The side thing I'm doing of voice. TTS I'm just like, slobbing out, whatever.It's nothing production. I'm like, how would I make this like this? And it's actually like a really good way. It's like a good way to learn what could be changed, what could be like, it's just a good analyzing, right? You give it all the codes, you give it all the context, you give it the article and it walks you through it very well.That's right. That's right.[00:25:57] Inlining Dependencies[00:25:57] Dependencies Going Away & Brett Taylor's Responseswyx: I guess one more thing before we go to Symphony is I wanted to cover [00:26:00] Brett Taylor's response. We had him on the show. He is your chairman, which is wild. Yeah. That he's reading your articles as well and like getting engaged in it. He says software dependencies are going away.Basically they can just be like vendored. Yes. Response.Ryan Lopopolo: Aswyx: hundred percent. A hundred percent agree. You still pro qr, you still pay Datadog. You still pay Temporal. Thank you.Ryan Lopopolo: Yep. The level of complexity of the dependencies that we can internalize is, I would say low, medium right now. Just based on model capability.What does the,swyx: what is medium?Ryan Lopopolo: I would say like a. A couple thousand line dependency is a thing that we could in-house No problem. Call in an afternoon of time. One neat thing about it is like probably most of that code you don't even need. Like by in-house and abstraction, you can strip away all the generic parts of it and only focus on what you need to enable the specific thing.Yes. You're building,swyx: I've been calling this the end of b******t plugins.Ryan Lopopolo: Yeah.swyx: Because there's so much when I published an open source thing, I want to accept everything, be liberal. I want to accept, this is post's law, but that means there's so much bloat. Yes. There's so much overhead.Ryan Lopopolo: One other neat thing about [00:27:00] this too is when we deploy Codex Security on the repo, it is able to deeply review and change. The internalized dependencies in a much lower friction way than it would be to like, push patches upstream, wait for them to be released, pull them down, make sure that's compatible with all the transitive I have in my repo and things like that.So it's also much lower friction to internalize some of these things if code is free. ‘cause the tokens are cheap sort of thing.swyx: Yeah. Yeah. I think like the only argument I have against this is basically scale testing, which obviously the larger pieces of software like Linux, MySQL, he calls up even the Datadog and Temporals and then maybe security testing where Yes.Classically, I think, is it linis tos, it said security open source is the best disinfectant.Ryan Lopopolo: Many eyes.swyx: Many eyes. And if inline your dependencies and code them up, you're gonna have to relearn mistakes from other people that Yep.Ryan Lopopolo: Yep. And to internalize that dependency, you're back to zero and you have to start.Reassembling all those bits and pieces to Yeah. Have [00:28:00] high confidence in the code as it is written. Yeah.Vibhu: Even part of the first intro of this, you basically mentioned like everything was written by codex, including internal tooling, right? So internal tooling, like when you're visualizing what's going on it's writing it for itself.swyx: Yeah. I'm built internal tools way I now, and like I just show them off and they're like, how long did you spend? And I didn't spend any time. I just prompted it,Ryan Lopopolo: very funny story here.swyx: Yeah, go ahead.Ryan Lopopolo: We had deployed our app to the first dozen users internally had some performance issues, so we asked them to export a trace for us get a tar ball, gave it to our on-call engineer, and he did a fantastic job of working with Codex to build this beautiful local Devrel tool, next JS app, the drag and drop the tar ball in, and it visualizes the entire trace.It's fantastic. Took an afternoon, but none of this was necessary. Because you could just spin up codex and give it the tar ball and ask the same thing and get the response immediately. So in a way, optimizing for human [00:29:00] legibility of that debugging process was wrong. It kept him in the loop unnecessarily when instead he could have just like Codex cooked for five minutes and gotten this same.swyx: Yeah, you verify your instincts here of this is how we used to do it. Or this is how I would have used to solve it.Ryan Lopopolo: Yeah. In this local observability stack. Like sure, you can de deploy Yeager to visualize the traces, but I wouldn't expect to be looking at the traces in the first place because I'm not gonna write the code to fix them.swyx: Yeah. So basically there needs to be like this kind of house stack and owning the whole loop. I think that is very well established. And it sounds like you might be like sharing more about that in the future, right?Ryan Lopopolo: Yeah. I think we're excited to do[00:29:36] Ghost Libraries Specs[00:29:36] Ghost Libraries & Distributing Software as SpecsRyan Lopopolo: We're gonna talk about Symphony in a little bit, but like the way we distribute it as a spec, which I think folks are calling Ghost Libraries on Twitter.This is like a such a cool name. It does mean it becomes much cheaper to share software with the world, right? You define a spec, how you could build your own specifying as much as is required for a coding agent to reassemble it [00:30:00] locally. The flow here is very cool. Like we have taken. All the scaffolding that has existed in our proprietary repo spun up a new one.Ask Codex with our repo as a reference. Write the spec. We tell it. Spin up a team ox spawn a disconnected codex to implement the spec. Wait for it to be done. Spawn another codex and another team ox to review the spec com or review the implementation compared to upstream and update the spec so it diverges less.And then you just loop over and over Ralph style until you get a spec that is with high fidelity able to reproduce the system as it is. It's fantastic.Vibhu: And you're basically, you're not really adding any of your human bias in there, right? That's correct. A lot of times people write a spec and be like, okay, I think it should be done this way, and you'll riff on something.And it's no, the agent could have just handled it like you're still scaffolding in a sense, right? I want it done this way. It can determine its spec better.swyx: That's right. That's right. Part of me it, I'm, I've been working a lot on evals recently, and part of me is wondering if [00:31:00] an agent can produce a spec that it cannot solve.Is it always capable of things that he can imagine or can you imagine things that it is impossible to do?Ryan Lopopolo: I think with Symphony, we, there's like this there's this axis where you have things that are easier, hard, or established or new, right? And I think things that are hard and new is still something that the models need humans.Yeah. Drive.swyx: Yeah. Yeah.Ryan Lopopolo: But I think those other quadrants are largely salt. Given the right scaffold and the right thing that's gonna drive the agent to completion,swyx: it's crazy that it solved,Ryan Lopopolo: but it means that the humans, the ones with limited time and attention get to work on the hardest stuff, like the problems where it's pure white space out in front. Or like the deepest refactorings where you don't know what the proper shape of the interfaces are. And this is where I wanna spend my time. ‘cause it lets me set up for the next level of scale.swyx: Yeah. Yeah. Amazing. Let's introduce Symphony.I think we've been mentioning it every now and then. Elixir. Interesting option.Ryan Lopopolo: Yeah.swyx: Yeah. I'm not,Ryan Lopopolo: again, like the [00:32:00] elixir manifestation here is just a derivative. Is it a modelswyx: chosen? Yeah.Ryan Lopopolo: Yeah. Yeah. And it chose that because the process supervision and the gen servers are super amenable to the type of process orchestration that we're doing here.You are essentially spinning up little Damons for every task that is in execution and driving it to completion, which. Means the mall gets a ton of stuff for free by using Elixir and the Beam.swyx: I had to go do a crash course in Beam and Elixir, and I think most people are not operating at that scale of concurrency where you need that.But it is a good mental model for Resum ability and all those things. And these are things I care about. But tell me the story, the origin story of Symphony. What do you use it for? Is this, how did it form maybe any abandoned paths that you didn't take?[00:32:46] Terminal Free Orchestration[00:32:46] Symphony: Removing Humans from the LoopRyan Lopopolo: At the end of December we were at about three and a half PRS per engineer per day.This was before five two came out in the beginning of January. Everyone gets back from holiday with five two and no other work [00:33:00] on the repository. We were up in the five to 10 PRS per day per engineer. And I don't know about y'all, but like it's very taxing to constantly be switching like that. Like I was pretty tapped out at the end of the day, again, where are the humans spending their time? They're spending their time context switching between all these active tmox pains to drive the agent forward.swyx: Yeah. No way. Yeah.Ryan Lopopolo: So let's again, build something to remove ourselves from the loop. And this is what frantic sprinted adapt here to find a way to remove the need for the human to sit in front of their terminal.So a lot of experimentation with Devrel boxes and, automatically spinning up agents, like it seems like a fantastic end state here, where my life is beach. I open live twice a day and say yes no to these things. Yeah. And this is again, a super, super interesting framing for how the work is done.Because I become more latency and sensitive. I have [00:34:00] way less attachment to the code as it is written. Like I've had close to zero investment in the actual authorship experience. So if it's garbage. I can just throw it away and not care too much about it. In Symphony, there's this like rework state where once the PR is proposed and it's escalated to