Check a brand’s visibility in web-grounded AI answers

This Actor checks a brand against a bounded set of prompts using the official OpenAI Responses API with its web-search tool. Each dataset item is one completed prompt: it records whether the answer mentions your brand or an accepted alias, whether the returned citations include your domain, the short mention context, citation URLs, model route, and timestamp. It is designed for repeatable API-based visibility sampling. Pair it with a dedicated SERP tracker for rank positions and a separate consumer-research workflow when those are the decision need.

Best fit for this Actor

• Growth and content teams that need an evidence record for a small, repeatable set of category, alternative, or recommendation prompts.
• Analysts who need to distinguish an answer-text mention from a citation to the brand’s own domain.
• AI-agent workflows that need bounded input, per-prompt provenance, explicit terminal outcomes, and exportable data.

The Actor uses one OpenAI web-grounded response per completed prompt and records that API route on every row. Use the output as a bounded, timestamped sample for the exact prompts supplied.

Focused standalone workflow

This Actor is designed as a focused standalone workflow: give it one brand and a small, stable set of real buyer questions, then use the returned mentions and citations in your own reporting or content-review process. The compact output makes it suitable as a standalone step before broader visibility analysis.

Practical scenario: compare a small prompt set before a content review

Maya runs a three-prompt audit for Ahrefs in the SEO category. The Actor saves one row for each prompt. In the output, Maya can see which answers mentioned Ahrefs, the position of its first answer-text mention, and whether a returned web citation matched ahrefs.com. She exports the rows with their timestamps before her team reviews content and third-party source coverage. A later run can use the same custom prompts for a like-for-like comparison.

Quick start input

{
  "brandName": "Ahrefs",
  "brandDomain": "ahrefs.com",
  "industry": "SEO",
  "queryCategories": ["best_tools", "alternatives", "recommendations"],
  "maxChecks": 3
}

maxChecks is a cost boundary. Custom prompts run first, then the selected built-in prompts, until the unique-prompt cap is reached.

Input reference

What data you receive

One dataset record represents one prompt completed through the OpenAI Responses API. The most important fields are:

• brand_mentioned: whether the returned answer text contained the brand name or an alias.
• mention_position: approximate 1–10 decile for the first mention; a smaller number means earlier in this particular answer.
• brand_domain_cited and brand_citation_url: whether a returned web-search citation matched your configured domain.
• citation_urls: the canonicalized citations returned with that response.
• response_excerpt, model, provenance, and checked_at: enough context to audit what was checked and when.

{
  "query": "What are credible alternatives to Ahrefs for SEO?",
  "brand_name": "Ahrefs",
  "brand_mentioned": true,
  "mention_position": 2,
  "brand_domain_cited": true,
  "brand_citation_url": "https://ahrefs.com/blog/seo/",
  "citation_urls": ["https://ahrefs.com/blog/seo/", "https://example.com/review"],
  "model": "gpt-4.1-mini",
  "provenance": "OpenAI Responses API; web_search required for this check.",
  "checked_at": "ISO 8601 UTC timestamp"
}

The default key-value store also contains OUTPUT (stable compact outcome) and RUN_SUMMARY (provider attempts, coverage, charges, warnings, and outcome). Read these records before treating an export as complete.

Use through the Apify API

import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: process.env.APIFY_TOKEN });
const run = await client.actor('khadinakbar/ai-visibility-checker').call({
    brandName: 'Ahrefs',
    brandDomain: 'ahrefs.com',
    industry: 'SEO',
    customPrompts: ['Which SEO tools are best for a content team?'],
    maxChecks: 1,
});

const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items);

Use with AI agents through Apify MCP

Check whether Ahrefs and ahrefs.com appear in one web-grounded answer to “Which SEO tools are best for a content team?” Return the mention flag, first-mention position, matching brand citation URL, all citation URLs, response excerpt, and terminal run outcome.

After calling the Actor, have the agent inspect OUTPUT and RUN_SUMMARY, then read the dataset. Preserve the prompt and checked_at when comparing runs. For current client setup, use Apify MCP.

Pricing

This Actor uses Pay per event plus Apify platform usage. Each completed Prompt checked record is the primary billable event. Open the live Pricing tab for the current event price and use Apify’s maximum-cost control to keep a run within budget.

Best results

• Use exact, decision-relevant prompts that a prospective customer would actually ask. Keep a fixed prompt set for comparisons across time.
• Provide the canonical domain when you need a source-citation signal. A mention and a domain citation answer different questions.
• Read VALID_EMPTY, PARTIAL, UPSTREAM_FAILED, and CONFIG_ERROR as separate terminal states. Each state keeps the evidence record and provider diagnostics clear for the next review step.
• Use an unambiguous brand name or aliases. Generic words can create false-positive text matches.

Builder's note

I designed the output around prompt-level evidence rather than a synthetic overall score. Search-grounded AI answers can change with wording, sources, and time, so keeping the prompt, citations, excerpt, route, and timestamp makes every result reviewable and easier to compare responsibly.

Responsible use

Use public brand names and prompts you are authorized to analyze. Respect applicable law, platform terms, and your organization’s policies. Represent each result as a bounded API sample and substantiate any public comparison with its underlying evidence.