xpost·Tools and apps
How Jev makes agents faster and cheaper
jev will make agents 10x faster and cheaper, here's how: 1/ model routing: pick the right model for each task, without training a custom router https://x.com/mdlahfir/status/2100314182201802811?s=20 2/ computer use: faster, cheaper and more reliable for action-heavy tasks https://x.com/gregpr07/status/2100411066966749359 3/ auto review: ask jev whether an action is safe, instead of using a slow and expensive LLM https://x.com/fazxes/status/2100300097695232164?s=20 4/ less obvious: subagent orchestration long-running agents (cursor projects, grokbot, energy) parallelize work with subagents. but every user message, email, or subagent reply can wake the expensive orchestrator. example: it costs $1 to wake up gpt 6 astra w 100k input tokens jev can decide what each event needs: - route directly to a subagent - queue for later - wake the orchestrator
david fant
@da_fant
jev will make agents 10x faster and cheaper, here's how: 1/ model routing: pick the right model for each task, without training a custom router https://x.com/mdlahfir/status/2100314182201802811?s=20 2/ computer use: faster, cheaper and more reliable for action-heavy tasks https://x.com/gregpr07/status/2100411066966749359 3/ auto review: ask jev whether an action is safe, instead of using a slow and expensive LLM https://x.com/fazxes/status/2100300097695232164?s=20 4/ less obvious: subagent orchestration long-running agents (cursor projects, grokbot, energy) parallelize work with subagents. but every user message, email, or subagent reply can wake the expensive orchestrator. example: it costs $1 to wake up gpt 6 astra w 100k input tokens jev can decide what each event needs: - route directly to a subagent - queue for later - wake the orchestrator
Evaluate input state and return typed decision for How Jev makes agents faster and cheaper.
Jev sits between the incoming context and the next system action. Rather than generating lengthy, slow natural language that requires brittle regex parsing, Jev returns non-autoregressive, calibrated probabilities that downstream code can immediately execute.
01actionPrimary action
02confidenceConfidence score
03fallbackFallback route