I gave Claude Code our entire codebase. Our customers noticed. | Al Chen (Galileo) · How I AI summary

Key takeaways

Code is often a more reliable source of truth than traditional documentation.
Utilizing AI tools like Claude Code can significantly enhance the speed and quality of customer support.
Creating a system for recording customer quirks leads to tailored solutions and improved customer relationships.
Human interaction remains crucial in engaging customers effectively, even when using AI.
Establishing a responsive knowledge base from customer interactions boosts team performance and customer satisfaction.

Summary

Introduction to Al Chen and the Problem with Documentation

Al Chen, a field engineer at Galileo, emphasizes the challenge of providing satisfactory answers to complex customer inquiries due to limitations in existing public documentation. He realizes that customers prefer in-depth, step-by-step answers over generic doc responses.

Harnessing Claude Code for Customer Support

Al shares how he utilizes Claude Code to query Galileo’s 15 separate repositories. By integrating this with Confluence documentation, he is able to deliver hyper-personalized responses, alleviating the need for constant engineering support.

Combining Repository Context with Customer Needs

The episode discusses a system of recording customer-specific quirks that help in creating tailored deployment guides. This process allows for a deeper understanding of a customer's requirements and enhances client trust.

The Role of AI in Enhancing Customer Experience

The conversation shifts to how AI can transform customer interactions. Al argues that AI tools help in scaling responses and creating a more enjoyable customer experience, not just focusing on product efficiency.

Building Knowledge from Customer Interactions

Al introduces a process where he turns customer inquiries from Slack interactions into help articles that can benefit future customers. This creates a living knowledge base that is more current than traditional documentation.

The Importance of Human Value in AI-Driven Support

Despite the efficiency of AI, Al highlights that human touch is irreplaceable in customer relationships. The role of a human remains vital in refining AI's output and providing personalized engagement.

Scaling Best Practices Across Teams

Al advocates for sharing successful strategies across teams, encouraging others in the field engineering team to adopt his methods for improved productivity. This approach emphasizes continual learning and adaptation.

Show notes

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 support
Why code is often a better source of truth than documentation
How to combine repository context with Confluence and Slack using MCPs
The “customer quirks” system that creates hyper-personalized deployment guides
How to build virtuous loops that turn single customer questions into scalable knowledge
Why information organization matters less in the AI era
A simple 16-line script (written by Claude Code) that pulls the latest main branch across all your repositories to keep your context current
How 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 workflows

Tines—Start building intelligent workflows today

—

In this episode, we cover:

(00:00) Introduction to Al Chen

(02:50) The problem: documentation wasn’t enough

(04:23) Pulling 15 repos into VS Code

(06:03) How Claude Code queries the entire codebase

(08:00) Why current code beats documentation

(08:31) The pull script that keeps everything updated