RESEARCH · RESEARCH · #1008
ArXiv paper proposes 'Jev' router to govern enterprise AI coding-agent harnesses and cut model costs
The paper (arXiv:2609.28919v1) studies ‘‘harnesses’’—products that run AI coding agents—and presents Jev, a fast calibrated classifier-based router that labels prompts by agentic request type and routes work to reduce model spend without rebuilding session caches. Using repricing of ~10,000 real sessions from public datasets and Anthropic list prices dated 21 September 2026, the authors estimate a 14–21% reduction in model costs ($3.3M–$5.0M/year) for an emulated 10,000-seat enterprise; they also map risks across twenty harnesses and propose an internal control plane for enterprises.
KEY POINTS
- The paper (arXiv:2609.28919v1) studies ‘‘harnesses’’—products that run AI coding agents—and presents Jev, a fast calibrated classifier-based router that labels prompts by agentic request type and routes work to reduce model spend without rebuilding session caches.
- Using repricing of ~10,000 real sessions from public datasets and Anthropic list prices dated 21 September 2026, the authors estimate a 14–21% reduction in model costs ($3.3M–$5.0M/year) for an emulated 10,000-seat enterprise; they also map risks across twenty harnesses and propose an internal control plane for enterprises.
- Harnesses determine which models, prompts and subagents run, so routing and governance tools like Jev can materially cut cloud-model spending and reduce vendor-dependence for large-scale enterprise deployments.
WHY IT MATTERS
Harnesses determine which models, prompts and subagents run, so routing and governance tools like Jev can materially cut cloud-model spending and reduce vendor-dependence for large-scale enterprise deployments.