Manifesto

Robots are moving from labs into the real world: warehouses, homes, farms, cities, but there's a bottleneck nobody talks about.

Software ships fast because every change is tested automatically, push code, run tests, and know what broke in seconds. Decades of tooling make this possible, from CI/CD and test suites to monitoring and observability.

Robots have none of this.

You train a policy, run it on a robot, and it fails. So you SSH in, pull the logs, download the video, and scrub through camera footage trying to figure out what went wrong, one run at a time, hundreds of runs per week, with no patterns detected and no memory between sessions. Every session starts from scratch.

This is the iteration loop for every robotics team on the planet, and it's slow.

The bottleneck isn't just training models; GPUs are fast. It's the work around them: preparing useful training data, testing every change before it ships, and understanding what happened when it fails, at scale, across thousands of runs.

We believe this is a solvable problem.

We're building evaluation and annotation infrastructure for robots. It turns deployment runs and demonstrations into reviewed action labels and task outcomes, and connects failures to their video and sensor evidence. Teams can compare policies across recorded runs and simulation tests, and curate the data needed to improve the next version.

When a task fails, the platform doesn't hand you a red X; it hands you evidence. Subtasks and behavior are annotated on the run and lined up with video, sensor signals and robot state, so the failed window helps locate the problem: data, policy, or hardware. The engineer knows their system. We give them the evidence to decide fast.

And every run compounds. Results become part of the release record, failed windows become curated training data, and every failure becomes a new case in the suite. The test suite grows from exactly what broke in the field, which is how software teams got fast, and how robotics teams will.

This is a hard problem. Evaluating physical behavior across robot types, sensor modalities, and environments is unsolved. We're not afraid of that. Hard problems worth solving are the only ones that matter.

If we succeed, robots iterate as fast as software. And when robots iterate fast, they deploy everywhere and diffuse into every part of society.