devwithjevJev Guard Prevents Wrong-Chat Prompts
Ron Adin built a Jev guard that compares recent chat context with a newly sent prompt to stop him from sending prompts to the wrong coding-agent session.
Ron Adin@adin_ron๐
jev (@typesafeai ) saves me from the worst part of coding with frontier models.
running multiple sessions in multiple terminals simultaneously i tend to shot a wrong prompt at wrong terminal. coding agents are pleasers they'll never tell you "wrong chat buddy".
sometimes ill spend hours reexplaining to a wrong chat cause it acts if its knows.
i built a jev guard that will stop me before harming a good chat and waisting time simply by comparing the recent chat context to the newly sent prompt.
Adin says he often runs multiple sessions in multiple terminals and sometimes sends a prompt to the wrong one. He says agents may act as if they understand, leading him to spend hours reexplaining.
Also filed under Tools & apps
- Search Telegram Channels by Topic
Sanyi built a tool using JEV that lets people search Telegram channels in his community by topic, question, or vibe. Matching channels rise up in seconds.
- Jev Omni MCP Build
eureka-pd/jev-omni-mcp is an MCP build for Jev.
- Jev Verbose Couscous Build
Beliato's `jev-verbose-couscous` is a build made with Jev.
- Build a Twilio IVR with Jev
This project uses Jev with Twilio to build an interactive voice response system.