Ask up to 25 prompts of AI answer engines and measure each tracked domain (the brand's and its competitors') two ways: URL cited among the answer's sources, and brand named in the answer. Saved as an audit.
Billing: 5–12¢ per engine check, one per answered prompt × engine — Perplexity 5¢, ChatGPT 7¢, Google AI Overviews 9¢, Gemini 12¢ (33¢ per prompt on the four default engines), Google AI Mode 10¢ when requested. Then the fix-it playbook unless playbook: false — about 12¢ (LLM usage) per answered check that didn't cite the brand, plus about 45¢ for a rollup ranking the fixes when two or more questions were lost; without it get_fix_plan can't plan from the audit. E.g. 10 prompts on the default engines: 330¢ of checks plus about 525¢ of playbook if no answer cites the brand. charged_cents is what the run billed.
Limits: the engines get about 4 minutes; unfinished checks are skipped, unbilled (partial, timed_out) — split runs past ~15 prompts.
Inputs: brand, domain (as in check_brand_citation); competitor_domains — up to 20, empty = the site's list; prompts — 1–25; engines — optional, default the four core ones; playbook — optional, default true.
Returns { audit_id, report_url, tracked: [{domain, is_brand, cite_count, share_pct, mention_count, mention_share_pct}], total_cites, total_mentions, sample: {answered_checks, prompts, confidence, note}, suggested_competitor_domains, suggested_sources: [{domain, cells, kind}], completed, total, partial, timed_out, out_of_credits, charged_cents, charged_breakdown_cents }. share_pct: share of tracked citations; mention_share_pct: of tracked mentions. Relay sample.note with them (confidence low = a handful of answers). suggested_competitor_domains: untracked hosts that won lost answers and that the answers name (confirm before add_site); suggested_sources: directories and publishers cited there, mention targets. Give the user report_url (public). Past ~45 s it returns { audit_id, status: "running", next_step }; read it later with get_audit (free).
