Blog: AI trends
Self-updating external docs is an infinite market
Product surface areas are growing exponentially, agents are becoming the main users of docs, and external agents can't read your primary sources. Together, these make self-updating external docs an infinite market.
Rise of the Knowledge Engineer
Agents are one of the largest audiences for company knowledge, accounting for 66% of measured web traffic across documentation powered by Mintlify. The emerging role responsible for keeping that knowledge accurate and retrievable is the knowledge engineer.
Highlights from the 2026 State of Knowledge Report
AI agents overtook humans as the primary readers across Mintlify-powered sites. In August alone, agents made 257 million web requests compared to 131 million human page loads, which means agent traffic now outnumbers human traffic by nearly 2:1.
The state of docs traffic: a 2026 midyear report
Agents now account for 66% of measured web-traffic across docs powered by Mintlify, with July logging over 213 million agent web requests and 105 million human page loads as the month comes to a close.
Docs as an abstraction layer for coding agents
A large engineering org ran controlled experiments to measure how structured Mintlify docs affect agent performance on massive codebases. The results: 64% more precise, 39% more discoverable, half the tokens, 1.5x faster.
Markdown is the easy part
Mintlify might look like a Markdown hosting service from the outside. But the build versus buy question for content infrastructure goes much deeper than rendering Markdown.
Tokenmaxxing: One AI budget, four jobs
Every company is now paying for AI tokens, but few can draw a clean line from that spend to business outcomes. Here's a framework that maps AI Credits to the P&L categories finance teams already understand.
The state of agent traffic in documentation (March 2026)
An analysis of 30 days of Mintlify documentation traffic, broken down by AI agents, browsers, and other sources.
Documentation is your AI interface
Your docs are doing more than ever--they're still your best developer resource and now the interface through which AI understands your product too.
Mintlify + Claude Opus 4.6: Powering AI-native knowledge management
How Mintlify is using Claude to deliver more concise, accurate documentation assistance
Why do we need MCP if skills exist now?
Skills and MCP solve different problems. Skills package knowledge. MCP packages authenticated, scoped access on a user's behalf.
Documentation is dead. Long live documentation.
How documentation is changing in the age of AI.
Top 7 ways to blend SEO with GEO for explosive brand growth
Practical tips on how to adapt your content strategy for GEO.
How Mintlify uses Claude Code as a technical writing assistant
As the sole technical writer at Mintlify, I'm always looking for ways to improve my workflows and empower other people on my team to contribute to the docs. I also want to take a vacation without blocking docs ships for a week and a half.
AI Documentation Trends: What's Changing in 2025
Coming into 2025, there were a number of predictions as to how AI would impact what we do and how we do it. And just halfway through the year, those predictions are already reshaping our daily tools and practices faster than anyone expected, across nearly every domain.
How to generate llms.txt
If you're trying to set up an llms.txt file, you're probably already familiar with the standard: a lightweight way to help AI tools better index your site's content.
Mintlify acquires Trieve to improve RAG search in documentation
We're excited to announce that Mintlify has acquired Trieve, a provider of retrieval-augmented generation (RAG) infrastructure designed to power quality AI search and chat experiences.
Behind Replit's Documentation Transformation
Replit is one of the hottest AI startups for creating and deploying AI applications.
How often do LLMs visit llms.txt?
Last month, we explored signals for the emerging standard of llms.txt, which is a Markdown file that makes websites easier for LLMs to index.
How Claude's memory and MCP work (and when to use each)
Large Language Models (LLMs) like Claude can read files, troubleshoot issues, use external tools, and write tutorials much faster than a human ever could. But they are prone to hallucinations, struggle to follow complex instructions, and miss important context.
Introducing AI Assistant: Turning docs into your product expert
AI is the new interface for learning about your product.
How to hire your first technical writer
Hiring your first technical writer feels obvious in hindsight, but rarely in the moment. Founders know documentation is important. Teams start drowning in support questions. Engineers grumble about having to write. And then, usually after too much pain, someone says it out loud: we need a writer.
GEO guide to optimize writing for LLMs
Google made it official last week at I/O: AI Overviews are now the default search experience in the U.S.—reaching over 1.5 billion people.
How Windsurf writes docs
At Windsurf, a leading player in the AI coding space, documentation is integrated in how they build, ship, and market their product.