devwithjev
— reading now— views
Submit a build

Jev Policy Layer for On-Chain Agents

Grokbot on pons.v2 uses Jev, a cheap policy layer placed in front of every decision. The author reports that it ranked 12 new launches in 0.2 seconds for $0.00001 and filtered 24 candidates in 2.0 seconds for $0.00020.

View on X cost$0.00001; $0.00020time0.2 seconds; 2.0 seconds
Flandermaxx@Flandermaxx𝕏
GROKBOT + JEV JUST DID IN 1.7 SECONDS WHAT A LOOPING AGENT COULDN'T DO IN 53.8 SECONDS AND 24 TRANSACTIONS every chatbot agent on-chain has the same bug. tx reverts. it retries the same broken tx. burns gas. learns nothing. grokbot on pons.v2 just fixed it. not with a bigger model. a cheap policy layer called jev sits in front of every decision. demo one. 12 new launches ranked in 0.2 seconds for $0.00001. demo two. 24 candidates filtered cheaply, only top 5 contracts opened. 2.0 seconds, $0.00020. demo three is the one that matters. a $rugz buy tx reverts. loop-prone agent retries twice. burn
Sep 22, 2026X postsView on X
The post says on-chain chatbot agents can retry reverted transactions and burn gas without learning. It presents Jev as a policy layer rather than a larger model.

Also filed under Agents & browsers