Salesforce adopts Claude Code to improve efficiency
The story so far
Salesforce has extended Claude Code to thousands of engineers, doubling effective output and reducing the number of bugs per line of code. The company's engineering leadership, in collaboration with Stanford researchers, has built an 'effective output' scoring system to measure AI coding ROI, and uses an agent maturity curve to guide engineers from simple prompts to fully autonomous agents. They have also used Claude Code to transform a decades-old codebase into a headless architecture in weeks instead of a year; created a shared agent skills marketplace; developed a fault agent that automatically finds the right team; and Claude Opus tracked down a bug within 24 hours after humans failed to do so.
AI-written from the reports · Updated 12 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- Claude · YouTubeHow Salesforce uses Claude Code
Salesforce expanded Claude Code to thousands of engineers, doubling effective output and reducing the number of bugs per line of code. The 'effective output' scoring system, co-built by the company's engineering leadership and Stanford researchers, measures AI coding ROI, and the intelligent agent maturity curve guides engineers from simple prompts to fully autonomous agents.