the human for review, it should be a cheap review.It is either mergeable or it is not. And if it's not, you move it to rework. The elixir service will completely trash the entire work tree NPR and start it again from scratch. Okay. And this is that opportunity again to say, why was it trash right? What did the agent do that wasswyx: bad. Yeah.Ryan Lopopolo: Fix that before moving the ticket toswyx: endRyan Lopopolo: of progress again.swyx: Yeah. Why is this not in codex app? I guess this, you guys are ahead of Codex app,Ryan Lopopolo: yeah, so the way the team has been working is basically to be as AI pilled as possible and spread ahead. And a lot of the things we have worked on have fallen out [00:35:00] into a lot of the products that we have.Like we were in deep consultation with the Codex team to. Have the Codex app be a thing that exists, right? To have skills be a thing that Codex is able to use. So we didn't have to roll our own to put automations into the product. So all of our automatic refactoring agents didn't have to be these hand rolled control loops.It has been really fantastic to be, in a way, un anchored to the product development of Frontier and Codex and just very quickly try to figure out what works and then later find the scalable thing that can be deployed widely. It's been a very fun way to operate. It's certainly chaotic. I have lost track very often of what the actual state of the code looks like.‘cause I'm not in the loop. There was. One point where we had wired playwright directly up to the Electron app. With MCPM CCPs, I'm pretty bearish on because the harness forcibly injects all those tokens in the [00:36:00] context, and I don't really get a say over it. They mess with auto compaction. The agent can forget how to use the tool.There's probably only what three calls in playwright that I actually ever want to use. So I pay the cost for a ton of things. Somebody vibed a local Damon that boots playwright and exposes a tiny little shim CLI to drive it. And I had zero idea that this had occurred because to me, I run Codex and it's able to, it's oh, it's better.Yeah. Like no knowledge of this at all. Uhhuh.[00:36:30] Multi Human ChaosRyan Lopopolo: So we have had like in human space to spend a lot of time doing synchronous knowledge sharing. We have a daily standup that's 45 minutes long because we almost have to. Fan out the understanding of the current state.swyx: Yeah, I was gonna say this is good for a single human multi-agent, but multi human, multi-agent is a whole like po like explosion of stuff.Ryan Lopopolo: Yeah. And that this is fundamentally why we have such a rigid, like 10,000 [00:37:00] engineer level architecture in the app because we have to find ways to carve up the space so people are not trampling on each other.swyx: Sorry, I don't get the 10,000 thing. Did I miss that?Ryan Lopopolo: The structure of the repository is like 500 NPM packages.It's like architecture to the excess for what you would consider, I think normal for a seven person team. But if every person is actually like 10 to 50. Then the like numbers on being super, super deep into decomposition and sharding and like proper interface boundaries make a lot more sense.swyx: Yeah. To me, that's why I talked about Microfund ends and I, an anex is from that world, but Cool. It is just coming back to, to, to this I dunno if you have other, thoughts on. Orchestrating so much work coin going through this. Is this enough? Is this like any aha moments?Vibhu: It'll be interesting to see like where, okay, so right now you pick linear as your issue tracker, right?swyx: Or it's like a is it actually linear? This is actually linear.[00:37:55] Linear vs Slack WorkflowVibhu: Oh, that's linear. It's linear.swyx: Oh I never looked atVibhu: video. The demo video I had to download to [00:38:00] run.swyx: So I, because I'm a Slack maxie, but Yeah, linear. Linear is also really good. Yes,Ryan Lopopolo: we do make a good use of Slack. We we fire off codex to do all these lotion, elasticity, fix ups, the things that like sync that knowledge into the repository.It's super cheap. Yeah.swyx: Yeah.Ryan Lopopolo: Just do it in Codex.swyx: My biggest plug is OpenAI needs to build Slack. You need to own Slack. Build yours. Turn this into Slack.Ryan Lopopolo: I did read about it. Youswyx: did?Ryan Lopopolo: Yeah.[00:38:25] Collaboration Tools for AgentsRyan Lopopolo: I would say that if we think that we want these agents to do economically valuable work, which is like this is the mission, right?We want AI to be deployed widely, to do economically valuable work, then we need to find ways for them to naturally collaborate with humans, which means collaboration tooling, I think, is an interesting space to explore.swyx: Yeah, totally. Yeah. GitHub, slack, linear.Vibhu: Yeah, that was my thing. Okay, where do we see right now Codex has started Codex Model, then CLI, now there's an app, app can let me shoot off multiple Codex is in parallel, but there's no great team collaboration for Codex.And it [00:39:00] seems like your team had some say into what comes out, right? So you talked to ‘em, codex kind of was a thing. From there, if you guys are on the bound, what stuff that like, you might not focus on, but what do you expect other people to be building, right? So people that are like five x 50 Xing.Should you build stuff that's like very niche for your workflow, for your team? Should it be more general so other people can adopt? Is there a niche there? ‘Cause part of it is just okay, is everything just internal tooling? Do we have everything our own way? Like the way our team operates has our own ways that we like to communicate or is there a broader way to do it?Is it something like a issue tracker? Just thoughts if you wanna riff on that.