Skip to content
Claude logo

How AI assistants read claude.com

What a machine reading this site receives: identity files, schema, crawler policy, the entity behind the name. Read weekly by a crawler, no model call. For the people who run Claude; the catalogue page is for the people who choose it.

← Back to Claude

Atlas Readinesssweptswept 2026-09-17

70/100

#1 of 134 rated Agents tools#12 of 4809 in the Atlas
  • Entitynot read
  • Machine-readable12.3/35
  • Retrieval access20/20
  • Footprint20/20
out of 75 of 100 points — entity not read
Usedsweptswept 2026-09-17

92/100

Does anybody use it: audience (Tranco list, Chrome UX report, estimated organic visits), installs from registries, referring domains. Never votes, never reviews.

  • Audience34.5/40
  • Installsnot read
  • References30/30
out of 70 of 100 points — installs not read
Alivesweptswept 2026-09-17

100/100

Is anybody home: the homepage answers, the content moves, something ships, somebody hires. Each part a dated reading from a public place; a part not read is left out and the total rescaled.

  • Answersnot read
  • Content moves30/30
  • Shipsnot read
  • Hiringnot read
out of 30 of 100 points — answers and ships and hiring not read
Against the fieldsweptreadiness, out of 100
  • Claude70
  • Agents medianof 135 rated59
  • Atlas medianof 4866 rated58
What the sweep readsweptswept 2026-09-17

  • The homepage did not answer when swept. robots.txt and llms.txt live at their own addresses and were still read.

  • Retrieval botsopenverify

    Whether the bots that decide citations are let in. Training bots are a separate list and are not counted here.

  • llms.txtyesverify

    A plain-text index at /llms.txt. Optional; read by some tools.

  • Organization schemanot read

    schema.org Organization markup on the homepage, which is what a resolver reads a company's name and links from.

  • Wikidata itemnot looked up

    Matched on the official website, never on the name. The substrate under the knowledge graph an engine resolves names against.

  • Server-rendered wordsnot read

    What a reader without JavaScript receives from the homepage.

  • Identity score35/100swept

    The analyzer's crawl-only section, 0-100: identity files, schema, crawler policy, sitemap. Not the analyzer score.

Position in Agentsswept129 swept

35/100

identity score

0identity score, 0-100100
4th percentile of 129 · median 90

Not measured with the analyzer.

The full run asks four engines about this company by name. It runs on request, not on a schedule.

Questions this page answers
  • What is Claude's Atlas Readiness?

    70 of 100 on 2026-09-17, computed from four parts — entity, machine-readable, retrieval access, footprint — out of 75 of 100 points — entity not read. It places #1 of 134 rated Agents tools.

  • Does Claude let AI retrieval bots in?

    Yes. On 2026-09-17, robots.txt at claude.com disallowed none of the retrieval crawlers we check.

  • Does Claude publish an llms.txt?

    Yes: claude.com/llms.txt was present on 2026-09-17.

  • Is Claude a Wikidata entity?

    Wikidata could not be asked on 2026-09-17.

How to read a row

swept
Read by a crawler: HTTP and parsing, no model call. Every row, every week.
measured
The full analyzer run, asked of four engines. Shown only where the company agreed to show it.

Can a retrieval engine find, resolve and quote this site? Four parts, each read by the sweep, each shown beside the total.

Entity 25 · Machine-readable 35 · Retrieval access 20 · Footprint 20

A part that was never read is left out and the total is rescaled to what was. It is never counted as zero.

Measure your own site →