在Salesforce工程团队中引领智能体化转型

100%

100%

Key Takeaways

核心要点

  • Autonomous tools are now writing code, reviewing pull requests (“PRs”), and driving deployments across the software development lifecycle.
  • 自主工具现在正在编写代码、审查拉取请求(“PR”),并推动整个软件开发生命周期中的部署工作。
  • Standardizing on Claude Code and removing token limits improved output and quality simultaneously — more shipped, fewer incidents, and fewer bugs.
  • 统一使用 Claude Code 并取消 token 限制,同时提升了产出和质量——交付更多,事故更少,bug 也更少。
  • An agentic workflow allowed a product team to complete a 231-person-day migration in 13 days — 18 times faster.
  • 一个 agentic 工作流使产品团队能够在 13 天内完成原本需要 231 人天的迁移工作——速度提升了 18 倍。
  • We’re still in the early stages of redefining how the roles across engineering, product, and design will change.
  • 我们仍处于重新定义工程、产品和设计领域角色将如何变化的早期阶段。

A few months ago, I wrote about the hard work of getting thousands of engineers to actually use AI — not just adopt it in name, but embed it meaningfully into how they work. We built the governance scaffolding, the measurement infrastructure, and the workflows to make it real. We crossed 90% adoption. That felt like a milestone.

几个月前,我写过关于让数千名工程师真正使用 AI 的艰辛工作——不仅仅是名义上采用,而是将其有意义地融入他们的工作方式中。我们建立了治理脚手架、测量基础设施和工作流,使其成为现实。我们的采用率超过了 90%。这感觉像一个里程碑。

It turns out, that was just the beginning.

事实证明,那仅仅是个开始。

Today, Salesforce Engineering is running on AI. We’ve moved from a world where AI was a helpful copilot to one where agentic tools are driving the software development lifecycle (SDLC) itself — writing code, reviewing pull requests (PRs), generating tests, updating documentation, managing deployments, and increasingly coordinating work that used to require significant human handoff. The change has been sharper and faster than anything I’ve seen in my career.

如今,Salesforce Engineering 正在 AI 上运行。我们已经从 AI 作为得力 copilot 的世界,迈入了 agentic 工具驱动软件开发生命周期 (SDLC) 本身的世界——编写代码、审查 pull requests (PRs)、生成测试、更新文档、管理部署,并越来越多地协调过去需要大量人工交接的工作。这种变化比我职业生涯中见过的任何变化都更加剧烈和迅速。

Here’s what that shift actually looks like, what drove it, and what it’s teaching us.

以下是这种转变的实际表现、驱动因素以及它带给我们的启示。

Ramping with Claude Code

借助 Claude Co...

开通本站会员,查看完整译文。

首页 - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-07-21 06:57
浙ICP备14020137号-1 $访客地图$