- Three commands, never a click.
search(Bing),open(skim a page as numbered plaintext),find(Ctrl+F inside the open page).clickwas used zero times across every logged session — content reachable only via JavaScript, accordions, tabs, or filters does not exist for the agent. Client-rendered SPAs are hit hardest. - All retrieval runs on Bing (
web_with_bing), no Google fallback. Bing snippets cap at ~285 characters — the entire window you get to earn the open. For ChatGPT, only the top 2–3 Bing results per query make the read set once the agent is confident (itstopndepth parameter narrows from 10 to 2–3 as it converges). - The read is your HTML, linearized top-to-bottom in source order,
<head>stripped, nothing JS-rendered. It follows links — including internal ones — by reading the href from inline link markers, so descriptive anchor text routes it to pricing and spec pages. - Blocked means invisible.
robots.txtblocks onOAI-SearchBotreturn zero content (this is a different bot from GPTBot, which governs training — see AI bot types). Login walls, bot-refusing marketplaces, and timeouts silently drop sources. - Re-reads are keyword-driven: the top trigger is a successful
find— the agent re-opens the page positioned on the matched line (95% of the time in the sample). Use the exact words people search, verbatim, in headings and copy.
How ChatGPT Deep Research reads your site — Bing, three commands, no clicks
Peec recorded Deep Research’s logs (Jun 2026) — the agent runs on Bing snippets (~285 chars), three text-browser commands (search, open, find), never clicks, and obeys OAI-SearchBot rules.
ChatGPT Deep Research narrates its whole session over a recordable WebSocket, and Peec recorded it across 10+ accounts and ~200 runs (full study, Jun 2026). The mechanics (this covers Deep Research’s text browser, not quick Search or Agent mode):
