Every transcript

102 talks · 34h 58m of video · 22,443 sentences, each linked to the second it starts · generated 2026-09-12T14:42:03+00:00.

One fetch instead of 102: all.txt is every talk's sentences under a header, for reading into a context window; all.json is the same with each sentence's id, start and end seconds. Per talk: the page (timecodes open YouTube), txt, and vtt with one cue per sentence for cutting clips.

• MCP Apps: Extending the Frontier — Ido Salomon & Liad Yoseftxtvtt▶
• When Will The Benchmaxxing Plague End? — Nick Heiner, Surge AItxtvtt▶
• What If Your Chip Design Team Moved Like a Single Body? — Abduallah Mohamed, AIDAChiptxtvtt▶
• Your company brain will leak secrets: how we stopped it for big banks — Tanmai Gopal, PromptQLtxtvtt▶
• Agentic SDLC at Uber — Uday Kiran Medisetty & Adam Huda, Ubertxtvtt▶
• The Signal Layer: What to Build When Anything Can Be Built — Lena Hall, Akamaitxtvtt▶
• Guardians of the State: An Air-Gapped AI Fortress for Consumer Data — Rachna Srivastava, DFPItxtvtt▶
• Rethinking Environments for Long-Horizon Work — Rayan Garg, Theta Softwaretxtvtt▶
• Scaling to Long Horizons — Ross Taylor & Chengxi Taylor, General Reasoningtxtvtt▶
• Agents Are Where Microservices Were in 2015 — Roberto Milev & Uday Kanagala, Navantxtvtt▶
• Your Fine-Tuned Model Is Tech Debt: A 50x ROI House of Cards — Dan Bjornn, Lease Endtxtvtt▶
• How to Get Your Org to Adopt Coding Agents (Without Shipping Garbage) — Eyal Blum, Figmatxtvtt▶
• Why AI Agents Need Million-Token Context — Thomas Wolf & Olive Song, MiniMaxtxtvtt▶
• Knowledge Systems: The New GTM Stack — Jeffrey Wang, Exatxtvtt▶
• Which AI startups actually land enterprise contracts? — Brian Lewis, Millenniumtxtvtt▶
• The Missing Layer: Design Taste in AI Agents — Hassan El Mghari, Together AItxtvtt▶
• Mousepower: agents that can’t be measured, can’t be managed. — Maximillian Piras, Yutoritxtvtt▶
• Build-Time vs. Run-Time: Why Dev Tools Fail in Production — Averi Kitsch & Prerna Kakkar, Googletxtvtt▶
• 500 Skills, Zero Fine-Tuning: LinkedIn's Playbook for AI Agents — Ajay Prakash, LinkedIntxtvtt▶
• Teaching agents to pay — Anna Spysz, Stripetxtvtt▶
• Multimodal Collaborative Agents for Next-Gen Commerce — Nidhi Kaushik Vyas, Google DeepMindtxtvtt▶
• How do you diffuse AI into the real world? — Varun Shenoy, Long Laketxtvtt▶
• Building GTM AI Agents: Lessons from Deploying to 6,000 Users — Sait Izmit, Snowflaketxtvtt▶
• Building uReview, Uber’s Multi-Agent Code Review Engine — Will Bond & Ameya Ketkar, Ubertxtvtt▶
• How I automate my own job at Hugging Face using agents — Niels Rogge, Hugging Facetxtvtt▶
• Preferences Over Benchmarks: Model Routing — Archana Kamath & Tyler Gillam, DigitalOceantxtvtt▶
• The Agentic Commerce Stack — Ahnaf Prio, Best Buytxtvtt▶
• FinOps for AI Agents: Who Spent All the Tokens? — Tisha Chawla & Susheem Koul, Microsofttxtvtt▶
• Building Agents Is Trivial Now, Context Is the Next Frontier — Jeff Ng, Unblockedtxtvtt▶
• Agent Frameworks Considered Harmful — Rémi Louf, .txttxtvtt▶
