# AI Trends Published articles for AI Trends. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Rise of the Knowledge Engineer DevFeed: [Rise of the Knowledge Engineer]() Original publisher: [Read original article]() Author: David Isquick Published: 2026-09-16T00:00:00Z Content type: article Language: en Sources: [Mintlify Blog]() Topics: [Documentation](), [Artificial Intelligence](), [AI-assisted coding](), [Users]() Tags: [agents](), [ai](), [ai-trends](), [api](), [developers](), [documentation](), [knowledge-base](), [operational](), [source-of-truth](), [support](), [workflows]() ### AI overview The article examines the rise of the knowledge engineer as companies increasingly serve AI agents that read documentation, compare products, solve support problems, and perform tasks. It argues that organizations need operating systems and processes to keep knowledge accurate, accessible, consistent, and retrievable, because incorrect information can spread through generated code, support responses, and automated workflows. ### Source excerpt 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 DevFeed: [Highlights from the 2026 State of Knowledge Report]() Original publisher: [Read original article]() Author: Lauren Volpi Published: 2026-09-16T00:00:00Z Content type: article Language: en Sources: [Mintlify Blog]() Topics: [Documentation](), [Artificial Intelligence](), [HTML](), [Website](), [MCP]() Tags: [2026](), [ai](), [ai-agents](), [ai-trends](), [documentation](), [llms-txt](), [markdown](), [mcp](), [report]() ### AI overview Mintlify's 2026 State of Knowledge Report examines how AI agents are changing documentation readership and access. It reports that agent requests exceeded human page loads on Mintlify-powered sites in August, with many agents using Markdown, llms.txt, agent skills, and MCP tool calls. Controlled tests across 20 documentation sites found that linking Markdown pages to llms.txt improved agent navigation and reduced token consumption. ### Source excerpt 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 DevFeed: [The state of docs traffic: a 2026 midyear report]() Original publisher: [Read original article]() Author: Kyan Yang Published: 2026-07-29T00:00:00Z Content type: article Language: en Sources: [Mintlify Blog]() Topics: [Documentation](), [Model Context Protocol](), [Logging](), [Server]() Tags: [2026](), [agent](), [ai-trends](), [clients](), [docs](), [mcp](), [report](), [retrieval](), [search](), [servers](), [tool]() ### AI overview Mintlify's 2026 midyear report examines how agents access documentation. It reports that agents represented 66% of measured web traffic in July, with direct machine routes becoming more common, and separately analyzes MCP assistant responses and tool calls. ### Source excerpt 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 DevFeed: [Docs as an abstraction layer for coding agents]() Original publisher: [Read original article]() Author: Han Wang Published: 2026-06-08T00:00:00Z Content type: article Language: en Sources: [Mintlify Blog]() Topics: [Documentation](), [AI-assisted coding](), [Claude Code](), [Model Context Protocol (MCP)](), [Development]() Tags: [ai-coding-agents](), [ai-trends](), [claude](), [claude-code](), [coding-agents](), [docs](), [mcp](), [performance](), [tokens]() ### AI overview The article describes controlled experiments testing structured Mintlify documentation as an abstraction layer for coding agents working in large codebases. It reports more precise answers, better discoverability, lower token consumption, and faster task completion than a no-docs baseline. ### Source excerpt 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. ## Why content infrastructure involves more than rendering Markdown DevFeed: [Why content infrastructure involves more than rendering Markdown]() Original publisher: [Read original article]() Author: Han Wang Published: 2026-06-03T00:00:00Z Content type: opinion Language: en Sources: [Mintlify Blog]() Topics: [Markdown](), [Documentation](), [hosting](), [Command-line interface](), [ci]() Tags: [ai-trends](), [ci](), [cli](), [docs](), [hosting](), [markdown]() ### AI overview This opinion article argues that rendering Markdown is only a small part of building content infrastructure. It describes the additional work involved in keeping documentation current, providing useful search, and supporting web, API, CLI, and CI-based workflows, while