From the first check to a defensible result.
A practical guide to the live workflow, with explicit definitions for the numbers you see.
1. Run a website readiness audit
Enter a public HTTPS URL, your brand and industry, and a country/language scope. You may include up to two more pages on the same origin. Each page has its own findings. The main readiness score always belongs to the primary URL.
Inspect the evidence beside each finding. A readiness score checks HTML signals and robots.txt rules; it does not query ChatGPT or prove that a crawler visited your site.
2. Save questions and observed answers
Use the prompt workspace to save questions with brand, engine, country and language. In Evidence Lab, enter the question and an answer you actually observed, along with the observation time and any share URL. Keep the original answer and source links intact.
Suggested prompts are editorial templates. They are not query-volume data or a transcript of real customer searches. Submitting evidence records what the collector supplied; HowAICite does not certify the authenticity of a pasted answer.
Metric dictionary · evidence-2.0
| Metric | Definition | Boundary |
|---|---|---|
| Readiness score | Passed checks / known checks × 100. | Ten equally weighted diagnostic checks. Unknown checks excluded. |
| Brand mention | The tracked name appears as a literal name in the answer, excluding URL text. | Aliases and ambiguous names require review; a mention is not a recommendation. |
| Own-domain source | A provider-reported citation URL belongs to the brand's domain or its subdomains. Submitted evidence has a separate link basis. | Retrieved search results and prose-only URLs do not count as provider citations. A source link does not prove endorsement or support for every claim. |
| Recommendation rate | Human-reviewed positive selections / eligible reviewed answers. | A research measure; not automatically inferred from mention counts. |
| Source frequency | Distinct observed answers linking to a source domain. | Repeated links in one answer count once; submitted samples are not market share. |
| Comparison scope | Question, brand/domain, engine/surface, model, parser version, citation basis, country, region, city and language. | Different models or measurement methods are not presented as directly comparable gains or losses. |
| Coverage | Successful collected answers / planned collection cells. | Failures and missing answers must remain visible. |
Preserve the observation, not just the score
Retain exact prompt text, brand, source URLs, answer, platform, model when exposed, requested market, location provenance, language, collection method and timestamp. OpenAI API runs and ChatGPT consumer searches belong to different cohorts. Model names may be unknown for consumer interfaces; record that explicitly.
Private workspace records stay private. The public research pages use their own explicitly published files. Opting into a future aggregate benchmark does not authorize publishing a customer's raw answer or brand.
Automated runs and missing data
Live means a connector has a server credential, a model setting and operator activation after a controlled request. A live connector can still fail later because of credit, authentication, rate limits or provider availability; every attempt retains its own state. Incomplete and missing-provenance answers are excluded from successful observations, not counted as zero brand visibility.
Open a completed run to inspect its exact evidence. Perplexity retrieved search-context URLs remain separate from its reported citation URLs. The presence of a cited domain without a visible brand-name mention has its own outcome; none of these signals alone establishes a positive recommendation.
Exports and account access
Reports export as JSON or a browser print/PDF. Citation insights and the intelligence ledger provide CSV exports from the workspace. Account data can be exported from account settings. Store your one-time recovery code securely; email resets are not available.
Paid organization owners and admins can create expiring, single-use invitation links and assign admin, contributor, reviewer or viewer roles across all three HowAI products. Links reserve a seat while active, are stored as hashes and can be revoked. Email delivery, SSO and SCIM are not included in the standard workspace.
Workspace endpoints require an authorized session. General-purpose public API keys are not included in standard plans. The separately authorized HowAICite Agent MCP interface exposes a narrow set of evidence and internal-action tools governed by workspace role, OAuth scope, quota and Agent policy.
Diagnose an empty report
- No saved observations: record an answer before expecting source trends.
- Provider not active: check coverage; audits remain available.
- No citation found: inspect the raw answer. No linked URL does not imply the brand was not recommended.
- Changed market: compare only matching scopes and keep the original observation.
- Too few samples: report counts and limitations; collect more before making a trend claim.
Find the first gap worth fixing.
Inspect your website now, then add observed AI answers when you are ready to measure visibility.