Claude's WebFetch never reads raw HTML: pages are extracted to markdown and answered by a small model

gaganghotra_ · x · 2026-09-23

Natzir Turrado corrects two misreadings of the new Claude tools: fetch tools never read raw HTML — they extract to text/markdown first ("markdown" plus legacy "traf" in Opus 4.7) — and fan-out with parallel subagents was already described by Anthropic in June 2025; the only novelty is a small fast model reading the markdown. His experiment on 15 HTML layout variants maps which page structures survive LLM extraction (no JS execution, Readability-style extraction), with SEO implications: money-page rankings aren't enough, evidence must hold up per decision criterion.

Original post →

More from Models

Models channel →