AI Visibility Lab — A public experiment

Using this site to study identity consistency, content evidence, and discoverability in AI search. The first saved search answers establish a starting point for observing how the public record is understood.

What this experiment observes

This site is a working experiment in how my identity and technical work are discovered through AI search. The first step is to make the public record consistent and separate four different outcomes.

Identity: does the answer correctly identify Wayturn and the work described here?
Discovery: does an answer mention this site without being given my name or URL?
Citation: does a linked page actually support the statement attached to it?
Visits: do people reach and read the site? Bot access and human visits are separate observations.

A fixed question set

Branded questions test identity. Unbranded questions observe discovery around relevant topics; they do not assume that every answer should mention Wayturn.

B1 · Wayturn 是誰？他主要分享什麼內容？
B2 · 洪偉騰與 Wayturn Hung 是同一位工程師嗎？有哪些公開作品？
B3 · Who is Wayturn Hung, and what does he work on?
B4 · What does Wayturn document about AI-assisted engineering and AI visibility?
U1 · 從 .NET Framework 遷移到 ASP.NET Core，如何規劃代表性 POC 與行為驗證？
U2 · 小型 AI 開發工具要如何設計工具邊界與可追蹤輸出？
U3 · How can a personal website test whether AI search identifies its author correctly?
U4 · How should I document a research program deployed to the cloud without overstating its production readiness?

How each run is recorded

Use a fresh conversation without this website discussion. Record the platform, displayed model, search setting, personalization setting, locale, exact prompt, time, and site content version. A model version that is not shown is recorded as unknown.

Save the original answer and cited URLs, then manually check identity and whether each citation supports its claim. URL-provided reading tests form their own group because giving the address is different from natural discovery.

Keep branded, unbranded, and provided-URL results separate.
Report raw counts with the sample size and conditions.
Record unavailable or failed tests as not tested, not as zero.
Repeat under comparable conditions and preserve answers that did not mention the site.

First observation · 6 September 2026

The first observation used independent Codex agents with public web search: eight fixed questions, one fresh answer per question. Each started without the website discussion, and no target URL was supplied. Original answers, search queries, times, citations, and a review of their supporting evidence are saved in the linked record.

All four branded answers mentioned Wayturn and cited this site; three of four passed the review of identity, current work claims and supporting citations. None of the four unbranded answers mentioned or cited Wayturn. These are separate question groups, each with only four observations.

One branded answer repeated older portfolio claims that the current pages no longer support. Search results and directly opened pages did not always describe the same version of the site.

This is a small observation from one agent-and-search setup, not a test of consumer ChatGPT or Gemini. The model label, search region and search personalization were not exposed or controlled. Search Console and human visits were not measured.

The observed site version was 0b40d37, already after the redesign and before this final polish. There is no before-and-after improvement measurement. Later differences will need comparable runs, not an assumption that a design or schema change caused them.

The next four weeks

Keep the design stable while gathering observations. Review indexing and search queries weekly when Search Console access is available, repeat the fixed questions every two weeks, and review the evidence after four weeks. Fix broken pages and add substantive project results as they arise.