Replit 演示如何用 Slack 反馈直接驱动智能体改进项目
Replit 演示了个挺顺手的玩法:让智能体去读 Slack 里的产品反馈,然后直接改项目代码,一个提示词就搞定。
Replit 在 X 上演示了一个工作流:用一句提示词让智能体读取 #product_feedback 频道里上周的反馈,自动改进 customer portal 的 onboarding。智能体会先定位项目,再拉取相关反馈并直接开始修改代码。如果反馈涉及多个项目,可以在同一个会话里继续操作。
That Slack thread about onboarding can become your next project improvement. Just ask Replit: “Use last week’s feedback from #product_feedback to improve onboarding in my customer portal.” Agent finds the project, pulls in the relevant feedback, and starts the edit. And if the feedback applies to multiple projects, keep going in the same chat. Your browser does not support the video tag. 🔗 View on Twitter 💬 3 🔄 2 ❤️ 8 👀 1684 📊 4 ⚡