[00:39:35] Standardizing Skills and CodeRyan Lopopolo: I think TBD we have not figured this out in a general way. I do think that there is leverage to be had in making the code and the processes as much the same as possible. If you think that code is context, code is prompts, it's better from the agent behavior perspective to be able to look in a package in directory X, Y, Z, and it not to have to page so [00:40:00] deeply into directory if you C, because they have the same structure, use the same language, they have the same patterns internally.And that same like leverage comes from aligning on a single set of skills that you're pouring every engineer's taste into to make sure that the agent is effective. So like in our code base, we have, I think, six skills. That's it. And if some part of the software development loop is not being covered, our first attempt is to encode it in one of the existing setup skills, which means that we can change the agent behavior.Yeah. More cheaply than changing the human driver behavior.swyx: Yeah.[00:40:39] Self Improvement via Logsswyx: Have you ever, have you experimented with agents changing their own behavior?Ryan Lopopolo: We do.swyx: Yeah. Or parent agent changing a subagents, behavior or something like that.Ryan Lopopolo: We have some bits for skill distillation. So for example, there's one neat thing you can do with Codex, which is just point it at its own session logs to ask it to tell you how you can use [00:41:00] the tool pedal better.swyx: It's like introspectionRyan Lopopolo: or ask it to do things. I useVibhu: this session better. What skills should Iswyx: high? I like the modification of, you can do, just do things to you can just ask agent to do things.Ryan Lopopolo: Yeah. You can just codex things. This is like a, this is like a silly emoji that we have, right? You can just codex things, you can just prompt things.It's really glorious future we live in, but okay, you can do that one-on-one. But we're actually slurping these up for the entire team into blob storage and. Running agent loops over them every day to figure out where as a team can we do better and how do we reflect that back into the repositories?Yes, though everybody benefits from everybody else's behavior for free. Same for like PR comments, right? These are all feedback. That means the code as written, deviated from what was good, a PR comment, a failed build. These are all signals that mean at some point the agent was missing context. We gotta figure out how toswyx: Yeah.Ryan Lopopolo: Slurp it up and put it back in the reboot.swyx: By the way, I do this exactly right. I used to, when I use cloud code for [00:42:00] knowledge work, cloud cowork is like a nice product, right? Yes. In I think you would agree. I always have it tell me what do I do better next time? And that's the meta programming reflection thing.So I almost think like you have six reflection extraction levels in symphony and almost like the zero of layer. So the six levels are PO policy, configuration, coordination, execution, integration, observability. We've talked about a couple of these, but the zero layer is like the, okay, are we working well?Can we improve how we work? Yes. Can I modify my own workflow without MD or something? I don't know.Ryan Lopopolo: Yeah, of course. Yeah, of course you can. Like this thing is also able to cut its own tickets ‘cause we give it full access.Yeah. Make it a ticket to have it cut. Tickets you can.Put in the ticket that you expect it to file as on follow up work,swyx: like Yeah. Self-modifying. Yeah.Ryan Lopopolo: Yeah.[00:42:44] Tool Access and CLI FirstRyan Lopopolo: Put, don't put the agent in a box. Give the agent full accessibility over it. Domain.swyx: I had a mental reaction when you said don't put the agent in a box. So I think you should put it in a box. Like it's just that you're giving the box everything it needs.Ryan Lopopolo: Yeah. Context and tools.swyx: But we're like, as developers, we're used to calling [00:43:00] out to different systems, but here you use the open source things like the Prometheus, whatever, and you run it locally so that you can have the full loop. I assume.Ryan Lopopolo: Yep.Vibhu: I think likeRyan Lopopolo: another, you wanna minimize cloud, cloud dependencies.Vibhu: You also want to make sure that you think about what the agent has access to. What does it see? Does it go back into the loop, like