Capture
Bring together your robot's test results and the conditions it worked in.
Skip to main contentYour robots, ready for
01 02 03 01 02 03
Your robots, ready for
new environments.
Supervise your fleet. Judge new skills before rollout.
Our software and hardware layers work together to supervise your fleet and evaluate your robot policies. See what works, what needs attention, and which skills are ready for new environments.
UC Berkeley SkyDeck · Batch 22It works in the demo. Will it work on site?
A different room, new lighting, or a software update can change how your robot performs. Before a fleet takes on a new skill, you need evidence that it works in the conditions it will face. A policy is the software behind a robot skill. Our policy enrollment review helps assess which updates are ready to introduce and which still need testing.
Know what to fix before your next deployment.
See how RunFP software records and compares robot tests to support a policy enrollment review.
Demo data
Check
See where your robot succeeds, where it fails, and what still needs testing.
Understand
Compare results before and after a change to help your team decide what to fix next.
Pick the decision that is blocking your team.
01
Policy Enrollment Review
Judge whether a new robot skill is ready to join your fleet.
- Bring
- Test results before and after the update, operating conditions, software versions
- Leave with
- Readiness review, reliability results, known failures, tests still needed
02
Field Failure Autopsy
Turn a costly field failure into a ranked, testable explanation.
- Bring
- Failed and healthy runs, logs, versions, calibration and operator notes
- Leave with
- Failure cohort, change map, likely contributors, next experiments
03
EOL Yield Intelligence
See which end-of-line conditions are driving rejects and rework.
- Bring
- Station outcomes, configurations, interventions and inspection records
- Leave with
- Yield baseline, loss segments, recurring signatures, action queue
Evidence in. Findings out.
Inputs
247labeled hardware runs
- Model, code and calibration versions
- 6 lighting setups · 4 calibration bands
- 18 object poses and run-level outcomes
Outputs
91%reliability · 95% CI [87%, 94%]
- Reliability segmented by condition
- Coverage matrix with confidence bounds
- Low-light called out as untested, not assumed
Engineering findings
Camera position shift aligned with a cohort drop from 91% to 64%.
- Candidate model showed 3× more object drops
- Runtime latency increased 18 ms after a software change
- Resulting success rate moved down 8 points
Anonymized snapshot. Association is reported separately from causation; findings become experiments to confirm.
The OORB loop
Capture every run. Score reliability. Explain what changed.
01
Capture the evidence available
Start with the outcomes and metadata your stack already produces. During intake, we identify gaps and agree on any additional instrumentation before the evaluation starts.
02
Score by operating condition
Report success and intervention rates with confidence intervals, cohort comparisons and an explicit list of conditions that remain untested.
03
Explain the movement
Link version, calibration and environment changes to outcome shifts, then rank the next experiments needed to confirm the likely cause.
Keep robot data inside your boundary.
Raw logs and video can stay in customer-managed infrastructure. Access, retention and deletion are agreed before data moves.
Local-first option
Process raw run data in a customer-controlled environment when required.
Minimum necessary data
Share derived run manifests and results instead of raw media where possible.
Scoped access
Use read-only paths where possible and document retention and deletion up front.
Evaluate one robot behavior before it ships.
We will come to your deployment site and provide a full audit, free of charge.