ChatGPT started citing my site. Here is what I changed, and what I still cannot prove.
In short — ChatGPT began naming Suman Debnath for the query "who is Suman Debnath" two days after a full answer-engine optimisation pass — a generated llms.txt, extractable answer blocks, entity disambiguation and structured data. Keyword stuffing was tried first and did nothing. Two days is not proof of cause, and Claude, Gemini and Grok still do not cite the site. First observed 24 August 2026…
ChatGPT began citing Suman Debnath's site two days after optimizing the page for search engines. The optimization included generating an llms.txt file, extractable answer blocks, entity disambiguation, and structured data. Initial attempts at keyword stuffing proved ineffective, as it did not alter the results. The first observation was made on August 24, 2026, with queries such as "who is Suman Debnath" and "Suman Debnath portfolio."
The tests were conducted on three devices, including one where the name had never been used before. After conducting the optimization work, the site started being cited by ChatGPT within two days. However, Claude, Gemini, and Grok still do not mention the site. The author discovered this after trying to find a shortcut by stuffing their name into metadata and headings, but it did not yield any results.
The key takeaway is that entity resolution is the process by which answer engines determine which real-world person a name refers to and whether they have enough information about that person to provide an answer. Repetition and more instances of the name in various fields did not help with either. The author also discovered that Claude, Gemini, and Grok do not cite their site due to the fact that they do not share an index and do not have access to the site's content.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.