In partnership with
AI agents now read your docs almost as much as humans do.
Mintlify analyzed 790 million requests across its documentation platform. The finding: AI coding agents account for 45.3% of all traffic, nearly tied with traditional browsers at 45.8%.
Two tools are driving almost all of it:
Claude Code: 25.2% of total traffic, more requests than Chrome on Windows
Cursor: 18% of total traffic
Together they account for 95.6% of all identified AI agent traffic
The rest of the field, OpenCode, Trae, ChatGPT, and NotebookLM, is showing up but nowhere close.
One caveat: OpenAI's Codex doesn't send an identifiable user-agent header, so the real agent percentage is likely even higher.
The takeaway for anyone maintaining developer docs: your documentation now serves two audiences. Structure and machine-readability matter as much as clarity for human readers.
Hey {{first name | there}},
It’s been an interesting week, and I thought I’d briefly cover a small pain plaguing maintainers everywhere.
It’s no secret that LLMs are slowly but surely becoming the default mode of work for many developers. This creates a problem for maintainers as the annoying “update readme” commits have evolved into full-on slop PRs, and maintainers are pushing back.
Argo maintainer Nitish Kumar took to Twitter to request that people not generate slop PRs.
See the tweet
Housekeeping:
To make sure you don’t miss future emails, here are two quick GIFs showing how to move this email to your Primary tab and add this address to your contacts.
Similarly, in the past week, Kubernetes has released guidelines for AI-assisted development, citing that:
Using AI tools to help write your PR is acceptable, but as the author, you are responsible for understanding every change.
If you used AI tools in preparing your PR, you must disclose this in the description of your PR.
Listing AI tooling as a co-author, co-signing commits using an AI tool, or using the assisted-by, co-developed, or similar commit trailer is not allowed.
Even the Benevolent dictator for life of Linux chimed in saying yes to AI-assisted development and no to AI slop.
The Linux kernel has now instated guidelines for submitting PRs assisted by AI. This comes after months of pretty intense debate among maintainers, mostly because of the growing wave of AI-assisted patches landing on mailing lists.
Instead of banning it outright, they’ve landed on something more practical. Use whatever tools you want, just be honest about it, and own your code. The guidelines put it plainly:
AI agents MUST NOT add Signed-off-by tags. Only humans can legally certify the Developer Certificate of Origin (DCO). The human submitter is responsible for reviewing all AI-generated code, ensuring compliance with licensing requirements, and taking full responsibility for the contribution.
You can read more about it here.
Just before I sent this out, it seems the Flux project has followed suit and added an AI contribution policy too:
Using AI Agents to help write your PR is acceptable, but as the author, you are responsible for understanding the code and the documentation you submit. AI Agents must not add their product name to Signed-off-by or Co-authored-by tags in the commit message. Only humans can legally certify the Developer Certificate of Origin
You can read more about it here.
And it likely won't stop there. It’s still early days, but I sense much more standardization across projects in open source.
As a closing note, I would like to ask that we all do our part in making maintainers' lives easier and avoid slop.
Thanks for reading this week's issue. Divine allowed me to talk about AI this week, seeing as it’s affecting the OSS community we hold near and dear.
In exchange, he asked that I tell you to share this link with a colleague or fellow DevOps Engineer who’d find it useful.
Learn how to code faster with AI in 5 mins a day
You're spending 40 hours a week writing code that AI could do in 10.
While you're grinding through pull requests, 200k+ engineers at OpenAI, Google & Meta are using AI to ship faster.
How?
The Code newsletter teaches them exactly which AI tools to use and how to use them.
Here's what you get:
AI coding techniques used by top engineers at top companies in just 5 mins a day
Tools and workflows that cut your coding time in half
Tech insights that keep you 6 months ahead
Sign up and get access to the Ultimate Claude code guide to ship 5X faster.
And it’s a wrap!
Jubril Oyentunji
Chief Technology Officer, EverythingDevOps
