Gritt AI is now installing 1 MW of solar capacity per day at 4× the speed of a typical installation crew. And our daily installation rate keeps accelerating. At our active site, each day’s installation adds enough solar capacity to meet roughly 200 homes’ annual electricity needs once operational. That’s the milestone: every day, more infrastructure built. Every increase in speed, more capacity to meet America’s growing energy demand. Solar is just the beginning. Next, we aim to bring Gritt’s construction superintelligence to data centers, water treatment plants, and pipelines. Our mission: enable humanity to build centuries’ worth of infrastructure in decades. Civilization. Accelerated. @Jason @andrewbeebe @albertwenger @hayleybay @CleanVC @rebeccakaden @Rajil @GrittRobotics

A worker kneeling beside a solar panel is doing ordinary construction work. But to a robot, successfully identifying that worker may present an edge case: the worker is low to the ground, partly hidden by equipment, and wearing heavy PPE. The problem in identifying the worker starts before model training. Annotation pipelines often reject images when they can’t confidently reconstruct a worker’s full pose. That may improve the dataset's apparent quality, while removing the difficult examples a safety-focused system most needs to learn from. At Gritt, we call this the selection-scarcity confound. After auditing four months of construction-site data, we found that low poses accounted for just 2.2% of the retained person instances. Further analysis suggested that this scarcity was partly created by the filtering process itself. So we separated person detection from pose-label quality, then brought the missing postures into simulation. Adding simulated workers who were kneeling, squatting, or deeply bent over improved detection recall on real site footage for those poses by 1.6 percent and low pose detection by 5 percent. In physical AI, rare examples aren’t necessarily unimportant... in fact, they may be the *most* important when it comes to safety. Read the full post from Gritt Perception Lead, @r15hav, with a link to the paper on arxiv: gritt.ai/news/the-safety-cas…

Gritt is creating a construction superintelligence that can build in decades what would take centuries today. To do that, we've built a generalizable AI backbone that learns representations of the construction site and applies them to any dextrous construction task. This AI is embodiment-agnostic, so we can bring the right machine-and-robotics combination to the site and task that works best, as quickly as possible. We're already deploying across the country, starting in solar and rapidly expanding to new verticals.

Large-scale infrastructure construction sites push physical and spatial AI to their limits. In Gritt’s first technical article, CTO and co-founder Vishal Dugar explains how field data, simulation, and our foundation model build practical intelligence that generalizes across tasks, environments, and embodiments. gritt.ai/news/how-gritt-work…

Going to Pittsburgh is a bit of a homecoming for our founding team of CMU Robotics Institute alums. Join Gritt at #IROS2026 on Monday, September 28th to meet the team, connect with robotics peers, and hear about the traction we’ve gained in deploying a physical AI intelligence layer in the field. RSVP: luma.com/w1zz14gu

How long does it take to teach a Gritt machine a new task? In one case, two days. Using the same AI stack behind our solar work, Gritt trained a robot to tie rebar. Here's @puneetp explaining the larger ambition behind our work: generalizable intelligence for infrastructure construction. Thanks to @JayKapoorNYC for the great interview.

At the Karn site in Michigan, Gritt machines installed thousands of solar panels for Burns & McDonnell without breaking a single module. Go on-site with the Gritt team to see how physical AI adapts to changing terrain and weather while operating safely and precisely.

Today, we’re announcing our partnership with Burns & McDonnell to deploy AI-powered robotics across utility-scale solar construction. The future of solar construction is a physical AI layer designed to build critical infrastructure safer, faster, and with greater predictability. Learn more here: gritt.ai/news/burns-mcdonnel…

At Gritt, we are laser-focused on deploying our systems into the field and getting work done. So far, Gritt has installed 30,000+ solar panels and over 18MW. Take a look at our deployments so far: piped.video/watch?v=obNjUtgv…

41% of skilled workforce in construction will retire by 2031 in US We are seriously short of workforce which can build infrastructure. Having an intelligence which is designed to work in chaotic outdoor setting can help speed up many step and repeat labor tasks. @GrittRobotics we have a mission to help civilization build infrastructure faster by creating an intelligence which understanding the variation of outdoor: rain dust snow. We have actively deployed our robots and handled over 35,000 placements of panels in real production settings. Thanks for a great conversation @JayKapoorNYC And thanks to @obviousvc @usv @albertwenger @Rajil @CleanVC @hayleybay @active_impact for supporting us

35,000 solar panels installed. Zero broken. And that's only the beginning. In his first long-form interview, Gritt CEO Puneet Puri explains our larger ambition: to build a generalizable construction intelligence that can ride on existing equipment and do real work across the world’s largest infrastructure projects. Watch: piped.video/watch?v=I0kiB0xD…

The world doesn’t lack ambition, capital, or demand. It lacks the capacity to build quickly and safely. Our latest post from Gritt co-founders Puneet Puri and Vishal Dugar goes into why infrastructure construction needs an automation revolution built in the field, not the lab. gritt.ai/news/the-world-cant…

RT @hayleybay: Construction is a real-world industry that hasn’t gotten nearly enough TLC from the AI revolution. But it’s an area in deep…

Automation has transformed many industries... but not construction. Now, demand for infrastructure is exploding, the labor pool is shrinking, and we're building slower than ever. Today, Gritt launches to help accelerate the world's infrastructure build-out. Our systems combine robotics and AI, attach to standard equipment already on job sites, and do labor-intensive tasks. They work in the rain, snow, heat, and mud. Gritt is already deployed and doing real work on real job sites today. Learn more about our vision here: gritt.ai/news/the-world-cant…