from the most basic sense of you let it see its own like calls, traces it can determine where it went wrong. But are you feeding that back in? So you know, just the most basic level of you wanna see exactly what's input output, like does the agent have access to.What is being outputted, right? It can self-improve a lot of these things. It's allRyan Lopopolo: text, right? My job is to figure out ways to funnel text from one agent to the other.swyx: It's so strange like way back at the start of this whole AI wave Andre was like, English is the hottest day programming language.It's here, it's just Yeah. The feature as well.Vibhu: A lot of, okay. Like a lot of software, a lot of stuff. There's a gui, it's made for the human. We're seeing the evolution of CLI for everything, right? All tools have CLIs. Your agents can use [00:44:00] them well, do we get good vision? Do we get good little sandboxes?Like right now? It's a really effective way, right? Models love to use tools. They love the best. They love to read through text. So slap a CLI let it go loose. That works for everything.Ryan Lopopolo: It does. Yeah. Yeah.[00:44:14] UI Perception and RasterizingRyan Lopopolo: We've also been adapting nont, textual things to that shape in order to improve model behavior in some ways, right?We want the agent to be able to see the UI agents do not perceive visually in the same way that we do. They don't see a red box, they see red box button, right? They see these things in latent space. So if we want, Hey, yeah, I do. We haveswyx: a ding if that goes off every time. Alien spaceRyan Lopopolo: ding.Anyway if we wanna actually make it see the layout, it's almost easier to rasterize that image to ask EOR and feed it in to the agent. Ha. And there's no reason you can't do both, right? To like further refine how the model perceives the object it's [00:45:00] manipulating.swyx: Cool. Could we, you wanna talk about a couple more of these layers that might bear more introspection or that you have personal passion for?[00:45:07] Coordination Layer with ElixirRyan Lopopolo: I will say that the coordination layer here was a really tricky piece to get right.swyx: Let's do it. Yep. I'm all about that. And this is Temporal core.Ryan Lopopolo: This is where when we turn the spec into Elixir, where like the model takes a shortcut, right? Like it's oh, I have all these primitives that I can make use of in this lovely runtime that has native process supervision.Which is I think, a neat way to have taken the spec and made it more choices achievable by making choices that naturally mapswyx: Yeah.Ryan Lopopolo: To the domain, right? In the same way that like you would prefer to have a TypeScript model repo if you are doing full stack web development, right? Because the ability to share types across the front end and backend reduces a lot of complexity.And becauseswyx: that's what graph kill used to be.Ryan Lopopolo: That's right. Andswyx: I don't know if it's still alive, butRyan Lopopolo: [00:46:00] no humans in the loop here. So like my own personal ability to write or not write elixir. Doesn't really have to bias us away from using the right tool for the job. It is just wild.swyx: Love it. I love it.Yeah. I wonder if any languages struggle more than others because of this? I feel like everyone has their own abstractions. That would make sense. But maybe it might be slower, it might be more faulty where like you'd have to just kick the server every now and then. I, I don't know. I think observability layer is really well understood.Integration layer, CP is dead. I think all these just like a really interesting hierarchy to travel up and down. It's common language for people working on the system to understandRyan Lopopolo: The policy stuff is really cool, right? Yeah. You don't really have to build a bunch of code to make sure the system wait for the, to passswyx: it's institutional knowledge.Ryan Lopopolo: Yeah. You just give it the G-H-C-L-I with some text that say CI has to pass. It makes the maintenance of these systems a lot easier.[00:46:57] Agent Friendly CLI Outputswyx: Do you think that CLI maintainers need to be [00:47:00] do anything special for agents or just as is? It's good because like I don't think when people made the G GitHub, CLI, they anticipated this happening.Ryan Lopopolo: That's correct. The GH CLI is fantastic. It's great super industry.swyx: Everyone go try GH repo create GH pull and then pull request number, right? GH HPR, like 1 53, whatever. And then it like pullsRyan Lopopolo: basically my only interaction with the GitHub web UI at this point is GH PR view dash web.Exactly. Glanceswyx: at the diffRyan Lopopolo: and be like Sure thing. Send it. Yeah. But the CLI are nice ‘cause they're super token efficient and they can be made more token efficient really easily. Like I'm sure you all have seen like I go to build Kite or Jenkins and I could just get this massive wall of build output.And in order to unblock the humans, your developer productivity team is almost certainly gonna write some code that parses the actual exception out of the