presenting Mintlify as a hosted alternative. ### Source excerpt 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 DevFeed: [Tokenmaxxing: one AI budget, four jobs]() Original publisher: [Read original article]() Author: Shawn Lestage Published: 2026-05-25T00:00:00Z Content type: opinion Language: en Sources: [Mintlify Blog]() Topics: [Artificial Intelligence](), [Claude Code](), [cursor](), [pull-requests]() Tags: [ai](), [ai-trends](), [claude](), [claude-code](), [cost](), [cursor](), [product](), [pull-requests]() ### AI overview The article presents a framework for evaluating AI token spending by mapping Credits to familiar P&L categories such as R&D, COGS, sales and marketing, and retention. It argues that separating these costs helps companies assess their relationship to engineering output, support costs, customer retention, and revenue. ### Source excerpt 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) DevFeed: [The state of agent traffic in documentation (March 2026)]() Original publisher: [Read original article]() Author: Han Wang Published: 2026-04-03T00:00:00Z Content type: article Language: en Sources: [Mintlify Blog]() Topics: [Documentation](), [ai-coding](), [Claude Code](), [cursor](), [Cloudflare](), [browsers]() Tags: [2026](), [agent](), [agents](), [ai](), [ai-agents](), [ai-coding](), [ai-coding-agents](), [ai-trends](), [analysis](), [browsers](), [caveat](), [claude-code](), [cloudflare](), [cursor](), [documentation](), [edge](), [firefox](), [http]() ### AI overview Mintlify analyzes 30 days of Cloudflare traffic across its documentation sites and finds that AI coding agents accounted for 45.3% of requests, nearly matching traditional browser traffic at 45.8%. Claude Code and Cursor generated 95.6% of identified AI-agent traffic, while OpenAI Codex could not be distinguished because it does not provide an identifying user-agent header. ### Source excerpt An analysis of 30 days of Mintlify documentation traffic, broken down by AI agents, browsers, and other sources. ## Documentation is your AI interface DevFeed: [Documentation is your AI interface]() Original publisher: [Read original article]() Author: Han Wang Published: 2026-03-13T00:00:00Z Content type: opinion Language: en Sources: [Mintlify Blog]() Topics: [Documentation](), [Artificial Intelligence](), [AI Agent](), [dev-tools](), [Model Context Protocol](), [Markdown](), [Claude](), [cursor](), [GitHub Copilot]() Tags: [agent](), [ai](), [ai-trends](), [developer](), [documentation](), [javascript](), [markdown](), [mcp]() ### AI overview The article argues that documentation should serve as an interface for AI systems as well as human developers. It says teams are building CLIs and machine-readable endpoints for agents, while documentation is often optimized for human browsing rather than machine parsing. It highlights MCP servers, llms.txt, and structured Markdown as ways AI assistants consume documentation. ### Source excerpt 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 DevFeed: [Mintlify + Claude Opus 4.6: Powering AI-native knowledge management]() Original publisher: [Read original article]() Author: Patrick Foster Published: 2026-02-05T00:00:00Z Content type: article Language: en Sources: [Mintlify Blog]() Topics: [Claude](), [Artificial Intelligence](), [knowledge-management](), [Conversational AI](), [anthropic]() Tags: [ai](), [ai-trends](), [api](), [claude](), [code](), [context-window](), [conversational-ai](), [debugging](), [knowledge-management]() ### AI overview Mintlify describes early testing of Claude Opus 4.6 in its documentation assistant. It reports more concise responses, improved search and tool calling, deeper code understanding, better bug identification, and support for a 1M-token context window. ### Source excerpt How Mintlify is using Claude to deliver more concise, accurate documentation assistance ## Why MCP and Skills Are Complementary for AI Agents DevFeed: [Why MCP and Skills Are Complementary for AI Agents]() Original publisher: [Read original article]() Author: Michael Ryaboy Published: 2026-01-26T00:00:00Z Content type: article Language: en Sources: [Mintlify Blog]() Topics: [Model Context Protocol](), [AI Agent](), [Authentication](), [OAuth](), [Caching](), [context window](), [Claude](), [anthropic]() Tags: [ai](), [ai-agent](), [ai-trends](), [authentication](), [context-window](), [dev](), [kv-cache](), [mcp](), [oauth](), [performance](), [skills]() ### AI