• Leads of Nano Banana, Imagen, Veo, Gemini Omni and Omni Thinking recap the year in Generative Mediatxtvtt▶
• Your agents lack context: Here's how to fix "You're absolutely right!" — Brandon Waselnuk, Unblockedtxtvtt▶
• Generative UI... in Python? — Jeremiah Lowin, Prefecttxtvtt▶
• The Agent Behind the Curtain: Building the Oz Cloud Agent Platform — Safia Abdalla, Warptxtvtt▶
• AI in GTM at Notion — Flora Liutxtvtt▶
• The Death of Developer Advocates — Stephanie Jarmak, Sourcegraphtxtvtt▶
• AI-Native Organisations Run on Skills: How to Structure and Scale Them — Imad Touil, QuantumBlacktxtvtt▶
• The Design-Code Roundtrip That Isn't — Jonathan Gordon, ReWeaver AItxtvtt▶
• Designing for AI Engineer — Vincent Wendy, AI Engineertxtvtt▶
• Everyone Gets A Software Company — Benjamin Guo, Zo Computertxtvtt▶
• The End of the Static Screen: Architecting Intent-Driven UX — Gus Iwanaga, commercetoolstxtvtt▶
• How AI Agents Let GTM Teams Scale — Justin Joyce, Cloudflaretxtvtt▶
• Agents' next frontier: agent-to-agent and network effects — Jean-Denis Greze, Towntxtvtt▶
• Gadgets: Personal app vibe coding that is actually safe — Kenton Varda, Cloudflaretxtvtt▶
• Tell the Robot What You Want — Sandhya Subramani, AWStxtvtt▶
• GTM Engineering: The Technical Bits — Everett Berry, Claytxtvtt▶
• How We Got LLMs to Recommend Our Open Source Library — Christopher Burns, Inthtxtvtt▶
• The Building Blocks of GTM Orchestration — Arman Vaziri, Ramptxtvtt▶
• How to build an AI-Native Health Company — Dan Feng, Maven Clinictxtvtt▶
• Don’t be data poor — Anuj Iravane, Anteriortxtvtt▶
• The Spatial Harness: Bringing Agents to the Canvas — Max Drake, tldrawtxtvtt▶
• The Missing Layer in Agentic AI — Giedrius Šteimantas, Oxylabstxtvtt▶
• How long can your skills be before your agent forgets what you told it? — Laurie Voss, Arize AItxtvtt▶
• KV Cache-Aware Routing and P/D Disaggregation on Kubernetes — Yuchen Fama & Ashish Kamra, Red Hattxtvtt▶
• ACP: The Universal Remote Control for AI Agents — Alex Hancock, Blocktxtvtt▶
• Trading Desks to Clinical Trials: Parallels in Applied Vertical AI — Ayush Bhardwaj, Allos AItxtvtt▶
• Teaching AIs to Hack — Prof. David Brumley, Bugcrowdtxtvtt▶
• Building the Engine While Flying the Plane: Launching the Figma MCP Server — Jesse Lumarie, Figmatxtvtt▶
• Agent Spending Without Controls — Rodrigo Coelho & Pranav Maheshwari, Edge & Nodetxtvtt▶
• Data Quality Is the Compute Multiplier — Ari Morcos, DatologyAItxtvtt▶
• The Era of Compound Engineering — Kieran Klaassen, Every/Coratxtvtt▶
• AI Evals for Cross-Functional Teams — Nachiket Paranjape & Swaroop Chitlur Haridas, DoorDashtxtvtt▶
• Prototyping as Leadership: How a CTO Ships with AI Agents — Hursh Agrawal, The Browser Companytxtvtt▶
• What's Next After RLHF? — Diogo Almeida, TypeSafe AItxtvtt▶
• Tribal Dungeons of Global Shipping: AI Agents at Global Scale — Dmitry Buykin, Maersktxtvtt▶
• From Tokenmaxxing to Trusted Throughput — Mingsheng Hong, Ironcladtxtvtt▶
