# jev-chat-jarvis-mac

A floating window for macOS that reads WeChat messages off the screen, has a small local model judge intent and risk, and then generates reply candidates in the chosen register.

Grade: X — Not 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.. Score: 4.76.

Vertical: Cross-industry.

Function: Social & creator.

Status: Seen in the wild.

Volume: high.

Value: meaningful.

Risk: moderate.

Evidence: described plan.

Flags: check-fit.

- [Source](https://madewithjev.com/builds/jev-chat-jarvis-mac)
- [Vertical](/verticals/cross_industry/)
- [Function](/functions/social_creator/)
- [Comment toxicity and harassment detection](/use-cases/comment-toxicity-and-harassment-detection/)
- [Content moderation and brand safety](/use-cases/content-moderation-and-brand-safety/)
- [Social clip caption brand risk pre-check](/use-cases/social-clip-caption-brand-risk-pre-check/)
- [Embargo leak monitor](/use-cases/embargo-leak-monitor/)
- [Twitter/X sentiment analysis at scale](/use-cases/twitter-x-sentiment-analysis-at-scale/)
- [Comment spam and off-topic detection](/use-cases/comment-spam-and-off-topic-detection/)