Industrial Next Aims to Let Factory Robots Change Tasks in Minutes, Not Weeks

Industrial Next helps manufacturers automate delicate, complex work that has traditionally required human workers.

Disrupt 2026 has officially begun. Get your pass now to be in the center of the startup hub. Register now

Disrupt the doors opening on October 13th. Get your card and bring someone with you with a 50% discount. Register now.

In most factories, automation is fixed: robots and machines are programmed for a specific task and product. A line change means reprogramming and physical retooling or equipment replacement, which can take weeks or months. San Francisco-based Industrial Next says it's changing that.

Presented today at Startup Battlefield at TechCrunch Disrupt 2026, the startup builds AI-powered robotic stations with proprietary base models that connect vision, context, and motion. The company says it enables a production line to be retooled in minutes instead of weeks without traditional programming. The goal is to allow manufacturers to automate complex and delicate tasks that traditionally require human labor.

The company announced on stage that it is working with BMW Group's technology office to evaluate Industrial Next's artificial intelligence manipulation for production.

Industrial Next was founded in 2021 by Lucas Pancao and Alan Pan, both of whom previously worked at Tesla. Before joining Waymo, Pankao served as a chief electrical architect at Tesla. Pan led Tesla's autonomous factory efforts and later became chief architect at autonomous driving company Neolix.

The couple came up with the idea of Industrial Next while working together at Tesla. Pankaw's first encounter with Pan literally fell on him, as Pan was asleep after pulling an all-nighter on the factory catwalk. Although the two didn't get along at first, they soon realized they had a common obsession with getting things done and complementary skills.

After years of watching advanced automotive and self-driving technologies, the founders realized that manufacturing needed to be revamped.

"We had all these fancy things we could do on cars. I could run machine learning algorithms to design a car for me. But I couldn't figure out how to program a robot, and that was very common for Tesla engineers," Pancao said. "You had this huge gap, right? You had people who were really into what they were doing — designing cars and designing autonomous systems — and then you effectively suppressed them in a factory that was looking at this equipment from the 1980s. And so we started rethinking what that should look like using the technology we have today and using everything we know today."

Even after moving on to their next job, the two reflected on their frustrations with industrial equipment. They stayed in touch, often recalling machines that never worked the way they wanted, and eventually decided they could do better.

"I was at Waymo at the time, I was kind of bored because I missed that Tesla speed," Pancao said. Pan, he added, held a similar position at Momenta, a developer of self-driving systems in China. Pan recalled their conclusion: "We're not getting any younger, and we're still obviously interested in it. We're still complaining about industrial technology. Say, three years from now, we've got to start the company."

Pankau points out that traditional industrial robots are typically programmed to perform very specific, repeatable tasks. As a result, even a small change in the process or product can cause the robot to fail or cause costly failure, forcing manufacturers to simplify their products for repeatability.

Making truly flexible robots presents a different challenge. They require massive amounts of training data, and unlike AI models trained on the Internet, robotics lacks the vast datasets needed to train machines to perform complex physical tasks.

"We can get robots to do all these cool things like dance because there's data for that, but we can't get them to collect things with high precision," Pankau explained. This is where we have made great progress in using simulated environments to perform these tasks with high precision and skill. "The secret sauce for the robots we have is that we've given them an overall understanding of the process, but we build that understanding using a very high-fidelity simulation engine that's so close to real dynamics that we almost allow the robots to perform these exact tasks without ever seeing the parts."

In other words, robots train in a highly detailed virtual world that closely mimics the physics of the real world. Industrial Next robotic stations can be reconfigured, combined and redeployed on production lines. New tasks are taught through simulations and demonstrations rather than hard-coding scripts.

Pankau explained that some of the startup's workstations are currently being used to make one of the world's most popular smartphones. They do things that manufacturers have tried and failed to automate for years, like twisting a delicate flexible cable and snapping a tiny connector cap into place. (He wasn't authorized to disclose the customer.) He also described a "film peeling" station, where their AI-powered robots peel away the protective film on camera modules and buttons at human speed or faster with 100 percent accuracy, even when being transferred to a new phone model and production line they've never seen.

"We started this company because this is the kind of functionality we aspired to have at Tesla, where we were bypassing robot stations because we couldn't program them well enough using traditional technologies," Pancao said. Now we want to do this to more complex tasks than building a phone. "Ultimately, we want to do this by building a complete car without any human contact."

For more coverage of the Startup Battlefield—along with a list of well-known founders and VCs you don't want to check out, miss—join us at Disrupt, happening this week in downtown San Francisco.

When you make a purchase through links in our articles, we may earn a small commission. This does not affect our editorial independence.

Ayesha is a consumer news reporter at TechCrunch. Before joining the publication in 2021, he was a telecom reporter at MobileSyrup. Ayesha holds a Bachelor's degree with honors from the University of Toronto and a Master's degree in Journalism from Western University.

You can contact or confirm Aisha by sending an email to [email protected] or by sending an encrypted message to aisha_malik.01 on Signal.

Get 50% off a second pass The Disrupt experience is meant to be shared. Grab your pass and bring a colleague, partner or peer for 50% off. Cover more ground by building connections, building momentum, and discovering what's next in the startup ecosystem.

Elon Musk attacks Ambani over Jagmeet Singh's India Starlink launch delay

Batteries are now cheaper than the natural gas turbines used in many of Tim de Chant's data centers.

Remember Orkut? Its founder wants to bring back Jagmeet Singh

The United States barred Microsoft, Adobe and major IT companies from the green card program for skilled foreign workers Ayesha Malik.

Elon Musk questions Ambani influence as Starlink India launches on Jagmeet Singh stands

The 19-year-old founder of Cal AI just raised $10 million for his new AI startup Julie Burt.