Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

What Changes When AI Agents Become Long-Running Assistants

AI summary

掘金 · 人工智能 argues that agent engineering differs from conventional backend development because a model may choose its next action from newly observed material, adding a semantically uncertain decision stage. Using an Open ETF Agent v0.19.0 teaching case, the article compares tool contracts, permissions, state, recovery, testing, and delivery, then draws on a private research application to examine asynchronous delivery, human replies, memory consumption, and daily replay. It explicitly says these examples do not demonstrate real investment-research or automated-trading capability.

In-depth insight

The analysis provides practical controls for building persistent agents, including bounded actions, explainable interruptions, retrievable deliverables, verifiable state, and permissions that remain effective across time and user changes.

如果已经做过后台应用,第一次接触 Agent 往往会觉得熟悉:接收请求、查资料、调用接口、保存结果,再返回给用户。把模型放在中间,似乎就是一个带自然语言入口的业务系统。

真正的变化出现在运行过程中:下一步做什么,不再全部由开发者提前写好,而可能由模型根据刚刚看到的材料临时决定。 这个决定还会受到上下文、工具描述、历史摘要和用户偏好的影响。

因此,Agent 工程是在成熟的后台工程基础上,接纳一个具有语义不确定性的决策环节。开发者既要让它能探索,也要让每次行动有范围、每次中断能解释、每份成果能取得。到了个人助手阶段,还要让这些约束跨越时间与用户的变化。

前半篇沿一个教学任务比较控制方式:读取两份基金披露并生成报告,再看工具、状态与成熟框架怎样组织工作。后半篇转向我们私有研究应用中已经做过的异步交付、人工回复、记忆消费和每日复读,用实际成功与反例解释视野为什么扩大。教学案例、脚本模型验收和小规模真实模型观察分别标明,不代表真实投资研究或自动交易能力。

#Open ETF Agent#Claude Agent SDK#Codex#OpenAI Agents SDK#LangGraph#Temporal

Original · 32 min readRead the original
Group chat

No comments yet. Start the conversation.