Enroll in shadow mode
Shadow mode is a dry run on real fleet data. Patchling evaluates your pinned policy against live canary signals and records what it would promote, pause, or roll back. without executing. Your OTA still ships. You still hold the switch.
- EnrollEmbed on the promote path of the OTA you already run. agent, API, and policy file.
- Would-have on paperReal signals, pinned policy. a would-have trail, not a fleet action. Deterministic; no model in the loop.
- You flip when readyEarn autonomy per rule, per market, when the pack is boring and right.
Work email, company, and fleet size. That’s enough to start. Add a note about your OTA if you want.
Prefer email? hello@patchling.io. Shadow is the land path: real device, still zero autonomous actions.
Built for fleets that can't afford a bad canary.
Start with a dry run.
Shadow mode runs your pinned policy on real fleet data and records what the gate would promote, pause, or roll back. without touching the fleet. Package on the device when you're ready; it does not wrap inference or sit on the GPU path. You hold the switch until a rule earns live.