build logs and sticks it in a sticky note at the top of the page. And you basically [00:48:00] want CLI to be structured in a similar way, right? You're gonna want to patch dash silent to prettier because the agent doesn't care that every file was already formatted.Just wants to know it's either formatted or not. So it can then go run a right command. Similarly, like in our PNPM distributed script runner, when we had one, when you do dash recursive, like it produces a absolute mountain of text. But all of that is for passing. Test suites. So we ended up wrapping all of this in another scriptswyx: to suppress the,Ryan Lopopolo: which you can vibe the channel only output the failing parts of the tests.swyx: You make a pipe errors versus the standard, standard out. I don't know. Okay. Whatever. Too much thinking have to do that. The CII used to maintain SCLI for my company and yeah, this is like core, very core to my heart. But you're vibing my job.Ryan Lopopolo: That's right.swyx: Cool. Any other things?This is a long spec. [00:49:00] I appreciate that. It's got a lot of strong opinions in here. Any other things that we should highlight? I think obviously you can spend the whole day going through some of these, but I do think that some of these have a lot of care or some of this you might wanna tell people, Hey, take this, but, make it your own.[00:49:15] Blueprint Spec and GuardrailsRyan Lopopolo: Fundamentally, software is made more flexible when it's able to adapt to the environment in which it is deployed, which means that things like linear or GitHub even are specified within the spec, but not required pieces of it. There's like a more platonic ideal of the thing that you could swap in like Jira or Bitbucket, for example.But being able to tightly specify things like the ID formats or how the Ralph Loop works for the individual agents. Basically means you can get up and running with a fully specified system quickly that you then evolve later on. I think we never intended for this to be a static spec that you can [00:50:00] never change.It's more like a blueprint to get something worth a starting point up and running.swyx: Yeah.Ryan Lopopolo: For you then to vibe later to your heart's content,swyx: you have like code and scripts in here where it's oh, I think this is a really good prompt. It's just a very long prompt.Ryan Lopopolo: Fundamentally, the agents are good at following instructions, so give them instructions.And it will, improve the reliability of the result. We, much like the way we use Symphony, we don't want folks to have to monitor the agent as it is vibing the system into existence. So being very opinionatedVery strict around what these success criteria are means that our deployment success rate goes up. Yeah. It means we don't have to get tickets on this thing.Vibhu: Think it all goes back to that like code to disposable, right? Like early on when you had CLI or you'd kick off a Codex run, it would take two hours. You would wanna monitor okay, I'm in the workflow of just using one.I don't want it to go down the wrong path. I'll cut it off and, just shoot off four, like that was my favorite thing of the Codex app, right? Yeah. Just Forex it like, [00:51:00] it's okay. One of them will probably be right, one of them might be better. Stop overthinking it. Like my first example was probably like deep research.When you put out deep research and I'd ask it something like, I asked it something about LLM, it thought it was legal something and spent an hour, came back with a report completely off the rails. And I was like, okay, I gotta monitor this thing a bit. No don't monitor it. Just you want to build it so it's that it, it goes the right way.And you don't wanna, you don't wanna sit there and babysit, right? You don't want to babysit your agentsRyan Lopopolo: with that deep research query that you made. Looking at the bad result, you probably figured out you needed to tweak your prompt Yeah. A bit, right? That's that guardrail that you fed back into the code base for the task, your prompt to further align the agent's execution.Same sort of concept supply there too.swyx: When you talk, how are the customers feelingRyan Lopopolo: for Symphony? I think we have none, right? This is a thing we have put out into theswyx: world. Symphony's internal, right? As long as you are happy, you are the customer. That'

