Skip to content
How I AIHow I AI

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

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:* 1. How to use Claude Code to query multiple repositories simultaneously for customer support 2. Why code is often a better source of truth than documentation 3. How to combine repository context with Confluence and Slack using MCPs 4. The “customer quirks” system that creates hyper-personalized deployment guides 5. How to build virtuous loops that turn single customer questions into scalable knowledge 6. Why information organization matters less in the AI era 7. A simple 16-line script (written by Claude Code) that pulls the latest main branch across all your repositories to keep your context current 8. 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: https://www.orkes.io/ Tines—Start building intelligent workflows today: https://tines.com/howiai *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 (09:54) Opening projects at the multi-repo level (11:40) Live demo: answering deployment questions (13:25) The customer quirks system (15:00) Living in chaos: why organization matters less now (17:03) Competing on customer experience, not just product (18:20) Should customers be able to query the code directly? (20:05) Where humans still add value (25:46) Using AI for reactive Slack support (29:16) The “and then” workflow discovery (32:07) Scaling processes across the team (34:07) Lightning round and final thoughts *Detailed workflow walkthroughs from this episode:* • How Al Chen Uses Claude Code and 15 Repos to Answer Any Customer Question: https://www.chatprd.ai/how-i-ai/claude-code-and-repos-to-answer-any-customer-question • Automatically Create a Knowledge Base from Slack Support Threads: https://www.chatprd.ai/how-i-ai/workflows/automatically-create-a-knowledge-base-from-slack-support-threads • How to Use AI to Answer Customer Questions from Your Entire Codebase: https://www.chatprd.ai/how-i-ai/workflows/how-to-use-ai-to-answer-customer-questions-from-your-entire-codebase *Tools referenced:* • Claude Code: https://claude.ai/code • VS Code: https://code.visualstudio.com/ • Pylon: https://usepylon.com/ • Confluence: https://www.atlassian.com/software/confluence *Other references:* • Slack: https://slack.com/ • Kubernetes: https://kubernetes.io/ • Stack Overflow: https://stackoverflow.com/ • Intercom: https://www.intercom.com/ *Where to find Al Chen:* LinkedIn: https://www.linkedin.com/in/thealchen/ Company: https://www.rungalileo.io *Where to find Claire Vo:* ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo _Production and marketing by https://penname.co/._ _For inquiries about sponsoring the podcast, email jordan@penname.co._

Al ChenguestClaire Vohost
Apr 6, 202645mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

Using Claude Code across repos to deliver precise customer support

  1. Public documentation and generic AI answers often fail for enterprise customers who need precise, step-by-step explanations tied to how services actually interact in production.
  2. By cloning ~15 service repos into one VS Code workspace, Al uses Claude Code to query the living source of truth (main branches) and generate accurate, code-referenced answers faster than pinging engineers.
  3. A lightweight automation script (written by Claude) keeps every repo updated, making it feasible to rely on code even as multiple releases ship daily.
  4. Al augments code context with Confluence and Slack via MCP integrations, including a “customer quirks” page that tailors deployment guidance to each customer’s unique security and infrastructure constraints.
  5. Reactive Slack support is turned into a virtuous loop by summarizing threads into reusable knowledge-base articles (via Pylon), improving future support, internal enablement, and potentially product roadmap inputs.

IDEAS WORTH REMEMBERING

5 ideas

Enterprise customers don’t want “the docs answer”; they want the system walkthrough.

In complex architectures, customers ask how services cascade together (deployment, caching, auth, callbacks), so answers must reflect real interactions—not just product narratives.

Open your IDE at the right “scope” to make AI useful across services.

Loading a multi-repo workspace lets Claude traverse dependencies across repos; you can also narrow or widen the directory level depending on the question to manage context bloat.

Treat main-branch code as the most current documentation—then keep it current automatically.

Because code changes daily, Al uses a simple Claude-generated script to git-pull main across all repos, avoiding tedious manual pulls and reducing stale answers.

Blend code with internal knowledge sources to answer what code alone can’t.

Using Confluence and Slack MCPs, Claude can incorporate deployment runbooks, prior Slack resolutions, and customer-specific constraints to produce responses that match real environments.

Maintain a “customer quirks” page to unlock truly tailored guidance.

Capturing items like secret managers, namespace rules, air-gapped constraints, CRD limitations, and encryption requirements allows Claude to produce deployment steps that feel bespoke and build trust.

WORDS WORTH SAVING

5 quotes

I can actually pull all of these repos into my VS Code, and I can now use Claude Code to ask our entire codebase questions.

— Al Chen

They don't want the docs answer. They want the step-by-step answer of how all these services cascade together.

— Claire Vo

The reality is we can now all live in a little bit more chaos because the AI navigates all that information for us across systems.

— Claire Vo

I treat it like my entry level analyst… I’m very relentless when it comes to getting the right answer from Claude or from AI.

— Al Chen

Throw it into Confluence, throw it into Notion, throw it into Slack, wherever.

— Al Chen

Multi-repo VS Code workspace setupClaude Code for cross-repo codebase Q&ACode as source of truth vs. docs driftAutomated ‘pull all’ script for repo updatesMCP integrations (Confluence, Slack) for context retrievalCustomer-specific ‘quirks’ micro-documentationSlack support → knowledge-base article pipeline (Pylon)Human value: editing, brevity, trust, escalation to engineersPrompting tactics: ‘think harder’, cite sources, verify in codeScaling the workflow across a customer-facing team

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome