Generative Engine Optimization Tool — GEO Recommendations avatar

Generative Engine Optimization Tool — GEO Recommendations

Pricing

from $40.00 / 1,000 prompt x engine checks

Go to Apify Store
Generative Engine Optimization Tool — GEO Recommendations

Generative Engine Optimization Tool — GEO Recommendations

Run a GEO audit across ChatGPT, Claude, Gemini and Perplexity: mentions, position, citations, a 0-100 GEO score and prioritized fixes. USD 0.04-0.05 per check.

Pricing

from $40.00 / 1,000 prompt x engine checks

Rating

0.0

(0)

Developer

Muhammad Afzal

Muhammad Afzal

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

20 days ago

Last modified

Categories

Features

Limited permissions

Share

This generative engine optimization (GEO) tool asks ChatGPT, Claude, Gemini, and Perplexity your buyer questions, measures how each answer mentions, ranks, and cites your brand against named competitors, and turns the results into a 0–100 GEO score, prioritized recommendations, and an HTML report. It is built for SEO and GEO agencies, consultants, and brand teams, and it costs USD 50.001 per 1,000 prompt checks (USD 0.050001 per prompt × engine) on the FREE tier, plus a USD 0.006251 start fee per run.

Free users: maximum 20 results per run.

What does this generative engine optimization tool do?

It runs a GEO audit and hands you an action list in one run. For every prompt × engine it records whether your brand is mentioned, its position among the brands you list, share of voice, sentiment, cited sources, and whether your domain or a competitor's domain is cited. It then compares each pair with the previous run for the same trackingId, scores the results, and writes rule-based recommendations.

Three key-value records come with the dataset:

  • SUMMARY: GEO score, visibility score, average position and share of voice, per-engine stats, top cited domains, and stop_reason.
  • RECOMMENDATIONS: the score breakdown and prioritized items.
  • REPORT: an HTML report with score cards, per-engine breakdowns, citation analysis, and the top recommendations, ready to share with a client.

How do I run a GEO audit of my brand?

Enter your brand and domain, 3–10 real buyer questions, and your direct competitors, then start the run:

{
"brandName": "Notion",
"brandDomain": "notion.so",
"prompts": [
"What is the best note-taking and productivity app?",
"Recommend the top productivity software for teams."
],
"platforms": ["perplexity", "chatgpt", "claude", "gemini"],
"competitorBrands": ["Evernote", "Obsidian", "Coda"],
"competitorDomains": ["evernote.com", "obsidian.md", "coda.io"],
"trackingId": "notion-geo-audit",
"generateHtmlReport": true
}

Each prompt runs on every selected engine, so this input makes 8 checks. With no prompts, four questions are generated from industry; with neither, three questions are generated around your brand name. The Console form starts with one prompt on ChatGPT for a quick, low-cost first run. ChatGPT, Claude, and Gemini answers use live web search by default (up to 3 results); set useWebSearch: false to test the models' built-in knowledge.

What GEO recommendations does it give?

Each recommendation has a category (visibility, citation, sentiment, position, or coverage), a severity (critical, high, medium, or low), a finding with the numbers behind it, a concrete action, an impact note, and the signals that triggered it. Items are sorted by severity. Examples of what triggers them: prompts where an engine leaves you out, a domain that is never cited while competitor domains are, negative sentiment, a low average position, or mentions that dropped since the last run.

Recommendations are generated by fixed rules from the collected metrics, not by an AI model, and cost nothing extra. The impact lines restate this run's measured rates and how far each fix could move the GEO score by its weights; they are not forecasts or industry benchmarks, and a run with only one or two checks can produce "critical" items from a single data point. Use 3 or more prompts on several engines before acting.

The GEO score (geo_opportunity_score, 0–100, higher means stronger visibility) weights visibility rate 25%, citation rate 20%, sentiment 15%, position 20%, and prompt coverage 20%.

What data does each check return?

FieldWhat it tells you
brand, brand_domainThe tracked brand and domain
engine, model_usedperplexity, chatgpt, claude, or gemini, and the neutral label fixed-ai-model (each engine uses one fixed model)
promptThe question asked
mentioned, mention_count, mention_contextWhether and how often the brand appears, and the first mentioning sentence
positionRank by first appearance among your brand and listed competitors
share_of_voiceYour share (0–100) of tracked-brand mentions in the answer
sentimentpositive, neutral, or negative, from a keyword lexicon
competitors_mentionedListed competitors in the answer
cited, brand_cited_url, citations, citation_domainsWhether your domain is cited, the first cited URL on it, all source URLs, and unique cited domains
competitor_domains_citedListed competitor domains among the citations
topic_keywordsFrequent words in the answer, for content-gap ideas
previous_mentioned, previous_position, position_change, visibility_statusComparison with the last run: new, gained, lost, improved, declined, unchanged, absent, or error
error, checked_atFailure reason (or null) and the check time

This row is from a real check that had a previous snapshot (model_used omitted; mention_context and topic_keywords truncated):