BONUS: Why Your Plan Is Lying to You — #NoEstimates, Throughput, and the Superstition of Project Management This episode is a cross-post from The EBFC Show, Felipe Engineer-Manriquez's podcast exploring Lean and Agile in construction. In this conversation, Felipe interviews Vasco about the #NoEstimates movement, throughput-based planning, and why traditional project management is still stuck in the middle ages of managing creative work. The Human Side of Scrum That the Scrum Guide Doesn't Cover "When you go into a daily meeting and you start looking at the people in that room, maybe they are the exact same people that were there yesterday, but the team is totally different. Somebody might have had a bad night's sleep, somebody might have had an argument with their spouse. These are human beings. These are not machines that you can just distribute work to."   Vasco's path to agile coaching started with a realization that most practitioners eventually reach: the problems in software development aren't technological. They're about people — getting agreements, sharing information at the right time, making the collective brain of a team actually function. The Scrum Guide gives you organizing principles — how many meetings, who's in them — but it says almost nothing about the real-time feedback cycle between humans that makes or breaks a team. That's why the Scrum Master role exists: to be the lubricant for human interactions, to break down complex ideas into items the collective mind can process. It's the piece that makes Scrum work, and it's the piece that's hardest to teach. From Project Manager to #NoEstimates — The Bet That Changed Everything "The PM wanted 15 items per sprint, and the team said 'yeah, we can do 15.' I said, this is not gonna happen. The team had been delivering between five and eight items per sprint. I said, I'm gonna be positive — I'm gonna say seven. And no surprise, by the end of the sprint, they delivered seven."   Vasco started as a project manager — and not the easy certification kind. He went through IPMA, which means six months of training, a four-hour written exam, and an expert interview, just for the entry level. Planning and estimating was the job. Then he ran his first Scrum project, specifically to prove it couldn't work. By the second month, he couldn't understand how anything else could work. The team delivered something to show every single sprint — something that never happened with traditional project management. The turning point came when he made a bet with a product manager: the PM needed 15 items per sprint, the team committed to 15, but historical throughput was 5-8 items. Reality delivered seven. That moment crystallized the #NoEstimates insight: we can't fight reality, but we can choose which seven items to deliver. Reality Is a Bitch — Why Linear Predictive Planning Fails "Never believe the plan. Or as in Scarface — never get high on your own supply. It's so unbelievable how project managers still today believe their freaking plans."   At Nokia, Vasco managed a program of 500 people across 100 teams on four continents. No way to get everyone in a room. So he tracked system-level throughput — features delivered to integration per week. Six months into a twelve-month project, the data said they'd be at least six months late. He told the program manager: cut scope now. The program manager did what every PMI-trained program manager does — sent an email asking all 100 teams if they'd deliver on time. Every single team said yes. Nobody wants to be first to admit they're late. Twelve months in, they discovered they were six months late. The project got canceled. 500 people, millions of euros, all because somebody believed the plan. Linear predictive planning is useful for exploring what might be possible if nothing goes wrong. It is not reality. The only tool that reflects reality is throughput — the number of items completed per unit of time. Earned Value Management — George Orwell at His Best "It's not earned, it's spent. It's not value, it's cost. It's not management, it's just observation. Monty Python could not have come up with a better name."   Felipe shares a story that mirrors the absurdity: an industrial project with a dedicated 35-person earned value management department. Before the meeting even started, the department head announced, "Let's all acknowledge that earned value management is more an art than a science." Their charts were made up, the contractor's charts were made up, and the goal of the meeting was to agree that the project would finish on time — regardless of what any data said. This is where traditional project management ends up when it disconnects from throughput: a $30 million scope addition with zero additional time, defended by charts that a mediocre attorney can invalidate in the first week of litigation. Felipe knows — he spent a year being cross-examined by forensic schedulers whose full-time job is proving that construction schedules are fiction. One Small Experiment to Test #NoEstimates "Never convince anyone. Convince yourself. Once you're convinced, whatever other people say, it doesn't really matter because you're not gonna take them seriously anyway."   Here's how to validate throughput-based planning with your own data: take the last 10 sprints (or periods). Calculate the average throughput and control limits from the first five. Then check whether the next five sprints fall within that range. They will. If you're in software and using Jira, you already have this data. You don't need anyone's permission. You don't need to change anything. Just look at what your team actually delivers versus what they planned to deliver. The gap between those two numbers is the gap between superstition and reality. About Felipe Engineer-Manriquez Felipe Engineer-Manriquez is a best-selling author, international keynote speaker, Project Delivery Services Director at The Boldt Company, host of The EBFC Show podcast, and a proven construction change-maker implementing Lean and Agile practices on projects from millions to billions of dollars worldwide. He is a Registered Scrum Trainer™ (RST), Registered Scrum Master™ (RSM), and recipient of the Lean Construction Institute Chairman's Award. His book Construction Scrum is the first practical guide for applying Scrum in construction.   You can link with Felipe Engineer-Manriquez on LinkedIn.

