LLMs previously always made me feel like it was a
Said that while LLMs felt like conversation, Jev adds a key missing piece by handling decisions inside agents.
The original post, translated
LLMs previously always made me feel like it was a conversation, even when later embedded into an agent Jev, piecing together another very crucial piece of the AI puzzle
Show the original post in its source language ▾
LLM之前一直让我感觉是对话，即使后面嵌入到agent Jev 拼上另一块非常关键的AI拼图
The post above is a machine translation from zh; the untranslated text is in the fold-out.
Engagement when collected
Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.
Where this case fits
Filed under agents & workflows. In the pattern Jev is built for, the model answers a bounded question per step — and ordinary code acts on the answer, because the answer is already a value rather than a paragraph. Other posts in the same family are on the agents & workflows page.
Related Jev cases
Applied for the Typesafe AI account last night, and it was
Browser agents
found the perfect use case for @typesafeai Jev: instant
Agents
Breaking: Browser Use + Jev = Ultrafast Findings flights
AgentsBrowser agents
Jev case: in 40 seconds it broke down 724 live ads from 37
WebsitesAgents
Keep browsing: all 1173 Jev cases · more from @tspy · builders · what Jev is
Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post