Dental AI Search Visibility Across Four Platforms

Fix the dental jobs before collecting answers

The protocol and 18 exact query cells were fixed before paid collection. Three convenience-selected US markets were crossed with veneers, implants and urgent dental care, using provider-selection and dentist/branch/evidence wordings. No practice brand was seeded in a query.

Collect the four surfaces separately

DataForSEO LLM Scraper collected ChatGPT and Gemini. ChatGPT used force_web_search=true. Google AI Overviews used organic live/advanced, depth 10 and asynchronous AI Overview loading; AI Mode used its own live endpoint. US-English country-level location 2840, desktop and Windows settings were used; city names were explicit in the query.

The returned model identifiers are retained in the public data where provided. This collection does not establish equivalence to every signed-in consumer session.

Keep repeats and collection states visible

The core contains 216 scheduled observation slots: three sequential same-day waves, 54 per platform. After the three first-pass waves, 18 explicitly diagnosed temporary failures received at most one missing-only recovery using the same query, surface and settings. There were 234 core requests in total. 5 technical preflight requests are excluded.

181 final core slots contained an AI answer; 28 successfully completed slots had no AI answer; 7 retained an unresolved collection error. Original failure states and both timestamps remain in the public observation metrics. Scheduled repeat labels are not a claim that delayed recoveries occurred in their original chronological wave. Provider-side caching was not controllable.

Count final-answer citations and source-set similarity

ChatGPT/Gemini use the provider’s declared final-answer sources, not unused search results. Google uses references inside top-level AI answer items, not ordinary organic listings, local packs or People Also Ask. URLs are deduplicated within an answer after hostname/www, tracking, fragment and trailing-slash normalization. Hostname means the normalized host, not corporate ownership.

Jaccard is intersection divided by union. Empty/empty citation sets are undefined, one-empty sets are zero, and both-nonempty summaries are reported separately. Within-query comparisons match exact query and platform; cross-platform comparisons match exact query and scheduled repeat label. Delayed recoveries are not represented as chronologically simultaneous captures.

Inspect a fixed first-reference source sample

The qualitative sample uses the first plan-ordered selection wording, scheduled wave 1, then the first declared normalized citation. A same-input recovery of a temporary failure may fill that original slot later; the source ledger flags recovery and actual timestamps. No-answer, no-source and unresolved-error slots remain explicit. Dated source-page evidence supports only what was actually visible on that page.

The URL classifier was corrected before publication after independent QA caught a generic dentist-prefix collision and nested treatment-path precedence. A finite set of observed directory hosts was added to the published codebook. All source-type counts were recomputed from the same saved references.

The public data omit full AI answers, API identifiers, credentials and private ClinicTruth project information. They retain prompt cells, observation metrics, citations, pair inputs and review evidence needed to inspect the analysis.