Formant Verified

Henrik Bennetsen

For over a decade we’ve been deploying robots into the wild. We give physical AI the verified real-world data—graded at capture—to take models beyond demos. Learn more at www.formant.ai Stay in the Xloop @FormantInc

Episodes

  1. 17 hr ago

    Formant Verified: What Makes Robotics Training Data Gold with Co-Founder of Northstar Robotics

    The conversation explores the evolving landscape of robotics data, focusing on the types of data used, the importance of real-world data collection, and the challenges faced in training robots effectively. Miki, the co-founder of Northstar, discusses the significance of high-quality data, the transition from lab to real-world applications, and the future of robotics in terms of deployment and data collection. The conversation explores the evolving landscape of robotics, focusing on teleoperation, hardware innovations, and the future of data collection in robotics. Miki discusses the importance of diverse data sets, the role of teleoperation in achieving autonomy, and the challenges and opportunities in the robotics data market. Takeaways Importance of real-world dataFuture of robotics deployment Teleoperation is essential for roboticsDiverse data sets enhance robot performanceChapters 00:00 Introduction to Robotics Data03:08 Current Landscape of Robotics Data05:03 Understanding Trainable Data06:35 Challenges of Lab vs. Real-World Data08:37 Market Dynamics in Robotics Data10:39 Recent Developments in Physical AI12:59 Pricing and Customization of Data15:34 Quality Control in Data Collection17:09 Northstar's Vision for Robotics18:39 Future Data Modalities20:32 Reliability in Robotics21:56 Lessons from Frontier AI23:54 Differences in Physical AI Training Data25:51 Teleoperation and Remote Control29:23 Teleoperation: A Bridge to Autonomy31:50 Innovations in Robotics Hardware35:55 The Future of Data Collection41:15 Data Capture Day: Behind the Scenes47:32 Fair Compensation in Data Collection50:55 The Robotics Data Market Landscape53:12 Understanding Valuable Data in Robotics

  2. 1 Oct

    Formant Verified: Inside the Robotics Data Bottleneck with Sam Padilla

    The conversation explores the challenges and insights from Sam Padilla's experience in the robotics data market, particularly focusing on the difficulties of building a sustainable business around robotics training data. Sam discusses the complexities of data collection, the importance of understanding buyer needs, and the evolving landscape of data in robotics. The conversation delves into the evolving landscape of robotics and AI, focusing on the challenges and opportunities for newcomers in the industry, the emotional toll of startup failures, and the importance of transparency and community engagement. Sam Padilla shares insights on the future of humanoid robots, the significance of learning from failures, and the potential for embodied AI to revolutionize various sectors. Takeaways Robotics data market is challengingUnderstanding buyer needs is crucial Embrace failure as a learning toolFocus on community and transparency Chapters 00:00 Introduction to Robotics Data Challenges02:35 The Complexity of Robotics Data Collection07:13 Go-to-Market Strategies in Robotics Data10:53 The Labor-Intensive Nature of Data Collection11:23 Geographical Choices for Data Collection12:55 Incentives for Data Collectors14:07 The Commoditization of Video Data15:53 Hardware vs. Software in Data Collection18:15 Market Dynamics and Competitive Landscape20:27 Understanding Data Buyers22:16 The Role of Data Brokers24:00 The Elusive Nature of Data Buyers26:56 The Challenges of Exclusivity in Data Deals30:06 The Lifecycle of Data Value32:30 Navigating Buyer Needs and Data Types34:56 The Future of Robotics Data Market42:20 Navigating the Robotics Landscape48:15 The Emotional Toll of Startup Failure52:03 Open Sourcing and Community Engagement58:16 Humanoid Robots: Pros and Cons01:05:10 Key Lessons for Robotics Entrepreneurs01:10:14 Future Directions in Robotics and AI