overview This article explains that MCP and Skills address different needs for AI agents: MCP provides standardized, authenticated and scoped access to external services, while Skills package the knowledge needed to use tools effectively. It also discusses MCP's context bloat and caching costs, and presents CLIs as an emerging complementary pattern. ### Source excerpt Skills and MCP solve different problems. Skills package knowledge. MCP packages authenticated, scoped access on a user's behalf. ## How Documentation Is Changing in the Age of AI DevFeed: [How Documentation Is Changing in the Age of AI]() Original publisher: [Read original article]() Author: Han Wang Published: 2025-11-24T00:00:00Z Content type: opinion Language: en Sources: [Mintlify Blog]() Topics: [Documentation](), [Artificial Intelligence](), [AI Agent](), [Critical Infrastructure](), [Claude Code](), [cursor]() Tags: [agent](), [ai](), [ai-agent](), [ai-trends](), [claude-code](), [critical-infrastructure](), [cursor](), [development](), [documentation](), [quality]() ### AI overview The article argues that documentation now serves both human readers and AI systems, including support agents, coding assistants, and other automated workflows. It emphasizes that inaccurate or incomplete documentation can cause AI systems to repeat errors at scale, and argues for self-updating knowledge systems because human-maintained documentation is difficult to keep current. ### Source excerpt How documentation is changing in the age of AI. ## Seven Ways to Combine SEO and Generative Engine Optimization for Content Visibility DevFeed: [Seven Ways to Combine SEO and Generative Engine Optimization for Content Visibility]() Original publisher: [Read original article]() Author: Emma Adler Published: 2025-09-24T00:00:00Z Content type: tutorial Language: en Sources: [Mintlify Blog]() Topics: [Search engine optimization (SEO)](), [Artificial Intelligence](), [Google](), [Website]() Tags: [ai](), [ai-tools](), [ai-trends](), [content-strategy](), [generative-engine-optimization](), [geo](), [google](), [how-to](), [practical](), [search](), [seo](), [strategy](), [tips](), [visibility]() ### AI overview This tutorial explains how Generative Engine Optimization (GEO) complements search engine optimization (SEO) as AI tools and AI Overviews change how online content is discovered. It recommends concise Q&A-style content, authoritative and timely material, and user-generated content to improve the likelihood of visibility and citation in AI-generated answers. ### Source excerpt Practical tips on how to adapt your content strategy for GEO. ## How Mintlify uses Claude Code as a technical writing assistant DevFeed: [How Mintlify uses Claude Code as a technical writing assistant]() Original publisher: [Read original article]() Author: Ethan Palm Published: 2025-08-19T00:00:00Z Content type: article Language: en Sources: [Mintlify Blog]() Topics: [Claude Code](), [Documentation](), [Code](), [configuration](), [context]() Tags: [ai-trends](), [claude-code](), [code](), [configuration](), [context](), [documentation](), [memory](), [quality](), [review](), [technical](), [technical-writing](), [terminal](), [tools](), [workflows]() ### AI overview Ethan Palm describes how Mintlify uses Claude Code as a technical writing assistant. The workflow includes CLAUDE.md guardrails, persistent memory across sessions, custom skill commands, and support for planning, drafting, updating, and reviewing documentation. The article emphasizes verifying all AI-generated documentation with human expertise. ### Source excerpt 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 DevFeed: [AI Documentation Trends: What's Changing in 2025]() Original publisher: [Read original article]() Author: Emma Adler Published: 2025-08-06T00:00:00Z Content type: article Language: en Sources: [Mintlify Blog]() Topics: [Artificial Intelligence](), [Documentation](), [Large Language Model](), [Developer experience](), [Model Context Protocol](), [ChatGPT](), [Claude]() Tags: [ai](), [ai-trends](), [developer-experience](), [developer-tools](), [developers](), [documentation](), [large-language-models-llms](), [model-context-protocol]() ### AI overview The article examines how AI is changing documentation in 2025. It argues that documentation teams need to structure content for AI readers, including through structured content, llms.txt files, and Model