This week, we're exploring an important and sometimes misunderstood topic: what to do when our neurodivergent kids are happier alone and genuinely prefer solitude over social interactions. Key Takeaways: Solitude Can Be Healthy: Recognize that some children genuinely enjoy being alone, and this can be restorative, not problematic. Honor their need for quiet time without assuming something is wrong. Distinguish Between Solitude and Isolation: Pay attention to signs. Healthy solitude is chosen, flexible, and doesn't carry shame, while isolation is often rigid, driven by fear, and paired with sadness or avoidance. Listen More Than You Talk: When your child expresses a preference for being alone, approach with curiosity rather than correction. Ask open-ended questions and avoid jumping into problem-solving. Don't Force Social Exposure: Avoid pushing frequent social situations or using solitude as a consequence. Let your child take breaks and control their level of social participation. Offer Invitations Without Pressure: Always keep low-demand connection options available. Respect "not now" and provide different types of social opportunities to let your child decide what feels safest. Honor Individual Differences: Never compare your child's social preferences to siblings or peers. Each child's needs and approach to friendships are unique and deserving of respect. Keep Connection Accessible: Even for children who prefer solitude, periodically check in. Offer short, interest-based activities, familiar settings, or intergenerational relationships to keep social muscles warm. Connection Isn't Linear or Urgent: Reassure your child (and yourself) that social growth happens at their own pace. Deep friendships may come later and are worth waiting for. Gentle Check-Ins: Periodically ask your child if they feel lonely or peaceful in their solitude, and discuss what helps them recharge and feel connected, without requiring action. Encourage Self-Discovery: Support your child's exploration of what types of friendships and connections work for them. Provide opportunities but let them drive the process. Cherish the connections your child finds, offer gentle support, and remember: The world would be boring if we all fit the same mold. Your child's unique wiring deserves celebration, not correction. Links and Resources from Today's Episode Thank you to our sponsors: CTC Math – Flexible, affordable math for the whole family! Curiosity Post – A Snail Mail Club for kids – Real mail; Real life! The Learner's Lab – Online community for families homeschooling gifted/2e & neurodivergent kiddos! The Lab: An Online Community for Families Homeschooling Neurodivergent Kiddos The Homeschool Advantage: A Child-Focused Approach to Raising Lifelong Learners Raising Resilient Sons: A Boy Mom's Guide to Building a Strong, Confident, and Emotionally Intelligent Family The Anxiety Toolkit Sensory Strategy Toolkit | Quick Regulation Activities for Home Affirmation Cards for Anxious Kids Nurturing Neurodivergent Friendships: Practical Tips for Parents and Kids RLL #42: What It's Like to be Homeschooled with Best Friends Molly and Ella Teaching Kids About Being a Good Friend with Help From Great Books and Netflix Teaching Kids to Befriend Others 5 Tips for Helping Gifted Children Make Friends Navigating Sensory Overload: Actionable Strategies for Kids in Loud Environments The Not-So Friendly Friend: How to Set Boundaries for Healthy Friendships Social Skills Activities for Kids Growing Friendships: A Kids' Guide to Making and Keeping Friends Have You Filled a Bucket Today?: A Guide to Daily Happiness for Kids One Big Heart: A Celebration of Being More Alike than Different Life Skills for Kids: Unlocking a World of Possibilities through Friendship, Decision-Making, Cooking, Achieving a Success Mindset, Time-Management, Budgeting, and More  Empathy Workbook for Kids: 50 Activities to Learn About Kindness, Compassion, and Other People's Feelings   Grab Your FREE Friendship Guide!

Career and leadership growth were never meant to be a straight line, and Akua Nyame-Mensah has lived that truth beautifully. From urban planning to AmeriCorps to leading a startup launch in West Africa, Akua's career has moved in seasons, each one building on the last. Now a leadership advisor and facilitator, she helps others navigate their own cycles with greater clarity and less pressure. In this conversation, Akua shares her Leadership Cycle framework and why the messier seasons of leadership are just as valuable as the flourishing ones.