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 decisions and locks the main model on Claude Code requests
Introduces Jev (TypeSafe) routing on Claude Code requests: picks subagent model and effort, locks the main model at session start to keep the prompt cache intact, accessible via TypeSafe API or Vercel AI Gateway.
Routing the decision, not rewriting the answer. Jev (TypeSafe) on every Claude Code request: pick subagent model + effort; lock main model at session start so the prompt cache stays intact. Direct TypeSafe API or Vercel AI Gateway. CTO take: the harness is becoming a classifier
· 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.
