# Data and Downloads | AI SEO Perth > Downloads from the Perth AI search observation programme: the observation schema, versioned methodology, project registry, and published datasets as CSV and JSON. Source: https://aiseoperth.net.au/data/ --- Data # Data and downloads Everything the programme publishes as a file. Datasets appear here only once observations exist. The schema, the methodology and the project registry are published now so the structure of future data is fixed in public before any of it is collected. ## Published datasets Status No datasets published yet No observation round has been completed, so there is no observation dataset to download. The files below define the structure that any future dataset will follow. [Read the methodology](https://aiseoperth.net.au/methodology/) ยท [View the data model](https://aiseoperth.net.au/data/) ## Structure and methodology files Schema ### Observation record schema JSON Schema for one observation: prompt, class, platform, run, session profile, brands mentioned and recommended, citations, source classes, capture and methodology version. - [View JSON Schema](https://aiseoperth.net.au/data/observation-schema.json) Updated 2026-09-09 Methodology ### Methodology v1.0 The observation methodology as data: query classes, platforms, session profiles, recorded fields, source classes, evidence labels, limitations and version history. - [View JSON](https://aiseoperth.net.au/data/methodology.json) - [Read Markdown](https://aiseoperth.net.au/methodology/) Updated 2026-09-09 Methodology ### Research project registry Every research project with its status, platforms, query classes and dataset links. Planned projects carry no dataset. - [View JSON](https://aiseoperth.net.au/data/research-projects.json) Updated 2026-09-09 Example only ### Perth AI search observations: example file Two placeholder rows showing the record structure in both download formats. Every value is a stand-in. Placeholder values that illustrate the structure. Not observations. Do not cite. - [Example CSV](https://aiseoperth.net.au/data/perth-ai-search-observations.example.csv) - [Example JSON](https://aiseoperth.net.au/data/perth-ai-search-observations.example.json) ## What one observation record contains The fields below are the record's schema. Sample rows are deliberately not rendered here: this publication is read by retrieval systems that extract table cells, and a table of realistic-looking observations is worth nothing to a reader while being easy for a machine to mistake for data. The [example file](https://aiseoperth.net.au/data/perth-ai-search-observations.example.json) uses placeholder tokens such as `BRAND_EXAMPLE_A` and `source-one.example.invalid` for the same reason. Observation record fields Field Type Description observation\_id string Stable identifier: ----r. Example: chatgpt-perth-chatgpt-p001-20261001-r01. research\_project string Slug of the research project the observation belongs to (matches the research collection entry). prompt string The exact prompt text submitted, unedited. prompt\_id string Identifier of the prompt within the project's fixed prompt set, so repeated runs of the same prompt can be grouped. query\_class enum informational, commercial, comparison, recommendation, local, brand, competitor, trust-validation buyer\_stage enum awareness, consideration, decision, retention, not-applicable industry string Industry slug from the observatory list (dentists, lawyers, mortgage-brokers, accountants, plumbers, electricians, builders, solar, real-estate, seo-agencies) or 'general'. location string Geographic context named in the prompt or the session, e.g. 'Perth, Western Australia'. platform enum chatgpt, google-ai-overviews, google-ai-mode, gemini, perplexity, claude, copilot model\_or\_surface string The model or surface as the platform labelled it at the time, e.g. 'GPT-5 (web, search on)', 'AI Overview on google.com.au'. observation\_date string observation\_time string Local time of the run, HH:MM. timezone string run\_number integer Sequence of this repeat within the observation round. Repeated runs are how session variance is measured. session\_profile enum Which controlled session the run used. Divergence between profiles on the same prompt is itself a measurement. brands\_mentioned array Every business or brand named anywhere in the response. brands\_recommended array Brands the response presented as a recommendation or shortlist entry, a subset of brands\_mentioned. brand\_order array brands\_recommended in the order the response listed them. citations\_present boolean cited\_urls array cited\_domains array Registrable domains of cited\_urls, deduplicated, lower case. source\_classes array Classification of each cited domain. response\_notes string Free-text notes on the response: format, hedging, refusals, non-Perth results. region\_or\_session\_notes string Anything about location handling, personalisation or logged-in state that could affect the run. source\_capture string Path or URL of the screenshot or raw capture for this run. methodology\_version string Methodology version the run was collected under, e.g. '1.0'. evidence\_type string ## Reuse Published datasets may be quoted and reused with attribution to AI SEO Perth and a link to the report they come from. Observations are dated and versioned; quote the observation dates and methodology version with any figure. Example files must not be quoted as data. Published by Search Scope AI SEO Perth is published by Search Scope, a Perth SEO consultancy founded by Dorian Menard. Search Scope provides commercial SEO and AI search optimisation services; this website is maintained as its specialist Perth AI search research and reference publication. [Search Scope](https://searchscope.com.au/)