Skip to content

AI Agent Android Automation

If you searched for AI agent Android automation, the practical question is whether your agent can inspect real device state, act through a host-side control loop, and recover with replay artifacts. That is exactly the slice Luotsi is built to cover.

  • inspect for structured JSONL exploration of the current screen.
  • view when a human still wants the mirrored device while the agent consumes stream state.
  • run when the flow is stable enough to codify as a JSON scenario.
  • replay when the device session is over and the next question is summarization, search, or triage.
Terminal window
luotsi doctor --device <serial> --fix
luotsi inspect --device <serial>
luotsi scenario-validate --path scenarios
luotsi run --path scenarios --device <serial>
luotsi replay packet --artifacts ./artifacts/<run>
luotsi replay packet --artifacts ./artifacts/<run> --check

This progression keeps the agent loop on the host machine: explore first, codify second, replay after the run. Start replay with packet and packet --check so the agent gets the At a Glance summary, failure snapshot, primary failure, recommended next action, and first-minute checklist before deciding whether to open, summarize, search, draft, or rerun.

When the starting point is Android CLI Journey-style intent, use Evidence-Backed Android Journeys to keep natural-language flow authoring separate from Luotsi’s reviewed scenario and replay evidence path.

  • The agent needs real-device Android state rather than browser DOM state.
  • You want machine-readable JSONL sessions instead of a window-only control path.
  • You want the same runtime to support human debugging, agent exploration, and CI scenarios.
  • You need artifacts after the run, not just a final pass or fail.
  • The workflow never leaves a browser automation surface.
  • You need a cloud platform to supply both the devices and the orchestration model.
  • You only care about scripted end-to-end runs and not agent-driven exploration.