Context Protocol integration, because language models increasingly discover, summarize, quote, and use documentation in developer-facing interfaces. ### Source excerpt 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 DevFeed: [How to generate llms.txt]() Original publisher: [Read original article]() Author: Tiffany Chen Published: 2025-07-25T00:00:00Z Content type: tutorial Language: en Sources: [Mintlify Blog]() Topics: [Documentation](), [Large Language Model](), [Markdown](), [Template]() Tags: [ai-trends](), [documentation](), [generator](), [guide](), [how-to](), [llms](), [markdown]() ### AI overview A practical guide to creating and hosting an llms.txt file. It explains the Markdown structure, describes Mintlify's generator, and covers how to organize useful documentation links for AI tools. ### Source excerpt 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 DevFeed: [Mintlify acquires Trieve to improve RAG search in documentation]() Original publisher: [Read original article]() Author: Han Wang Published: 2025-07-24T00:00:00Z Content type: release Language: en Sources: [Mintlify Blog]() Topics: [Retrieval Augmented Generation (RAG)](), [AI search](), [Documentation]() Tags: [ai](), [ai-search](), [ai-trends](), [announce](), [documentation](), [rag](), [search]() ### AI overview Mintlify has acquired Trieve, a provider of retrieval-augmented generation infrastructure, to enhance AI search and chat experiences in documentation. The companies aim to provide faster, more accurate, and context-aware answers at scale. ### Source excerpt 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. ## How often do LLMs visit llms.txt? DevFeed: [How often do LLMs visit llms.txt?]() Original publisher: [Read original article]() Author: Tiffany Chen Published: 2025-06-27T00:00:00Z Content type: article Language: en Sources: [Mintlify Blog]() Topics: [Large Language Model](), [Markdown](), [Data analysis](), [Crawler](), [Retrieval-Augmented Generation]() Tags: [ai-trends](), [claude](), [data-analysis](), [google](), [llms](), [markdown](), [pages](), [retrieval](), [retrieval-augmented-generation]() ### AI overview The article presents a Profound data analysis of how language models access llms.txt and llms-full.txt. The supplied text says both files receive AI traffic, with a strong preference for llms-full.txt and ChatGPT accounting for most visits. It attributes this preference to models embedding full content instead of relying on retrieval-augmented generation, while noting that the analysis covers 25 companies. ### Source excerpt 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. ## Behind Replit's Documentation Transformation DevFeed: [Behind Replit's Documentation Transformation]() Original publisher: [Read original article]() Author: Tiffany Chen Published: 2025-06-27T00:00:00Z Content type: article Language: en Sources: [Mintlify Blog]() Topics: [Documentation](), [Repl.it](), [developer-relations](), [Artificial Intelligence]() Tags: [agents](), [ai](), [ai-trends](), [developer-relations](), [documentation](), [replit](), [vibe-coding]() ### AI overview Mintlify examines how Replit rebuilt its documentation during the company's shift toward AI. The overhaul rewrote much of the documentation for vibe coders and AI agents and introduced Vale linting, automated changelogs, and AI-assisted writing workflows. The article reports that these changes reduced manual changelog work by 90% and established processes intended to support continued product growth. ### Source excerpt Replit is one of the hottest AI startups for creating and deploying AI applications. ## How Claude's memory and MCP work (and when to use each) DevFeed: [How Claude's memory and MCP work (and when to use each)]() Original publisher: [Read original article]() Author: Emma Adler Published: 2025-06-24T00:00:00Z Content type: tutorial Language: en Sources: [Mintlify Blog]() Topics: [Claude](), [Model Context Protocol](), [context](), [Large Language Model]() Tags: [ai-trends](), [claude](), [documentation](), [llms](), [memory](), [model-context-protocol]() ### AI overview This guide compares Claude's memory with Model Context Protocol (MCP). Memory retains user preferences and context across sessions, while MCP provides real-time access to external sources such as files, logs, documentation, and APIs during a session. It also explains that well-organized documentation helps both methods work