Data
The raw records of the Query Fan-Out Observatory, published as versioned CSV and JSON under Creative Commons Attribution 4.0. Each row is one test of one prompt on one platform at one time, with the subqueries the platform displayed, the sources it retrieved and cited, and an evidence class. The method is on the Research page. Use the data freely; cite queryfanout.wiki and the version number.
Batch 1 summary
TESTED Eleven frozen prompts, one per prompt class, run on Perplexity (signed-in free account, Colorado, USA) on 8 September 2026 between 03:08 and 03:20 UTC, which was the evening of 7 September in Colorado, plus two repeat runs of the multifaceted prompt. Twelve rows are OBSERVED: the platform displayed its searches and they were captured as shown. One row (the follow-up turn) is recorded with fanout_observable false because the platform displayed no step panel. Google AI Mode rows are absent from this batch for the reasons on the Measurement page.
| Prompt class | Subqueries shown | Sources retrieved | Domains cited |
|---|---|---|---|
| simple | 1 (the prompt itself) | 9 | 3 |
| ambiguous | 1 (the prompt itself) | 9 | 2 |
| longtail | 3 | 16 | 4 |
| multifaceted (3 runs) | 3, 3, 3 | 15, 15, 15 | 9, 9, 11 |
| comparison | 3 | 15 | 9 |
| commercial | 3, plus 3 page fetches in a second step | 15 | 3 |
| rare | 3 | 15 | 7 |
| fresh | 3 | 23 | 4 |
| local | 3 | 15 | 3 |
| product | 3 | 17 | 6 |
| followup | not displayed | 9 | 4 |
Batch 1 records
Abbreviated view. The CSV and JSON carry every field including timestamps, cited domains, notes and the thread link for each capture.
| id | run | class | prompt | observed subqueries | n | src | class |
|---|---|---|---|---|---|---|---|
| qfo-0001 | 1 | multifaceted | What is the best CRM for a 50-person law firm concerned about security and migration cost | best CRM for law firm 50 employees security · legal CRM migration cost considerations 2025 2026 · top secure CRM platforms for mid-size law firms | 3 | 15 | OBS |
| qfo-0001 | 2 | multifaceted | (same) | best CRM for law firm 50 employees security · legal CRM migration cost considerations · top CRM for mid-size law firms 2025 2026 security compliance | 3 | 15 | OBS |
| qfo-0001 | 3 | multifaceted | (same) | best CRM for law firm 50 employees security · legal CRM migration cost comparison 2025 2026 · law firm CRM security compliance Clio Lawmatics Filevine | 3 | 15 | OBS |
| qfo-0002 | 1 | simple | How tall is the Eiffel Tower | How tall is the Eiffel Tower | 1 | 9 | OBS |
| qfo-0003 | 1 | longtail | How do I stop my sourdough starter from developing a grey liquid layer on top | sourdough starter grey liquid layer on top what is it · how to prevent hooch sourdough starter grey liquid · sourdough starter gray liquid hooch fix | 3 | 16 | OBS |
| qfo-0004 | 1 | comparison | Sony WH-1000XM6 vs Bose QuietComfort Ultra for long flights | Sony WH-1000XM6 vs Bose QuietComfort Ultra long flights · Sony WH-1000XM6 battery life ANC comfort review 2025 2026 · Bose QuietComfort Ultra battery life ANC comfort long flight review | 3 | 15 | OBS |
| qfo-0005 | 1 | commercial | Best standing desk under $400 for a small apartment | best standing desk under $400 2025 2026 · compact standing desk small apartment under $400 · standing desk reviews small space budget | 3 | 15 | OBS |
| qfo-0006 | 1 | ambiguous | jaguar speed | jaguar speed | 1 | 9 | OBS |
| qfo-0007 | 1 | rare | Traditional dairy dishes served at Tsagaan Sar in Uvs province Mongolia | Tsagaan Sar traditional dairy dishes Uvs province Mongolia · Mongolian Tsagaan Sar food dairy products Uvs · traditional Mongolian dairy dishes holiday Tsagaan Sar | 3 | 15 | OBS |