    Formant Verified: Inside the Robotics Data Bottleneck with Sam Padilla

  3. 5 May

    Manufacturing AI: The Lost Decade With Dr. Matthew Gordon

    The conversation with Matt Gordon covers his journey from early career to founding A3 Analytics, insights from Toyota Research Institute, challenges in implementing machine learning in manufacturing, lessons from early days at Palantir, and the interplay between forward deployed engineers and software engineers. Matt also discusses the challenges in advanced manufacturing and AI adoption, the role of AI in manufacturing, and the balancing of software and services at Palantir. The conversation highlights the Rice Theory of Culture and its impact on manufacturing, as well as the contextualization of data with LLMs. Finally, Matt shares insights into the role of forward deployed engineers and the concept of Data-driven Kaizen. Takeaways Data-driven KaizenChallenges in ManufacturingHolistic vs Analytic Thinking Chapters 00:00 Challenges in Advanced Manufacturing and AI Adoption

  4. 29 Apr

    Boots on the Ground Tech

    The conversation explores the impact of AI technology in the field, focusing on productivity enhancement and the importance of data structuring. It delves into customer stories, time savings, quality of data, and the future vision of AI in the physical world, highlighting the adoption of robotics and drones, customer interaction, and the evolution of field operations. Takeaways AI in the field enhances productivityData structuring is crucial for AI technology Chapters 00:00 Introduction and Mic Check05:27 Time Sheets and Billing12:02 Rich Context and AI Interfaces17:33 Customer Interaction and Scheduling

    Boots on the Ground Tech

  5. 17 Apr

    What AI Gets Wrong About Manufacturing

    The conversation covers Formant's services, Caleb's role as a forward deployed engineer, the challenges of operational complexity in manufacturing, and the potential of AI in predictive maintenance. It also explores the collaboration between software and services, as well as the issue of data-rich, action-poor environments in advanced manufacturing. Takeaways The role of a forward deployed engineer involves on-site interaction with customers and the translation of customer needs into product features.The potential of AI in predictive maintenance offers a new approach to solving long-standing problems in advanced manufacturing. Chapters 00:00 Introduction to Formant's Services09:24 Operational Complexity in Manufacturing Facilities16:20 Collaboration Between Software and Services22:33 Predictive Maintenance in Manufacturing27:37 Data Rich, Action Poor in Advanced Manufacturing

    What AI Gets Wrong About Manufacturing

  6. 17 Mar

    AI Agents on the Factory Floor: From Chaos to Clarity

    In this episode, Henrik Bennetsen and Fin Elliott pull back the curtain on the "Data-Rich, Action-Poor" reality of modern manufacturing. While the world hears "automation," the truth on the ground is often a "tsunami of alarms"—sometimes over 9,000 per day—that leave operators drowning in noise. Henrik and Fin discuss how Agentic AI is changing the game by moving beyond simple dashboards to active investigation. We dive into: The 9,000 Alarm Problem: Why a single facility's sensor systems can generate more data than humans can realistically process. Investigation Blueprints: How Formant captures "tribal knowledge" to train AI agents as specialized procedural masters for your specific site. The Junior Technician at Scale: Real-world results from semiconductor pilots where AI identified over 50% of alarms as false or "shelved," saving massive amounts of human labor. Chaos to Clarity: Shifting from reactive "firefighting" to a stable, scalable operational flow

    AI Agents on the Factory Floor: From Chaos to Clarity

  7. 10 Mar

    Why a 100-Year-Old Fleet Giant Just Went All-In on Robotics

    Ready to audit your own automation strategy? Don’t let your next robotics investment collect "robot dust." Visit [Link] to download our Robotics Deployment Checklist—a framework used by Holman and Formant to ensure every machine drives measurable business value from day one. Resources |👉 Explore the Holman-Formant Partnership: Formant.io Learn how to scale your fleet without scaling your headcount. We dive deep into the specific Physical AI workflows mentioned in this episode and how Holman is redefining asset management for the next century. 🚀 Join the Movement: Follow Formant on LinkedIn Don’t get left behind as the industry moves to AI-driven ops. Follow us for daily insights on robot-human collaboration and the software power behind the world’s largest fleets. 🚛 Experience the Legacy: Holman Official Website Visit the home of the 100-year-old leader in automotive and fleet services. To see their specific work in automation, check out the Holman Robotics division. 🔗 Connect with the Experts: Holman on LinkedIn Stay updated on the latest hardware and service innovations from Joe Foster and the Holman team as they play offense in the robotics space. #Robotics #PhysicalAI #FleetManagement #Automation #Formant #Holman #IoT #FutureOfWork

