ClawMetry
Field notes
Building Mizu with SO-101 arms: ClawMetry at La Machine
A firsthand account of Mizu, the Healthy Desktop prototype, with original team photos and the historical ClawMetry dashboard.
Field notes from the physical world.
Real builds, inspectable evidence, and the questions we are still working through. Follow the work from SO-101 arms in Amsterdam to a remote robot pilot and the next hackathon.
Developer guide
Developer guide
SO-101 and LeRobot observability: what to record before your next run
An evidence checklist for the SO-101 workflow, from calibration context and camera freshness to a useful saved run.
Developer guide
Robot cameras, telemetry, and replay: how to investigate a failed task
A step-by-step investigation method for camera freshness, state mismatches, recording gaps, and historical review.
Developer guide
From simulation to a real robot: an observability validation checklist
A practical path from an inspectable simulator record to one carefully documented hardware result.
Integration notes
Integration notes
Inside the ClawMetry and BluPe robot observability pilot
The early BluPe pilot, explained through its actual interface, recorded evidence, and an instructive warm-up failure.
Event preview
Event preview
ClawMetry at Leukerbad Robotics Hackathon 2026: what we plan to test
Confirmed selection and a concrete test plan for November 14 to 16. An event preview, with results to follow after the hackathon.
Research analysis
Research analysis
The METR and Anthropic report: what Physical AI builders can learn
The primary report, its limits, and our interpretation of what evidence-led evaluation means for robot builders.
Foundations
Foundations
What is Physical AI observability? Follow a task from instruction to outcome
A clear introduction to the task, evidence, timing, and outcome questions behind robot observability.
Foundations
Robot guardrails: the difference between seeing, blocking, and stopping
A vocabulary for evaluating robot guardrails, with clear boundaries between observation and an actual control response.
Each article distinguishes historical experiments, current integration work, proposed tests, and external research. Photographs, screenshots, organizer artwork and diagrams identify their sources and context.