Multi-account and multi-device operations
Run the same saved Flow across different authorized accounts, devices, or emulator instances. Parameters, Flow inputs, variables, and node outputs let each run adapt without rebuilding the workflow.
AI Android automation
AI Android自動化ツール
Use AI to generate repeatable Android automation Flows, then run the same parameterized workflow consistently across devices and emulators.
実機AndroidWindowsとmacOSマウス・キーボード操作カスタムキーマッピング複数端末グループ
LaiCai
Why use AI Android automation?
A one-time AI action is useful for exploration, but real operations need consistency. LaiCai Flow turns Android work into saved, parameterized automation profiles with explicit nodes, run logs, and reusable inputs and outputs.
- Save automation as repeatable Flow profiles instead of one-off AI actions.
- Use parameters, Flow inputs, variables, and node outputs so the same workflow can adapt to different accounts, content, devices, or task data.
- Keep results consistent with explicit node order, stable contracts, branches, waits, and structured outputs.
- Debug runs with node status, logs, screenshots, outputs, and clear failure points.
- Validate on one Android target, then reuse the stable flow across device groups or emulator workflows.
手順
How LaiCai Flow automation works
Create the workflow visually, let AI help with structure, test it on one target, then scale only after the run is reliable.
- 01
Install LaiCai on your Windows PC or Mac.
- 02
Connect an Android device or supported emulator to the LaiCai workspace.
- 03
Open LaiCai Flow and create a workflow in Graph View.
- 04
Use LLM chat or MCP to generate a draft flow when you want AI assistance.
- 05
Run the flow on one Android target and inspect logs, screenshots, and node output.
- 06
Refine the flow, then reuse it across device groups or emulator workflows.
ワークフロー
LaiCai Flow automation use cases
Content, form, and search workflows
Automate repeated Android app steps such as opening a screen, searching, filling forms, reading text, checking results, and continuing from structured OCR, UI, API, or LLM output.
Status checks, screenshots, and result reporting
Build stable flows that inspect app state, capture screenshots or recordings, save evidence, call HTTP APIs, write outputs, and use run logs to verify what happened on every device.
Automation comparison
How LaiCai Flow differs from common Android automation approaches
One-off AI agents
Useful for exploring a task or asking AI to try something once.
LaiCai Flow saves the result as a reusable Profile with explicit nodes, parameters, inputs, outputs, and run logs, so the same workflow can run consistently again.Macro recording and fixed scripts
Good when every screen, coordinate, account, and timing stays the same.
LaiCai Flow can change behavior from parameters, OCR, vision results, API data, variables, and branches, so it is built for repeatable Android automation rather than fixed replay.General RPA or test frameworks
Powerful for developer-led desktop or test automation projects.
LaiCai Flow focuses on production-style Android operations: visual graph editing, AI-assisted generation, stable node contracts, run-log debugging, and reuse across device groups.よくある質問
AI Android automation FAQ
Is LaiCai Flow just a one-time AI action?
No. LaiCai Flow saves automation as a repeatable Profile with explicit nodes, parameters, inputs, outputs, and run logs. You can generate it once, debug it, parameterize it, and rerun it consistently across devices, accounts, or task data.
Can LaiCai Flow use YOLO or object detection?
Yes. The vision.detect node can run a selected local YOLO/ONNX object detection model, then output the best rectangle, center point, confidence score, class name, and detection list for later tap or branch steps.
Does LaiCai Flow support LLM text and image analysis?
Yes. llm.textAnalyze can analyze OCR, API, file, or other node output text. llm.imageAnalyze can inspect screenshots or image artifacts with a vision-capable runtime LLM and return stable structured JSON fields for later branches.
Can it recognize text, buttons, or images on the screen?
Yes. LaiCai Flow supports vision.ocr for ROI text recognition, vision.match for template image matching, ui.find for Android UIAutomator element search, and vision.capture for screenshots used by LLM or downstream nodes.
What Android actions can a Flow run?
A Flow can tap, swipe, long press, drag, type text, send keys, set or read clipboard text, open or force-stop apps, go Home or Back, then organize the work with wait, branch, repeat, for-each, until, and child Flow nodes.
Can a Flow speak or play voice prompts?
Yes, with one boundary: audio.speak plays text aloud on the desktop LaiCai computer using desktop text-to-speech from the local speech engine. It is for spoken reminders or OCR/API result announcements, not Android device-side TTS.
Can Flow connect HTTP, ADB, AutoJS, or macro steps?
Yes. LaiCai Flow includes http.request for external APIs, adb.shell for Android shell commands, autojs.run for existing AutoJS scripts, macro.play for saved macros, plus file, template image, and storage data nodes.
Automate Android workflows with AI
LaiCai Flow is built for repeatable Android automation: generate the workflow once, parameterize it, debug it, and run it consistently whenever the task comes back.