• Data and Environment Curation for Post-Training LLMs — Mahesh Sathiamoorthy, Bespoke Labstxtvtt▶
• x402 isn’t good (yet) — Jan Curn, Apifytxtvtt▶
• AI Agents Are Just Distributed Systems Now — Salman Munaf, TikToktxtvtt▶
• Building Turbopuffer: Gergely Orosz (@pragmaticengineer ) × Simon Eskildsen (CEO)txtvtt▶
• Agentic Sites: Building Hyper Personalized Websites — Carlos Sanchez, Adobetxtvtt▶
• Learning on the Job: The Future of Post-Training — Raymond Feng, Applied Computetxtvtt▶
• Your Code Has Bugs. Lean4 Has Proofs: Formal Verification for Engineers — Varun Pant, AWStxtvtt▶
• MCP Apps: Give the Model Data, Give the User a UI — Dustin Mihalik, Indeedtxtvtt▶
• How to avoid disaster when vibe-coding a billing engine — Andrew Garvin, Stripetxtvtt▶
• Einstein Arena: Harnessing Collective Agent Intelligence for Open Science — James Zou, Together AItxtvtt▶
• Why Your Enterprise Tech Stack Isn’t Ready for AI Agents — Christopher Lovejoy & Saul Howardtxtvtt▶
• Your Agent Evolved. Your Evals Didn't. — Ameya Bhatawdekar, Braintrusttxtvtt▶
• Can LLMs Write Fast Multi-GPU Kernels? — Simran Arora, Together AItxtvtt▶
• From AI-Assisted to AI-Native: Building a Frontier Development Team — Clare Liguori, AWStxtvtt▶
• IT Admin for the AI Workforce — Sarthak Aggarwal, Decaworktxtvtt▶
• When AI Agents Pay and Sellers Monetize: Building x402 Apps on AWS — Anil Nadiminti, AWStxtvtt▶
• How to Generate Mergeable Code with a Context Engine — Peter Werry, Unblockedtxtvtt▶
• How Anthropic Builds: Lessons from Labs — Mike Krieger, Anthropictxtvtt▶
• Give the Agent a Budget, Not a Token — Sachin Malhotra, Anthropictxtvtt▶
• The Last Human Code Review: Building Trust in AI-Generated Code — Itamar Friedman, Qodotxtvtt▶
• MCP Tasks (async): Why Aren't Any Agents Supporting Them? — Cornelia Davis, Temporaltxtvtt▶
• Training Taste — Thais Castello Branco, Taste Labstxtvtt▶
• The Half Life of Agent Infrastructure — Ben Kus, Boxtxtvtt▶
• Beyond the Lethal Trifecta: Agentic Commerce on the Open Internet — David Levine, Kiduna Clubtxtvtt▶
• Design at the Speed of Adjectives — Paul Bakaus, Renaissance Geek, Inc.txtvtt▶
• Your Agent Just Authorized What?! — Jay Mok & Ben Coumes, Paypaltxtvtt▶
• Tethered: Our Agents Are Us — Shu Fang, Two Sigmatxtvtt▶
• Reverse-Engineering the AI Buyer — Aliisa Rosenthal, Acrew Capitaltxtvtt▶
• Why Your AI Agent Needs a Wallet: USDC and Nanopayments — Harshal Bhangale, Circletxtvtt▶
• It’s Tokens All The Way Down: How RLMs are Different — Kevin Madura, AlixPartnerstxtvtt▶
• From coding to Knowledge work agents — Karan Vaidya, Composiotxtvtt▶
• Deep dive on LLM Inference at Scale — Harshul Jain, Audible & Tanmay Sah, Independent AI Researchertxtvtt▶
• Inside 847 Production Clinical AI Notes — Sebastian Fox, Composotxtvtt▶
• Coding Agents Don't Scale Themselves. Neither Do Your Teams. — Patrick Debois, Tessltxtvtt▶
• Unlock Agent Autonomy: The Runtime for AI-Native Systems — Tushar Jain, Dockertxtvtt▶
• Productionizing LLM Gateways: Architecture, Tradeoffs and Hard Lessons — Kanish Manuja, Twiliotxtvtt▶