Claire Vo · 2 min read · Gen AI Tools
I gave Claude Code our entire codebase. Our customers noticed. | Al Chen (Galileo)
Read the original on lennysnewsletter.com →
Al Chen shows how he built a Claude Code-powered system to query Galileo's 15 repositories, blend that context with Confluence docs and customer quirks, and deliver hyper-personalized deployment guides. The episode explains why code is often a better truth source than documentation, how to integrate repository context with Slack via MCPs, and how to scale knowledge while reducing engineering interruptions.
Key Takeaways
- Claude Code can query multiple repositories at once to surface relevant context for customer support.
- Codebase data can be a more reliable source of truth than documentation for deployments.
- You can blend repository context with Confluence and Slack using MCPs to generate personalized guides.
- A 'customer quirks' system helps tailor deployment guidance and scales across the team.
- Small automation, like a 16-line script to pull the latest main branch across repos, keeps context current and reduces interruptions.
Excerpt
Al Chen is a field engineer at Galileo, an observability platform for AI applications, where he works on the front lines with enterprise customers asking highly technical questions. Despite never having held an engineering role, Al has built a system using Claude Code to query Galileo’s 15 separate repositories, combine that with Confluence documentation and customer-specific quirks, and deliver hyper-personalized answers that would otherwise require constant engineering support. Listen or watch on YouTube , Spotify , or Apple Podcasts What you’ll learn: How to use Claude Code to query multiple repositories simultaneously for customer support Why code is often a…