This NEW Jev + Claude OS Just Changed Every AI Workflow
Chase AI demonstrates an agentic OS architecture utilizing Jev to route user requests across three execution tiers. The setup pairs Jev classification with Whisper, Kokoro, Obsidian vault memory, and Claude Code execution.
Original by Chase AIAgent workflowsIntermediate22 min 16 secPublished Source reviewed
Before you press play
What you’ll find in the video
Jev acts as a fast classification router to sort incoming requests into predefined execution tiers based on task complexity.
Requests categorized into the simplest tier bypass generative LLMs entirely, executing local commands or fetching cached reports directly.
Obsidian serves as an organized local file-and-folder memory layer using raw, wiki, and output directories to structure agent context.
Worth knowing
Gemini-assisted video/transcript review. Claims that Jev executes 200x faster and cheaper reflect creator-reported estimates in a specific routing setup rather than controlled third-party benchmarks.