Computer use without screenshots
A local CoreML model finds every button and UI element on screen, on-device OCR reads the labels, and that text is all Jev gets.
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.3.77
Key facts
- Vertical
- Cross-industry
- 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/computer-use-without-screenshots
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 “Computer use without screenshots”?",
"input": "<input to classify>",
"output": "one label from a fixed list"
}Related use cases
Cite this
Copy a link in your preferred format.