Happening this week: Rethinking Predictive Maintenance with Physical AI Agents webinar 📅 Our physical world model, Newton, generalizes across different machines, adapts to new conditions in real time, and learns from the sensor data you already have. This approach to predictive maintenance keeps intelligence useful as equipment, processes, and operating conditions change. If you’re interested in the ways Newton can help your organization make operations more efficient, register here: luma.com/jwedb311

🗣️ Last call to register for our predictive maintenance webinar on Sept. 24. 🔗 luma.com/jwedb311

Next week in Houston: Jaime Lien, Archetype Co-Founder and Chief Scientist, is speaking at AI4Energy Americas about non-productive time in drilling, which can cost upwards of $100K an hour. Jaime will cover how Newton enables real-time insights and adaptive decision-making for critical infrastructure. 📍 Houston, TX | Sept 28–29

There is a default way people talk about AI right now. You delegate the work, the agent handles it. Archetype Co-Founder and CDO Leonardo Giusti suggests we take a different approach. "What if AI worked like a microscope or telescope? Not replacing the scientist, but giving them a new understanding of the world around them. That's the lens we should be designing toward." Leo spoke with Massimo Banzi at Super Moderno on augmentation, agents, and why the best AI doesn't replace human judgment.

In "The Evolution of Physics", Einstein says that what matters is to pick and frame the question; the solution is mostly technical. That’s even more true now: AI is commoditizing technical. Humans' role will be to decide what truly matters and frame it so machines can solve it.

📅 Join us Sept 24: Rethinking Predictive Maintenance with Physical AI Agents Equipment doesn't always fail in ways you've seen before. And as predictive maintenance expands across more assets and operating conditions, building and maintaining specialized models can make coverage difficult to scale. Physical AI offers a different approach. Our physical world model, Newton, generalizes across different machines, adapts to new conditions in real time, and learns from the sensor data you already have. In this session on predictive maintenance, you will learn how to: 🔎 Discover: Surface previously unseen anomalies without labeled failure history or predefined signatures. 🔄 Adapt: Keep intelligence useful as equipment, processes, and operating conditions change. 📈 Scale: Extend predictive intelligence across pumps, motors, compressors, cooling systems, and more without building a specialized model for every asset. Save your seat: luma.com/jwedb311

📅 Join us Sept 24: Rethinking Predictive Maintenance with Physical AI Agents. Equipment doesn't always fail in ways you've seen before. And as predictive maintenance expands across more assets and operating conditions, building and maintaining specialized models can make coverage difficult to scale. Physical AI offers a different approach. Our physical world model, Newton, generalizes across different machines, adapts to new conditions in real time, and learns from the sensor data you already have. In this session on predictive maintenance, you will learn how to: 🔎 Discover: Surface previously unseen anomalies without labeled failure history or predefined signatures. 🔄 Adapt: Keep intelligence useful as equipment, processes, and operating conditions change. 📈 Scale: Extend predictive intelligence across pumps, motors, compressors, cooling systems, and more without building a specialized model for every asset. Save your seat: luma.com/jwedb311

Excited to be a part of this amazing peer group of incredible entrepreneurs and visionaries and talk about our vision of @PhysicalAI.

Calling technical ML/AI and data engineers! 🗣️ We’re looking for 15 people who want to test and deploy our physical world model, Newton. It’s BYOD (bring your own data), so you’ll use your own sensor and video data to build with Newton Agents and our API in real time. Plus, after the meetup, you'll have continued platform access for several weeks and a dedicated Slack channel with access to the Archetype AI team to ask questions and get answers. Think of this as a real opportunity to understand what Physical AI is capable of and apply it to your everyday job. Save your spot here ⬇️ lnkd.in/gyEm-Tfp

We attended Lanner EdgeAI Summit this week and showcased our physical world model, Newton. Our head of solutions engineering, Sisinio Baldis, shared how Newton Agents bring practical AI capabilities directly to the edge. From anomaly detection and task verification to real-time operational insights, these agents are designed to solve complex physical-world challenges across industrial environments.

One week left to apply to join our September 15 developer meetup! Calling all ML engineers, data engineers, and technical leads who are interested in exploring what Physical AI can do for their organization. Join our 2-hour virtual meetup where you will work with the Archetype team to build a custom agent powered by our physical world model, Newton. After the event, you will receive Slack support from the Archetype AI product team as you finalize your build. This is an opportunity to bring your own sensor or video data and work to solve a real-world problem in your industry. 🔗 Apply for Newton Meetups today: archetypeai.io/newton-meetup…

Newton Agent with skills are packaged instructions that teach a coding agent how to run a Newton task. Every agent blueprint also has a playground for testing against sample data. ➡️ Python SDK, agent skills, and the playground are all live: docs.archetypeai.app/for-age…

Early experiments with Newton running on a Raspberry Pi, discovering the physical world through sensor data, not video or images.

The Manufacturing Leadership Council recently published a survey that validates some of my observations. 53% of organizations report that their data comes from incompatible systems and formats. Another 28% lack the skills to analyze their data effectively. Counterintuitively, more data often means less clarity, and more sensors make it harder to make decisions. Real-world industries need tools for turning data and observations from sensors into actionable understanding. That's the core vision behind our physical world model, Newton. It is pre-trained on billions of cross-modal sensor measurements (vibration, pressure, temperature, current, acoustics, radar, video, time-series telemetry, and more). It generalizes across machines, sites, and use cases without a custom model built for each one and delivers insights, predictions, and automation to our customers. Newton eliminates those pain points and turns data into insights and decisions. Full report: manufacturingleadershipcounc…

What if the most valuable skill right now isn't predicting the future, but seeing the present differently? @FastCompany spoke with Archetype AI Co-founder and Chief Design Officer, Leonardo Giusti, on why Physical AI lives in the space everyone else is overlooking. Read on: fastcompany.com/91585811/dur…

We’re excited to have Naji on board at Archetype AI! Naji brings operational infrastructure expertise from Scale AI, Vercel, and Google and joins us as our Sr. Executive Business Partner. Welcome to the team 👏

Machines already have a perception system. Most of them don't have the intelligence to interpret these signals. We built our physical world model, Newton, to change that. In this demo, Newton learns to distinguish two distinct physical states (fan on/off) in real time using only sensor streams via an IMU connected to a Raspberry Pi. No labels. No training data. Just raw signals translated into insights. Newton is pre-trained on billions of cross-modal sensor measurements (vibration, pressure, temperature, current, acoustics, radar, video, time-series telemetry), so it can generalize across machines, sites, and use cases without a custom model built for each one.

LLMs were designed to work with text and images, but can’t compete when it comes to drawing insights from physical world data. That's why we built our world model, Newton. In this webinar our head of solutions engineering, Sisinio Baldis, explains how agents build on top of Newton to support upstream oil and gas operations. Watch the replay: piped.video/watch?v=BAY_yTXp…

📢 15 seats spots left for the first Newton Meetup on September 15. You will use your own data to build Physical Agents powered by our world model. - Two-hour virtual session with hands-on support from Archetype AI - Bring your own sensor or video data and a physical-world use case you actually care about. - Built for ML engineers, data engineers, and technical leads Afterward, you’ll have access to Newton for several weeks, plus a dedicated Slack channel with our engineers. Come test a physical world model instead of reading about one: archetypeai.io/newton-meetup…

Most industrial AI systems encode static physics like hardcoded equations for each use case, each customer, each facility. Newton is trained on raw sensor data and develops an emergent physics understanding.