Jev takes over the tool-call loop: 12/12 passed, 36% lower cost
Delegating tool selection and next-step decisions to Jev while the main LLM only frames the task and summarizes results passed all 12 tool-calling benchmark scenarios, with 89% fewer outer-LLM tokens.
I used Jev to delegate the entire tool call, execution, and next-step loop away from the main LLM. The setup was simple: On one hand we have the native vanilla Harness . The LLM sees the tool catalog, picked a tool, got the result, reasoned again, picked the next tool, and repeated. The other harness gave the LLM exactly one tool: `delegate_to_jev`. This acts as the starting state. Jev then handled the closed-set routing: which real tool to call next, what typed arguments to use, when to continue, and when to stop. The LLM only framed the task and summarized the final evidence. We ran this on a deterministic tool calling benchmark with 12 tasks: multi-step workflows, safety checks, prerequisite chains, and state-changing actions. Results: Baseline harness: - 10 / 12 scenarios passed - $0.01966 cohort cost - 49,364 outer-LLM tokens LLM + Jev delegation: - 12 / 12 scenarios passed - $0.01249 cohort cost - 5,363 outer-LLM tokens That is ~36.5% lower cost and ~89.1% fewer outer-LLM tokens. That is crazyyyyy!! This means, we can use the LLM for reasoning and synthesis. And use Jev for fast, typed, repeated decisions inside the tool loop.