Salesforce研究员复盘AI工作流：从手写转向调度多编码智能体
Start here
2026年11月4日，Salesforce AI Research 研究员发布年度 AI 使用复盘。该研究员透露，其日常工作已从手写代码全面转向同时调度 5 到 6 个 Claude Code 等编码智能体，机器完成了其中 90% 以上的代码编写。复盘指出，智能体能大幅加速原型开发，但目前仍缺乏架构设计能力，且同时调度多个智能体会带来管理疲劳；此外，大语言模型在协助教学和搜索方面表现出色，但在复杂原创研究与独立写作上仍无法替代人类。
AI-generated from reports · Updated 16 hours ago
Report timeline
Follow the reports to see different sides of the story.
- Hacker News · AISelectedSalesforce AI Researcher's Annual Review: Shifting from Hand-Coding to Orchestrating Multiple Coding Agents
A researcher at Salesforce AI Research published an annual review of their AI usage, noting that their daily work has fully shifted from manual coding to orchestrating five to six coding agents—such as Claude Code—simultaneously, with machines now writing over 90% of the code. The author highlighted that while agents dramatically speed up prototyping, they still lack architectural design capabilities and introduce managerial fatigue. Furthermore, while LLMs excel at tutoring and search, they remain unable to replace humans in complex original research and independent writing.
Story heat trend
Current heat 6·Comparable peak 10（Nov 4 03:00）·Comparable change, last 24 hours–
Trends compare only the same parties observed continuously, so the scope can be narrower than current heat counts. Move the pointer or tap the chart to see hourly heat; use the left and right arrow keys on a keyboard.