# How to review code

What I learned from Anthropic's code review process, and why visual artifacts could become bridges to understanding complex systems.

Canonical URL: https://jdjuan.io/code-review
Author: Juan Herrera
Published: 2026-10-27
Category: Entrepreneurship

I recently read [Anthropic's Claude Code guide to merging code](https://claude.dev/blog/solving-code-review-at-anthropic/).

My biggest learnings are these:

1. Involve the **human** as little as possible, **automate** as much as possible.
2. Sounds obvious, but some people still advocate for involving the human **throughout**, and others for not involving the human **at all**, so their approach is still not obvious.
3. To what degree humans are involved depends on the **blast radius**. How much **damage** a feature/PR could do changes the **approval policy** (0 humans for simple things, 1 for the average, 2 or 3 for very delicate stuff).
4. Second, I learned they don't expect engineers to understand the **whole** codebase, only the **part** they need to change. This also sounds obvious, but there are companies where it's expected to understand the whole codebase or have **owners** of certain parts of the application. They didn't say they don't have owners, but their approach seems to focus more on **pragmatism** than **ownership**.
5. So what some engineers do is create **artifacts** of the part of the code they need to update, say a **graphic** or a **video**, and then use that to have a better understanding of the **components** affected by the expected change, instead of expecting them to know that from reading **code**.

I think their approach is sound and I'm curious, especially about point 5. I think we'll see that more and more, people creating **artifacts** as **bridges** to better understand **complex** things. I like it!

That's it!

## AI Coding Working Session

Bring a real project or bottleneck. We'll improve your workflow, work through it together, and build a repeatable process you can keep using after the call.

- Prompt and collaborate with AI more effectively
- Work through a real project or bottleneck
- Build a 10× AI-augmented engineering workflow
- Private 60-minute video session

Price: $99 (regular price: $165)
Duration: 60 minutes, private video session
Booking: https://www.paypal.com/ncp/payment/PLB-N8QDDSUE9SAA
After payment, you will be redirected to the booking page.
Session details: https://jdjuan.io/ai-coding-session
