Four practical ways to use Jev for agent harnesses: judging, routing, subagent orchestration
omarsar0 · x · 2026-09-18
A practical thread on using Jev for agent engineering: 1) LLM-as-a-Judge evaluation, 2) routing in agent harnesses, 3) scaling orchestration via smarter subagent creation with SOTA classification, and 4) dynamic harness generation with structured outputs. The author reports huge cost/efficiency ROI on the first three and calls the model an important primitive for tool calling and context engineering.
More from coding & agent
- Distributed-Slides: an MCP server that compiles agent-written talks into offline presentations — arthurcolle · 2026-09-18
- Vercel skills CLI adds Notion-hosted agent skills, no Git repo required — ivanhzhao · 2026-09-18
- Vercel teams have long written GTM and on-call skills in Notion — ivanhzhao · 2026-09-18
- eve adds automatic model selection: agents pick models by task difficulty before inference — cramforce · 2026-09-18
- DHH on Lex Fridman: Nov 2024 split coding into two universes, agentic coding is transformative — zakkohane · 2026-09-18
- Vercel CLI now deploys static artifacts in under one second, build step skipped — cramforce · 2026-09-18