# AI Answer Monitor — Is Your Brand in AI Answers? (`gangary/ai-answer-monitor`) Actor GEO / AI-SEO tracking: give a brand and a list of questions, and see whether AI answer engines (Perplexity, Gemini) mention your brand, how prominently, and whether they cite your site. The new search-visibility metric for the AI era. No login. - **URL**: https://apify.com/gangary/ai-answer-monitor.md - **Developed by:** [Gangary](https://apify.com/gangary) (community) - **Categories:** SEO tools, AI - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks - **User rating**: No ratings yet ## Pricing Pay per usage This Actor is paid per platform usage. The Actor is free to use, and you only pay for the Apify platform usage, which gets cheaper the higher subscription plan you have. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-usage ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js/docs.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python/docs.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## AI Answer Monitor — Is Your Brand in AI Answers? When your customers ask an AI ("best digital bank in Brazil", "top marketing agency for clinics"), **does your brand come up?** This Actor asks a real AI answer engine your questions and tells you, for each one, whether your brand is **mentioned**, how **prominently**, and whether your site is **cited as a source**. It's the search-visibility metric for the AI era — GEO / AI-SEO. No login. ![Cover](https://empresas-por-cnae.vercel.app/covers/ai-answer-monitor.png) Em português: *monitor de GEO / AI-SEO, minha marca aparece no ChatGPT/Perplexity/Gemini, visibilidade de marca em respostas de IA*. ### Input example ```json { "brand": "Nubank", "domain": "nubank.com.br", "questions": [ "melhor banco digital do Brasil", "qual conta digital sem tarifa vale a pena" ], "engine": "gemini" } ```` - `brand` — the brand to look for in the answers. - `domain` (optional) — your site, used to detect if the AI **cites you as a source**. - `questions` — the questions your buyers would ask an AI (up to 100). - `engine` — `perplexity` (cites sources) or `gemini` (Google Search grounding). ### Output example One row per question: ```json { "brand": "Nubank", "engine": "perplexity", "question": "melhor banco digital do Brasil", "checked": true, "mentioned": true, "mention_count": 4, "prominence": "top", "cited": false, "answer_excerpt": "Os mais citados no Brasil costumam ser Nubank, Inter e ...", "citations": [] } ``` - `mentioned` / `mention_count` — is the brand in the answer, and how many times. - `prominence` — `top` / `mid` / `low`: where the first mention falls in the answer (top = named first = most visible). - `cited` — the brand's `domain` appears among the answer's sources. - `answer_excerpt` + `citations` — the raw evidence, so you can read exactly why. ### What you learn - **Which questions you already win** (brand named, `top` prominence) — protect and amplify these. - **Which questions you're invisible on** (`mentioned: false`) — your GEO gap, where competitors are getting the AI's recommendation instead of you. - **Whether the AI trusts your site** as a source (`cited`). Run it weekly to watch your AI visibility move as you publish content. ### Pricing (Pay per event) | Event | When | Price | |---|---|---| | `actor-start` | once per run | $0.01 | | `question-checked` | per question successfully asked to the AI | $0.10 | Monitoring 20 questions = $0.01 + 20 × $0.10 = **$2.01**. A question whose engine is temporarily unavailable is returned with a note and **not charged**. ### Engines - **Perplexity (`sonar`)** — fast, web-grounded answers. Strong for the mention/prominence signal. - **Gemini (Google Search grounding)** — answers grounded in Google Search, and returns the **source links**, so the `cited` signal is richest here. Also the closest proxy to what Google's AI surfaces to users. `mentioned` and `prominence` work on both engines. `cited` depends on the engine returning source links (always on Gemini; Perplexity's base model may omit them). ### Is this compliant? Yes — the Actor sends your questions to a public AI API and analyzes the text of the answer. No scraping, no login, no private data. ### Limitations - AI answers are **non-deterministic** — the same question can vary run to run. For a trend, run the same set weekly and watch the direction, not a single snapshot. - `mentioned` is a text match on the brand name — a very generic brand name can over- or under-count (use a distinctive name or brand form). - Coverage and citation richness depend on the chosen engine (see above). ### From the same maker - **[B2B Leads Brazil](https://apify.com/gangary/b2b-leads-brazil)** · **[CNPJ Discovery](https://apify.com/gangary/cnpj-discovery)** — build and score the company lists behind your outreach. # Actor input Schema ## `brand` (type: `string`): Nome da marca a monitorar nas respostas (ex: 'Runrun.it', 'Nubank'). ## `domain` (type: `string`): Dominio da marca (ex: nubank.com.br). Usado pra detectar se a IA CITA seu site como fonte. ## `questions` (type: `array`): Perguntas que seus clientes fariam a uma IA (ex: 'melhor banco digital do Brasil'). Ate 100 por execucao. ## `engine` (type: `string`): Qual motor de IA consultar. Gemini (busca do Google, gratis) ou Perplexity. ## `maxQuestions` (type: `integer`): Teto de perguntas processadas (teto duro 100). ## Actor input object example ```json { "brand": "Nubank", "questions": [ "melhor banco digital do Brasil", "qual conta digital sem tarifa vale a pena" ], "engine": "gemini", "maxQuestions": 100 } ``` # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "brand": "Nubank", "questions": [ "melhor banco digital do Brasil", "qual conta digital sem tarifa vale a pena" ] }; // Run the Actor and wait for it to finish const run = await client.actor("gangary/ai-answer-monitor").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "brand": "Nubank", "questions": [ "melhor banco digital do Brasil", "qual conta digital sem tarifa vale a pena", ], } # Run the Actor and wait for it to finish run = client.actor("gangary/ai-answer-monitor").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "brand": "Nubank", "questions": [ "melhor banco digital do Brasil", "qual conta digital sem tarifa vale a pena" ] }' | apify call gangary/ai-answer-monitor --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=gangary/ai-answer-monitor", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "AI Answer Monitor — Is Your Brand in AI Answers?", "description": "GEO / AI-SEO tracking: give a brand and a list of questions, and see whether AI answer engines (Perplexity, Gemini) mention your brand, how prominently, and whether they cite your site. The new search-visibility metric for the AI era. No login.", "version": "0.1", "x-build-id": "BPMZdwCc7yvj182Gc" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gangary~ai-answer-monitor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gangary-ai-answer-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/gangary~ai-answer-monitor/runs": { "post": { "operationId": "runs-sync-gangary-ai-answer-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/gangary~ai-answer-monitor/run-sync": { "post": { "operationId": "run-sync-gangary-ai-answer-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "brand", "questions" ], "properties": { "brand": { "title": "Brand to track", "type": "string", "description": "Nome da marca a monitorar nas respostas (ex: 'Runrun.it', 'Nubank')." }, "domain": { "title": "Brand domain (optional)", "type": "string", "description": "Dominio da marca (ex: nubank.com.br). Usado pra detectar se a IA CITA seu site como fonte." }, "questions": { "title": "Questions to ask the AI", "type": "array", "description": "Perguntas que seus clientes fariam a uma IA (ex: 'melhor banco digital do Brasil'). Ate 100 por execucao.", "items": { "type": "string" } }, "engine": { "title": "AI engine", "enum": [ "gemini", "perplexity" ], "type": "string", "description": "Qual motor de IA consultar. Gemini (busca do Google, gratis) ou Perplexity.", "default": "gemini" }, "maxQuestions": { "title": "Max questions", "minimum": 1, "maximum": 100, "type": "integer", "description": "Teto de perguntas processadas (teto duro 100).", "default": 100 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } } ```