July 2026 Summaries

In the midyear 2026 report on documentation traffic by Mintlify, agent-driven web requests have surged dramatically, accounting for 66% of total traffic compared to just 15.2% at the year's start, with projections suggesting this could reach 90% by year-end. This shift underscores the importance of machine-readable routes for agents, as they primarily utilize explicit machine routes, particularly .md file requests, which increased significantly from February to July. Machine Client Protocol (MCP) activities, which include search and filesystem tool calls, have also risen, with search accounting for a majority of these calls. The report highlights the inefficiencies in agent operations, where incorrect URL guesses and irrelevant page loads inflate request volumes, and emphasizes the benefits of integrating llms.txt to reduce errors. Mintlify's unified publishing system aims to synchronize human and machine-readable content, ensuring consistent updates across all formats and enhancing analytics to better understand customer needs and documentation shortcomings.

Browserbase encountered a persistent issue where Claude Code generated 404 errors when accessing Mintlify-hosted documentation, due to the absence of navigational guidance in stripped-down markdown pages meant for AI agents. To address this, a simple solution involved linking to an llms.txt file, which serves as a comprehensive map of available pages, dramatically reducing dead URLs and unnecessary fetches. A benchmark test, involving 2,400 runs across different document formats and AI models, confirmed that linking to llms.txt was the most efficient method, cutting down token usage and improving navigation without compromising accuracy. The study highlights the growing importance of structuring documentation not just for human readability but also for the navigation capabilities of AI agents, with the llms.txt link proving to be an effective and low-cost solution for optimizing agent interactions with documentation.