LogoThread Easy
  • 探索
  • 線程創作
LogoThread Easy

Twitter 線程的一站式夥伴

© 2025 Thread Easy All Rights Reserved.

探索

Newest first — browse tweet threads

Keep on to blur preview images; turn off to show them clearly

Do you send your SaaS customer an email with what their „best next step“ is, some time after signing up?

If yes, how long do you wait to send that email? Is it custom to their needs? Or templated?

If no, why not?

Do you send your SaaS customer an email with what their „best next step“ is, some time after signing up? If yes, how long do you wait to send that email? Is it custom to their needs? Or templated? If no, why not?

Building https://t.co/od97B0HVrk and https://t.co/666FnyVVE0 in Public. Raising all the boats with kindness. 🎙️ https://t.co/6w69DZmi8H · ✍️ https://t.co/lpnor5rsTW

avatar for Arvid Kahl
Arvid Kahl
Wed Oct 29 01:00:26
splitting one of these with a friend like divorced parents. training it to gaslight and respond to orders in exotic languages

splitting one of these with a friend like divorced parents. training it to gaslight and respond to orders in exotic languages

investing @a16z // curating https://t.co/ssslqn6eo7

avatar for Ryan McEntush
Ryan McEntush
Wed Oct 29 00:49:37
RT @yanatweets: My boss and big Satya 👀

RT @yanatweets: My boss and big Satya 👀

Parable Founder & GP @parable_vc | x-a16z: @whatnot @livekindred @prismsofreality | Biggest fan @spenserskates | “It’s always Day 1”

avatar for Anne Lee Skates
Anne Lee Skates
Wed Oct 29 00:44:12
RT @spenserskates: "The way you produce your artifact, your software, is changing. The product development process is completely getting ri…

RT @spenserskates: "The way you produce your artifact, your software, is changing. The product development process is completely getting ri…

Parable Founder & GP @parable_vc | x-a16z: @whatnot @livekindred @prismsofreality | Biggest fan @spenserskates | “It’s always Day 1”

avatar for Anne Lee Skates
Anne Lee Skates
Wed Oct 29 00:36:29
You mad geniuses @daniel_eckler @WizLikeWizard

You mad geniuses @daniel_eckler @WizLikeWizard

GM @speedrun. Investor at @a16z. Apply here: https://t.co/bbxTvgMK6w You've probably played a game I worked on. Husband, girldad x2, cook, point guard

avatar for Josh Lu
Josh Lu
Wed Oct 29 00:30:45
最近在选择自己开发的 AI 工具栈,有一个感觉:Claude Code/Codex 等 AI Agent 的整体规划能力、架构能力都很不错,不过用来做前端开发,总感觉有些地方不太用得上力,比如设计团队的 Figma 设计稿还原,比如基于前端组件库和 CSS 样式来新增和修改产品设计。可能把 Spec 和 Plan、Skills、Agents md 等编写到位,多次迭代后,也能达到满意的结果。

不过感觉有些大炮打蚊子了,token 成本也是没必要的高!

最近几天试用 Kombai 这个前端专精智能体,在前端开发方面值得试试,它通过领域优化(如内置 30+ 库 RAG 和任务特定规划),自研的 Figma 设计稿引擎等,直接生成高保真输出——少编译错、代码审查通过率高,还附带浏览器预览。用户能控制上下文,确保适配你的栈。

基准测试(200+ 任务)显示,它在 UI 实现和错误率上超通用智能体 2 倍左右,特别适合中大型组件。试了几个项目,确实高效,但也需熟悉其规划模式。

https://t.co/dSOvfD53YF

最近在选择自己开发的 AI 工具栈,有一个感觉:Claude Code/Codex 等 AI Agent 的整体规划能力、架构能力都很不错,不过用来做前端开发,总感觉有些地方不太用得上力,比如设计团队的 Figma 设计稿还原,比如基于前端组件库和 CSS 样式来新增和修改产品设计。可能把 Spec 和 Plan、Skills、Agents md 等编写到位,多次迭代后,也能达到满意的结果。 不过感觉有些大炮打蚊子了,token 成本也是没必要的高! 最近几天试用 Kombai 这个前端专精智能体,在前端开发方面值得试试,它通过领域优化(如内置 30+ 库 RAG 和任务特定规划),自研的 Figma 设计稿引擎等,直接生成高保真输出——少编译错、代码审查通过率高,还附带浏览器预览。用户能控制上下文,确保适配你的栈。 基准测试(200+ 任务)显示,它在 UI 实现和错误率上超通用智能体 2 倍左右,特别适合中大型组件。试了几个项目,确实高效,但也需熟悉其规划模式。 https://t.co/dSOvfD53YF

专注 - Context Engineering, AI(Coding)Agents. 分享 - AI papers, apps and OSS. ex Microsoft MVP 合作 - 私信/邮箱:shaomeng@outlook.com 📢 公众号/小红书: AI 启蒙小伙伴 🔗 信息卡提示词 🔽

avatar for meng shao
meng shao
Wed Oct 29 00:27:26
  • Previous
  • 1
  • More pages
  • 2051
  • 2052
  • 2053
  • More pages
  • 2118
  • Next