| qfo-0008 | 1 | fresh | What changed in the most recent iOS update | iOS 26.0 update changes features · Apple iOS latest update September 2026 what's new · iOS 26 release notes changes | 3 | 23 | OBS |
| qfo-0009 | 1 | local | Best time to visit Great Sand Dunes National Park to avoid crowds | best time to visit Great Sand Dunes National Park avoid crowds · Great Sand Dunes National Park least crowded months weekdays · Great Sand Dunes National Park crowd patterns seasonal tips | 3 | 15 | OBS |
| qfo-0010 | 1 | product | Is the DJI Mini 5 Pro worth it over the Mini 4 Pro | DJI Mini 5 Pro vs Mini 4 Pro differences specs · DJI Mini 5 Pro worth it over Mini 4 Pro review · DJI Mini 5 Pro release date price features | 3 | 17 | OBS |
| qfo-0011 | 1 | followup | Which one has better battery life (turn 2 of qfo-0004) | not displayed | null | 9 | OBS* |
* Recorded as OBSERVED with fanout_observable false: the observation is that nothing was displayed.
Schema
Columns in the CSV and keys in each JSON record. Lists are pipe-separated in the CSV.
| Field | Type | Meaning |
|---|---|---|
id | string | Stable identifier for the prompt, e.g. qfo-0001. Repeat runs share the id and differ in run. |
run | integer | Run number for repeated prompts, starting at 1. |
prompt | string | Exact prompt text submitted. |
prompt_class | enum | simple, longtail, multifaceted, comparison, commercial, ambiguous, rare, fresh, local, product, followup. |
platform | string | perplexity, google-ai-mode, google-ai-overview, chatgpt-search, and so on. |
timestamp_utc | ISO 8601 | When the test was run, to the minute. |
location | string | Country and region of the tester. |
logged_in | boolean | Whether the session was signed in. |
fanout_observable | boolean | Whether the platform displayed any subqueries for this turn. |
observed_subqueries | list | Subqueries exactly as displayed. Empty when not observable. Direct page fetches are not subqueries and are described in notes instead. |
subquery_count | integer or null | Length of the list above; null when not observable. |
sources_retrieved | integer or null | The number the platform reported consulting (Perplexity's "N sources"). |
sources_cited | integer | Distinct domains attached to the final response as citations. |
cited_domains | list | Those domains, as the platform labelled them. |
repeat_runs | integer | Total runs of this prompt in the batch. |
repeat_consistency | float or null | Share of subqueries identical, word for word, across all runs. 0.33 for qfo-0001 (one of three). |
overlap_with_plain_search | float or null | Share of cited domains also in the top 10 of a plain web search for the prompt. Not computed in batch 1. |
evidence_class | enum | OBSERVED, RECONSTRUCTED, SYNTHETIC. Batch 1 is entirely OBSERVED. |
evidence_file | string | The Perplexity thread the record was captured from. Screenshots will be added under the same field in a later version. |
notes | string | Step labels, second-step fetches, and anything the fields cannot express. |
Versions
- 0.1.0 · 2026-09-08Launch. 13 rows: 11 prompts on Perplexity plus 2 repeat runs. No Google AI Mode rows.
overlap_with_plain_searchnot computed.
Planned for 0.2: ChatGPT search rows for the same eleven prompts; manual AI Mode captures with screenshots (RECONSTRUCTED); plain-search overlap computed for all rows; repeat runs for every prompt.
How to cite
QueryFanout.wiki (2026). Query Fan-Out Observatory: timestamped AI search fan-out tests, version 0.1.0. https://queryfanout.wiki/data/. Licensed CC BY 4.0.
If you use a single record, cite it by id and run. If you reproduce a subquery list, keep the platform and timestamp with it. The whole point of the dataset is that these are observations tied to a moment, not facts about a system.
- Information retrieval
- AI search
- Google AI Mode