Skip to developer documentation
Browse developer documentation
CLI documentation / Reports

AI search

attriboo reports ai-search

Keep crawler activity, referred human visitors and revenue credit separate for each AI engine.

Access: OAuth analytics:read or workspace key

Options

attriboo reports ai-search options
FieldTypeDescription
--sitestringWebsite ID or domain. Required when the workspace has more than one website.
--periodstringUTC date selection. from and to override period.

Values: realtime, today, yesterday, 7d, 30d, 90d, 12m, wtd, mtd, qtd, ytd, all.

Default: 30d.

--fromstringInclusive start date. Supply to as well.
--tostringInclusive end date. Supply from as well.
--comparestringComparison range.

Values: previous_period, mom, qoq, yoy, none.

Default: previous_period.

--modelstringHow recorded sources share revenue credit.

Values: first_touch, last_touch, linear, time_decay.

Default: first_touch.

--filtersstringJSON array string of up to twenty visitor filters, for example [{"dim":"country","op":"is","value":"US"}]. Dimensions: source, channel, campaign, entry_page, page, hostname, country, device, browser, os, goal. Operators: is, is_not. Values are exact strings up to 500 characters. All filters must match the visitor across available history; report dates then select activity for that cohort. Unmatched payments are excluded. Crawler counts remain website-wide; spend requires every filter to be source/channel/campaign. Preserve filters when paging.
--limitintegerMaximum rows where supported.

Default: 50.

--jsonbooleanCompact JSON instead of formatted JSON.
--csvbooleanCSV for the main row collection; nested values remain JSON cells. Cannot be combined with --json.

Read ai search

Replace example websites, dates and cursor values with your own. Running these commands makes real requests or changes the local session.

Terminal command
attriboo reports ai-search --site shop.example.com --from 2026-10-01 --to 2026-10-07 --compare none --json

Example output

Illustrative stdout
{"site":{"id":"site_example","domain":"shop.example.com","currency":"USD"},"period":{"from":"2026-10-01T00:00:00.000Z","to":"2026-10-08T00:00:00.000Z","label":"Custom","compare":"none","attribution_model":"first_touch"},"engines":[{"engine":"ChatGPT","bot_crawls":20,"visitors":10,"attributed_buyers":1,"attributed_revenue":5000,"conversion_rate":10,"revenue_per_visitor":500,"top_page":"/pricing"}]}

Output fields

attriboo reports ai-search output fields
FieldTypeDescription
siteobjectWebsite ID, domain and currency.
periodobjectResolved UTC boundaries; to is the exclusive timestamp after the selected end date.
enginesarrayReport records. See the fields below.
coverageobjectWhen provided, describes completeness, snapshot time and row coverage. Row limits apply to this page, not to headline totals.

site fields

site nested fields
FieldTypeDescription
idstringWebsite ID.
domainstringWebsite domain.
currencystringThree-letter currency.

period fields

period nested fields
FieldTypeDescription
fromstringInclusive UTC start.
tostringExclusive UTC end.
labelstringHuman-readable date selection.
comparestringComparison selection.
attribution_modelstringRevenue-credit model.

engines[] fields

engines nested fields
FieldTypeDescription
enginestringChatGPT, Perplexity, Claude, Gemini or Copilot.
bot_crawlsintegerCrawler requests.
visitorsintegerReferred human visitors.
attributed_buyersnumberAttributed conversion credit; can be fractional.
attributed_revenueintegerAttributed revenue in cents.
conversion_ratenumberAttributed buyers divided by visitors, percent.
revenue_per_visitorintegerCents per referred visitor.
top_pagestring | nullLeading page or null.

The data follows the ai search API contract. CLI JSON omits the REST envelope.

Behavior and limits

Money is integer cents in site.currency. Percentages use a 0–100 scale.

Examples show one engine for brevity. Actual reports include the supported engines.

Crawls do not prove citations or visits. Never call crawls divided by visitors a conversion rate.

CLI JSON output is the API data object directly, without the REST status/data envelope. Default output is formatted JSON; --json is compact JSON.

CSV contains only the returned page's main row collection. Continue using returned next_cursor values rather than assuming a single CSV is a complete export.