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.What you’ll learn:How to use Claude Code to query multiple repositories simultaneously for customer supportWhy code is often a better source of truth than documentationHow to combine repository context with Confluence and Slack using MCPsThe “customer quirks” system that creates hyper-personalized deployment guidesHow to build virtuous loops that turn single customer questions into scalable knowledgeWhy information organization matters less in the AI eraA simple 16-line script (written by Claude Code) that pulls the latest main branch across all your repositories to keep your context currentHow to reduce engineering interruptions to near-zero by empowering customer-facing teams to query the codebase directly—Brought to you by:Orkes—The enterprise platform for reliable applications and agentic workflowsTines—Start building intelligent workflows today—In this episode, we cover:

Introduction to Al Chen

The problem: documentation wasn’t enough

Pulling 15 repos into VS Code

How Claude Code queries the entire codebase

Why current code beats documentation

The pull script that keeps everything updated

Opening projects at the multi-repo level

Live demo: answering deployment questions

The customer quirks system

Living in chaos: why organization matters less now

Competing on customer experience, not just product

Should customers be able to query the code directly?

Where humans still add value

Using AI for reactive Slack support

The “and then” workflow discovery

Scaling processes across the team