{
"brand": "Notion",
"brand_domain": "notion.so",
"engine": "chatgpt",
"prompt": "What is the best note-taking and productivity app?",
"mentioned": true,
"position": 2,
"share_of_voice": 50,
"cited": false,
"citations": [
"https://zapier.com/blog/best-note-taking-apps/",
"https://appstested.com/best-note-taking-apps-2026/",
"https://www.softwareadvice.com/note-taking/"
],
"brand_cited_url": null,
"mention_count": 2,
"mention_context": "...- **Best for productivity, teams, and databases:** **Notion** — combines notes with project tracking, databases, and shared workspaces.",
"sentiment": "positive",
"competitors_mentioned": ["Obsidian"],
"topic_keywords": ["best", "notes", "personal", "obsidian", "ideas"],
"citation_domains": ["appstested.com", "softwareadvice.com", "zapier.com"],
"competitor_domains_cited": [],
"previous_mentioned": true,
"previous_position": 1,
"position_change": -1,
"visibility_status": "declined",
"error": null,
"checked_at": "2026-10-26T07:42:16.510Z"
}

How much does a GEO audit cost?

Pay-per-event prices, active since September 20, 2026, with no change scheduled. Model and web-search costs and Apify platform usage are included.

EventFREEBRONZESILVERGOLDPLATINUMDIAMOND
prompt-engine-check: one successful prompt × engine (primary)$0.050001$0.04875$0.0475$0.04$0.04$0.04
actor-start: run start$0.006251$0.006094$0.005938$0.005$0.005$0.005

This Actor's start event is charged once per run after the input is validated, not per started GB of allocated memory; the default memory is 512 MB. Free users: maximum 20 results per run.

  • Store prefill (1 prompt on ChatGPT), FREE: $0.006251 + $0.050001 = $0.056252.
  • 4 prompts × 4 engines (16 checks), BRONZE: $0.006094 + 16 × $0.04875 = $0.786094.

A check is charged only after its row is saved. Failed checks are saved with an error and not charged, and rejected input is not charged. Set a maximum total charge to cap spend; the Actor stops before a check it could not charge.

When should I use this GEO tool, and when not?

Use it when you want measurement and an action plan in one run, for example a monthly client audit. Choose a sibling Actor otherwise:

It is not a Google rank tracker, site crawler, or backlink index, it does not read the consumer chat apps, and no recommendation can guarantee that a model changes its answers.

Use it from an AI assistant

This GEO tool works from Claude, ChatGPT, Cursor, or any MCP client through Apify's MCP server. Add it as a single tool with https://mcp.apify.com/?tools=muhammadafzal/ai-geo-rec-tracker, then ask, for example: "Run a GEO audit for Notion against Evernote and Obsidian on five buyer questions, and list the three most urgent recommendations."

How do I run it from the API?

JavaScript (apify-client):

import { ApifyClient } from 'apify-client';
const client = new ApifyClient({ token: process.env.APIFY_TOKEN });
const run = await client.actor('muhammadafzal/ai-geo-rec-tracker').call({
brandName: 'Notion',
prompts: ['What is the best workspace tool for startups?'],
competitorBrands: ['Evernote', 'Obsidian'],
});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
const recs = await client.keyValueStore(run.defaultKeyValueStoreId).getRecord('RECOMMENDATIONS');
console.log(items.length, recs?.value.geo_opportunity_score);

Python (apify-client 3.x):

from apify_client import ApifyClient
client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("muhammadafzal/ai-geo-rec-tracker").call(run_input={
"brandName": "Notion",
"prompts": ["What is the best workspace tool for startups?"],
"competitorBrands": ["Evernote", "Obsidian"],
})
for item in client.dataset(run.default_dataset_id).iterate_items():
print(item["engine"], item["mentioned"], item["position"], item["visibility_status"])

Apify schedules, webhooks, and integrations with Make, Zapier, n8n, and Google Sheets can run audits on a cadence with a fixed trackingId.

Limits and reliability

  • Up to 200 prompts per run on four engines.
  • Checks run one at a time; each request times out after 90 seconds without retry. Raise the run timeout above the default 300 seconds for audits of more than about 40 checks.
  • Answers are capped at 700 tokens. Mention detection is case-insensitive text matching, and topic_keywords can include fragments of URLs from the answer.
  • If AI access is rejected for the Actor, the run stops, keeps delivered rows, and says so in its status message.

FAQ

What is generative engine optimization?

Generative engine optimization (GEO) is the work of getting a brand mentioned, recommended, and cited in AI-generated answers. This tool measures where you stand and lists what to fix first.

What is a GEO audit?

A GEO audit checks a fixed set of buyer questions across AI engines and reports visibility, position, citations, and sentiment against competitors. This Actor adds a score, recommendations, and an HTML report.

Are the recommendations written by an AI model?

No. Fixed rules generate them from the collected metrics, at no extra charge.

How often should I run it?

Weekly or monthly with the same prompts and trackingId, so trend labels compare like with like.

Why do results differ between runs?

Models sample answers and web results change. Compare repeated runs, not single answers.

Do I need an AI API key?

No. Model access is included in the event price.

The Actor sends your prompts to AI model APIs and analyzes the answers; it does not access private accounts. Use it for lawful research, keep personal data out of prompts, and do not promise clients guaranteed AI placement.

Last verified: 2026-10-27