    Why a 100-Year-Old Fleet Giant Just Went All-In on Robotics

  8. 4 Mar

    How AI Agents are Automating Physical Operations

    Are your operations data-rich but action-poor? Most operational teams spend 40% of their time "firefighting" data alerts. In this episode, Henrik Bennetsen and Fin Elliott show you how to hand that work off to AI Agents. The Demo | Watch as we build a "digital brain" for physical AI using Formant Triage. We move away from complex coding and toward "Plain English" instructions, allowing AI to: Analyze telemetry spikes (like thermal shock) in real-time.Reason through failures using specific business principles.Collaborate with human operators through "Human-in-the-Loop" checkpoints. Key Chapters | 0:00 – The Vision: AI Agents vs. Human Teams 2:15 – Demo: The "Triage" Kanban Board 5:05 – Setting Triggers: From Data to Action 9:30 – Why "Plain English" is the New Coding 13:15 – Human-in-the-Loop: Managing AI Autonomy 23:00 – Cost vs. Intelligence: Choosing the Right AI Model 44:00 – From Rules-Based to Principle-Based Ops Resources | 👉 Read the Full Breakdown: Learn More Learn how to scale your fleet without scaling your headcount. We dive deep into the specific AI workflows mentioned in this video on the Formant Blog. 🚀 Join 10k+ Robotics Leaders: Join the Fleet Don’t get left behind as the industry moves to AI-driven ops. Follow us on LinkedIn for daily insights on the future of robot-human collaboration. #Robotics #AIAgents #Automation #Formant #IOT #AI

    How AI Agents are Automating Physical Operations

  9. 22 Jan

    The Future of AI Agents in Software

    In this conversation, Henrik Bennetsen and Jeff Linnell explore the transformative impact of AI agents on software and robotics. They discuss the evolution of software from traditional models to more dynamic, disposable forms that adapt to user needs. Jeff shares his extensive background in robotics and automation, emphasizing the importance of human factors in technology adoption. The discussion highlights the shift from dashboards to proactive AI agents that can analyze data and take action autonomously. They also delve into the significance of incorporating tribal knowledge into AI systems and the necessity of building trust through transparency and engagement. The conversation concludes with insights on the future of interfaces in AI software and the evolving landscape of business in the age of AI. Takeaways AI agents can take initiative within workflows.Software is becoming more disposable and adaptable.The evolution of software requires a participatory approach.Robotics deployment faces challenges related to human factors.AI agents can proactively solve problems before human intervention is needed.Data richness is crucial for effective AI and robotics.Institutional knowledge is invaluable for operational efficiency.Trust in AI is built through engagement and transparency.Interfaces should be flexible and user-driven.The landscape of business is rapidly changing with AI advancements.

  10. 02/12/2025

    Inside Formant’s AI Hackathon: Becoming an AI-First Company

    In the new podcast episode, Henrik sit down with our Technical Product Manager, Fin Elliott, to unpack what came out of it, including: A prompt-driven robot simulator that lets our team spin up realistic, vertical-specific demos in hours instead of weeks.A compensation review tool built by HR + chief of staff using AI-assisted “vibe coding,” no traditional dev team.Examples of going from “idea in Slack” → working proof of concept in front of customers in a couple of days.

  11. 21/11/2025

    Physical AI: From Rules to Principles

    In this episode, Henrik chats with Richard Anaya, Formant's Head of AI, about his essay, "Physical AI: From Rules to Principles." They explore topics such as why traditional robots often get stuck in a loop with their rigid rules and how we can transform them by using principles rather than just a series of if–then statements. This shift might just be the key to helping machines thrive in the real world! If you're curious about Physical AI—what it means, why it matters, and where things are headed—this episode is a must-listen! Article can be read here!

  • 11 Episodes

About

For over a decade we’ve been deploying robots into the wild. We give physical AI the verified real-world data—graded at capture—to take models beyond demos. Learn more at www.formant.ai Stay in the Xloop @FormantInc

Information

  • Creator
    Henrik Bennetsen
  • Years Active
    2025 - 2026
  • Episodes
    11
  • Rating
    Clean
  • Copyright
    © 2026 Henrik Bennetsen
  • Show Website
    Formant Verified