Your documentation's biggest readers stopped being human. mintlify's analytics across hosted docs…
your documentation's biggest readers stopped being human. mintlify's analytics across hosted docs sites show close to half of traffic now comes from ai agents like cursor and claude code, which means onboarding content has to be machine-readable first.
the new reader needs structured headings, not prose.
Context
Mintlify's post The state of agent traffic in documentation (March 2026), published 3 April 2026, analyzes 30 days of traffic across Mintlify-powered docs sites, about 790 million requests classified by user-agent headers from Cloudflare. AI coding agents made 357.6 million requests, 45.3 percent of all requests, against traditional browsers at 45.8 percent, with Claude Code at 199.4 million (25.2 percent) and Cursor at 142.3 million (18.0 percent). The post says not every agent sends an identifiable user-agent and that OpenAI's Codex does not, so its traffic cannot be told apart from generic HTTP clients.
Close to half is supported for the March 2026 window at 45.3 percent, vendor data and not independent, and no September 2026 figure was inspected. The unit is requests and not readers, and classification is by user-agent string, so a request share need not be a share of readers. Browsers are still slightly higher at 45.8 percent, so the biggest readers stopped being human goes beyond the data. Machine-readable first is the author's recommendation and no outcome evidence was seen.
Watch next
- The Mintlify data page's current figure and definition, and a later 30-day window.
Sources
Provenance
The note above is reproduced unedited from the original post, first published on Threads on 21 September 2026 at 04:48 IST. Sources are the papers and datasets the note draws on.
View the original post ↗Embed this note
More notes
The air is now being asked to keep its own ledger
the air is now being asked to keep its own ledger: ecmwf’s aifs compo becomes the first ai model to forecast atmospheric composition globally every three hours, cleanair simulates 365 days of pm2.5 over china in ten seconds, and a unified framework maps six pollutants at one kilometer across the whole country. the air now files its own composition report.
read the note →The current is now being asked to draw its own map
the current is now being asked to draw its own map: china’s langya 2.0 predicts six ocean phenomena including internal waves and mesoscale eddies, a deep net called wenhai resolves eddies globally with air sea flux formulas built in, and scripps infers surface currents from the way temperature patterns deform in satellite images. the ocean now files its own circulation report.
read the note →The soil is now being asked to report its own carbon
the soil is now being asked to report its own carbon: a nix color sensor paired with generative data augmentation predicts soil organic carbon without a lab, random forest drives 74 percent of soil health mapping studies, and sentinel 2 tracks five year carbon change across france and italy from 922 samples. the dirt now files its own carbon account.
read the note →