Claude Code + 15 repos: how a non-engineer answers every customer question | Al Chen

2026-04-06 · Source: How I AI · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Cloud Computing & IT Infrastructure · Depth: Intermediate, extended

Summary

Al Chen, a field engineer at Galileo, demonstrates how he uses Claude Code and his company's 15 code repositories to provide highly detailed, customized answers to complex customer technical questions. Facing limitations with public documentation for Galileo's AI observability platform, Chen pulls all service repositories into VS Code. This setup allows him to query the entire codebase, including API and authentication repos, for in-depth feature explanations and deployment specifics. He also integrates customer-specific "quirks" from a Confluence page into his queries, enabling Claude Code to generate tailored deployment plans for air-gapped enterprise environments. This approach significantly reduces reliance on internal engineering teams for support, streamlines customer interactions, and ensures answers are current with the evolving codebase.

Key takeaway

For field engineers or customer-facing technical roles struggling with generic documentation, integrate your company's code repositories with AI coding assistants like Claude Code. This allows you to generate precise, real-time, and customer-specific technical answers, reducing reliance on engineering teams and significantly improving customer trust and experience. Consider upskilling your team in basic Git and IDE usage to maximize this approach's effectiveness.

Key insights

Integrating code repositories with AI tools provides highly contextualized, current answers for complex customer support.

Principles

• Codebase is the ultimate source of truth.
• AI can navigate information across fragmented systems.
• Tailored answers build customer trust.

Method

Pull all relevant code repositories into a multi-repo VS Code workspace. Use AI (e.g., Claude Code) to query the entire codebase, combining it with internal documentation and customer-specific notes for highly customized responses.

In practice

• Use a script to pull latest main branches across all repos daily.
• Open multi-repo projects in your IDE for cross-repo querying.
• Maintain a "customer quirks" page for AI context.

Topics

• Claude Code
• Codebase Querying
• Customer Support Automation
• Field Engineering
• Knowledge Management

Best for: Software Engineer, AI Engineer, Director of AI/ML

Related on AIssential

• 🎙️ This week on How I AI: I gave Claude Code our entire codebase. Our customers noticed. — Integrating AI with a full codebase and internal knowledge bases provides real-time, tailored customer support.
• I gave Claude Code our entire codebase. Our customers noticed. | Al Chen (Galileo) — AI can transform customer support by querying entire codebases and internal knowledge for precise, real-time answers.
• Claude Code Isn’t a Coding Tool. It’s Your Team’s New Workflow Engine. — AI coding tools excel as workflow engines, not just code generators.
• Top 5 GitHub Repositories to get Free Claude Code Skills (1000+ Skills) — Leveraging shared Claude Code skills from GitHub significantly enhances AI assistant capabilities and workflow automation.
• How to use Claude Code to build a board room of world class Product Mentors — Claude Code enables non-engineers to build AI mentor systems for strategic product decision-making.
• Onboarding Claude Code like a new developer: Lessons from 17 years of development — Treating AI coding tools like new human developers, with structured onboarding and context, significantly enhances their effectiveness on complex codebases.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by How I AI.