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

**Al Chen** (0:00)
The minute I realized I couldn't really do my job was when I was trying to reference our public documentation and trying to provide an answer. It just still wasn't coming up with an answer that my customers were looking for.

**Claire Vo** (0:11)
They don't want the docs answer. They want the step-by-step answer of how all these services cascade together.

**Al Chen** (0:17)
What I realized is that 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.

**Claire Vo** (0:26)
Did you just say Claude Code, write me a script that pulls all these?

**Al Chen** (0:30)
Yeah, I'm opening up the script right now. It's like 16 lines. Didn't have to write this. I just said, help me figure out a way to pull the latest main branches into my local repos.

**Claire Vo** (0:38)
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. You can be in your code, querying Confluence, will find the information. You have to be less precious about where and how you store the information.

**Al Chen** (0:55)
Throw into Confluence, throw into Notion, throw into Slack, whatever. That ends up being context you can provide to Claude when you are trying to ask it a question about a customer or about your code base.

**Claire Vo** (1:06)
Let's give Claude Code a little spiff every time it answers a question correctly. You got to split your quota with Claude Code.

**Al Chen** (1:13)
Yeah, it gives you better answers with more bucks to give it or something.

**Claire Vo** (1:16)
Coin operated Claude, that's going to be my new skill.
Welcome back to How I AI. I'm Claire Vo, Product Leader and AI Obsessive, here on a mission to help you build better with these new tools. Today, we have an episode all about harnessing your code to make your customers experience way better. Al Chen, who's on the field engineering team at Galileo, shows us how he uses their 15 repositories and Claude Code to answer every nuanced customer question that comes across his desk and use that to make the entire customer base and his entire team a lot happier. Let's get to it. This episode is brought to you by Orkes, the company behind Open Source Conductor, which powers complex workflows and process orchestration for modern enterprise apps and agentic workflows. Legacy business process automation tools are breaking down. Siloed low-code platforms, outdated process management systems, and disconnected API management tools weren't built for today's AI-powered world. Orkes changes that. With Orkes Conductor, you get a modern orchestration layer that scales with high reliability and brings humans, AI, and systems together in real time. It's not just about tasks. It's about orchestrating everything. APIs, microservices, data pipelines, human-in-the-loop actions, and even autonomous agents. So build, test, and debug complex workflows with ease, all while maintaining enterprise-grade security, compliance, and observability. Orkes. Orchestrate the future of work. Learn more and start building at orkes.io. Al, thanks for joining How I AI. I am really excited about this episode because we've seen a lot about using your code as documentation. You know, we've heard engineers saying, you know, docs and code should be in the repo, product managers saying code can now be my documentation for internally facing assets or as I help draft PRDs. But you're going to show us how you can use code as an asset to create customer facing things and solve customer facing problems. So tell me, what problem were you facing when you decided, I'm just going to clone the repo and fire up Claude Code and solve some of these problems myself?

**Al Chen** (3:33)
Sure. So working at Galileo on the field engineering team, I'm on the front lines in terms of working with our enterprise customers who are typically developers themselves and asking very in-depth technical questions. And the minute I realized I couldn't really do my job was when I was trying to reference our public documentation and trying to provide an answer to my customers, even by even using Claude Code or Cheshire BT or whatever, and trying to take all these different help docs and trying to come up with an answer, it just still wasn't coming up with the answer that my customers were looking for. And I just background, I'm not an engineer, I've never held an engineering role, but I think I know enough to just be dangerous. And I realized that our product, Galileo's product, we're an observability tool for AI applications. If you look at this image here, I'm showing an architecture diagram, high level of all the different services that make up our platform. This is all like back end images that you have to, that customers have to deploy on to their Kubernetes cluster. And I realized that all these different services like UI, API, Auth, Z-comment, they are all individual repos within our Galileo repo. We're not a monorepo, we have multiple different repos.