ChatGPT SEO: How to Earn Discovery, Citations and Clicks
A practical ChatGPT SEO workflow that separates crawler discovery, answer citations, referral clicks and qualified outcomes instead of hiding them in one score.
-
-
Cloudflare /crawl Now Enforces Content Signals: Test reference vs full
Cloudflare Browser Rendering now compares /crawl contentUse with a publisher’s Content Signals ceiling. Use this controlled matrix to test reference and full without overstating what the signal proves.
-
ChatGPT Work Can Sign Into Websites: What Publishers Should Measure
ChatGPT Work can help on some signed-in websites after the user enters credentials. Publishers should distinguish crawler, public fetch, signed-in session, and webhook traffic.
-
Google Now Unescapes JSON-LD Once: Find Double-Escaped Schema
Google now applies one HTML-unescape pass while extracting JSON-LD. Audit templates for double-escaped values and fix the serializer rather than individual pages.
-
Google AI Mode Adds Link Carousels for Developing Topics
Google AI Mode can now show link carousels for developing topics. A 24-, 48-, and 72-hour ledger helps publishers separate inclusion, source movement, and visits.
-
Google AI Overviews Can Expand Before You Scroll
Some Google AI Overviews can expand automatically before a user scrolls. Measure the pixel displacement and first-organic visibility instead of relying on rank position alone.
-
ChatGPT Restaurant Reservations: Local Search Guide
ChatGPT now connects restaurant questions to reservation availability through OpenTable, Resy, and Yelp. Selection, inventory, and completed bookings remain separate outcomes.
-
Perplexity Source Labels Apply to Domains, Not Every Page or Claim
Perplexity’s Government, Academic, and Trusted labels provide domain-level context. They do not endorse every page, verify every claim, or promise citation visibility.
-
Google AI Search Console Logging Error: Aug 13–17
Google says a Search Console logging error underreported Generative AI impressions from August 13 through August 17. It was a reporting issue, not an actual traffic decline.