effectively. ### Source excerpt 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. ## How to hire your first technical writer DevFeed: [How to hire your first technical writer]() Original publisher: [Read original article]() Author: Emma Adler Published: 2025-05-27T00:00:00Z Content type: tutorial Language: en Sources: [Mintlify Blog]() Topics: [Documentation](), [Tooling](), [Support]() Tags: [ai-trends](), [developer](), [guides](), [hiring](), [how-to](), [technical]() ### AI overview This guide explains when and how to hire a company's first technical writer. Drawing on experiences from technical writers, it emphasizes timely hiring, access to appropriate tools, candidates with initiative and curiosity, and support systems for maintaining useful documentation. ### Source excerpt 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 DevFeed: [GEO guide to optimize writing for LLMs]() Original publisher: [Read original article]() Author: Tiffany Chen Published: 2025-05-27T00:00:00Z Content type: tutorial Language: en Sources: [Mintlify Blog]() Topics: [Large Language Model](), [Documentation](), [tokenization]() Tags: [ai-trends](), [documentation](), [geo](), [guide](), [llms](), [writing]() ### AI overview This guide explains how to improve documentation readability and retrieval for large language models using Generative Engine Optimization principles. It covers tokenization, chunking, embeddings, and five practices: consistent headings, clear pronouns, text alternatives for media, consistent terminology, and correctly formatted code examples. ### Source excerpt 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 DevFeed: [How Windsurf writes docs]() Original publisher: [Read original article]() Author: Tiffany Chen Published: 2025-05-27T00:00:00Z Content type: article Language: en Sources: [Mintlify Blog]() Topics: [Documentation](), [product analytics](), [ai-coding](), [human review]() Tags: [agent](), [ai-coding](), [ai-trends](), [documentation](), [human-review](), [product-analytics]() ### AI overview Windsurf treats documentation as a core product component, with marketing leading the process and shipping docs alongside every release. The team uses product analytics to monitor adoption and guide improvements, focuses pages on user value, and applies AI tools with human review to maintain consistency and quality. ### Source excerpt At Windsurf, a leading player in the AI coding space, documentation is integrated in how they build, ship, and market their product. ## Should you generate docs from your API schema? DevFeed: [Should you generate docs from your API schema?]() Original publisher: [Read original article]() Author: Emma Adler Published: 2025-05-16T00:00:00Z Content type: tutorial Language: en Sources: [Mintlify Blog]() Topics: [Documentation](), [OpenAPI Specification](), [API](), [Structured-data](), [Swagger](), [JSON](), [YAML]() Tags: [ai-trends](), [api](), [api-documentation](), [automate](), [automation](), [best-practices](), [hybrid](), [json](), [openapi](), [schemas](), [swagger]() ### AI overview This guide examines the benefits and limitations of generating API documentation from OpenAPI schemas. It explains how schema-based tools such as Swagger UI automatically create documentation from structured endpoint, method, data model, and response definitions, while noting that automation can leave gaps in user guidance and conceptual explanations. It recommends combining automation with customization. ### Source excerpt When your API constantly changes, how do you ensure your documentation keeps up? ## Evaluating the Value of llms.txt for AI Retrieval DevFeed: [Evaluating the Value of llms.txt for AI Retrieval]() Original publisher: [Read original article]() Author: Tiffany Chen Published: 2025-05-09T00:00:00Z Content type: article Language: en Sources: [Mintlify Blog]() Topics: [LLMs](), [web-standards](), [AI Trends]() Tags: [a2a-protocol](), [ai-trends](), [anthropic](), [generative-engine-optimization](), [google](), [llms]() ### AI overview The article evaluates whether llms.txt provides practical value for AI-driven discovery and retrieval. It argues that structured, simplified text files can help large language models process web content more efficiently, citing reported adoption and observations from Vercel, Google, Anthropic, and Windsurf. ### Source excerpt If you've been following AI trends, you've probably heard of llms.txt. [Next page]()