Building a Codebase Classifier with Jev
A developer shares building a codebase classifier with Jev, suggesting it may solve overengineered code from agents, and asks what to test next.
Jev routes prompts for Claude Code
A developer places Jev as a router in front of Claude Code. Each decision costs about $0.00002, routing prompts to the smallest capable model among Haiku, Sonnet, and Opus, cutting costs while managing latency.
Every prompt I sent to Claude Code ran on Opus. Renames included. So I put a router in front of it: Jev sizes each prompt and hands it to the smallest model that can do the job (haiku / sonnet / opus). ~$0.00002 per decision. The real cost is latency.
· 0 likesOpen on X
More like this
Jev Enables LLM-as-a-Judge at 20–200x Speed and 40–400x Lower Cost
Jev was used to pick which model is AGI, offering 20–200x speed and 40–400x lower cost, making LLM-as-a-judge extremely fast and nearly free.
Testing apps with TypeSafe Jev & OpenCode
Filip shares a small demo showing how fast testing apps can be with TypeSafe Jev and OpenCode.
