WeChat automation with Jev and DeepSeek
It reads the app node tree through Android accessibility services and falls back to screenshots when the tree is not enough, with Jev deciding the next step.
XNot a typed-decision job: needs written output, plain rules or lookups would do it, or needs raw image or audio. Also marks ideas that must not be built.3.89
Key facts
- Vertical
- Software & tech
- Function
- Agents & dev
- Status
- Seen in the wild
- Volume
- routine
- Value
- minor
- Risk
- moderate
- Evidence
- described plan
- Flags
- check-fit
Source: https://madewithjev.com/builds/wechat-automation-jev-deepseek
Build this with a classifier
Define a typed decision with a bounded answer, then evaluate it on examples.
{
"decision_type": "choice",
"question": "Does this input match the decision in “WeChat automation with Jev and DeepSeek”?",
"input": "<input to classify>",
"output": "one label from a fixed list"
}Related use cases
Cite this
Copy a link in your preferred format.