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

A Voice-First Workflow for Coding, Writing, and Local AI Agents

AI summary

Oil describes an AI-assisted workflow built around real-time voice input, having a local agent interview him and organize his spoken answers, and passing links, screenshots, or Selector paths to agents. He also runs multiple agent threads in parallel and stores recurring procedures as local Skills and scripts. His desktop setup uses Shandianshuo with Alibaba Cloud Bailian’s qwen3-asr-flash-realtime model, though his speed and cost observations are personal claims.

In-depth insight

The tutorial provides a concrete, reusable pattern for supplying richer context to AI agents while reducing repetitive setup and manual transcription.

前言

哈喽大家好,我是欧呦,这篇文章将为大家分享我使用 AI 的四个高效习惯。

我现在几乎所有的事情都是由 AI 来处理的。但当这些操作变成每天的习惯之后,自己平时反而不觉得有什么特别,有时也不知道怎么把这些做法总结出来分享给大家。

所以你现在看到的这篇文章,本身就是用我日常最顺手的方式做出来的:我没有对着空白文档自己憋字,也没有让 AI 凭空替我编一篇教程,而是跟本地 AI Agent(比如 Codex、Claude Code 这类能直接读写电脑本地文件并执行操作的工具)说了一句「我想新增一篇使用 AI 的高效习惯,你可以开始采访我」,接着按住快捷键用语音聊了四轮,最后只让 AI 把我的原话整理成文。

整个过程里用到的动作,刚好串起了我每天高频使用 AI 的四个核心习惯——用实时语音快速输入上下文、让 AI 采访自己来写稿、挑最省事的方式给上下文与配环境,以及多话题并行和沉淀 Skill。下面我们就从最基础、也最能立竿见影改变沟通效率的「语音输入」开始一个个聊起。

#qwen3-asr-flash-realtime#Alibaba Cloud Bailian#Shandianshuo#Codex#Claude Code#Selector#OpenClaw

Original · 11 min readRead the original
Group chat

No comments yet. Start the conversation.