# \[DEPRECATED] GEO Prompt Research - AI Keyword Research (`dltik/geo-prompt-research`) Actor

Generate and score AI prompts from seed keywords. The AI equivalent of keyword research. Get difficulty score (how competitive), opportunity score (how underserved), intent classification, and brand presence check for hundreds of prompts.

- **URL**: https://apify.com/dltik/geo-prompt-research.md
- **Developed by:** [Walid](https://apify.com/dltik) (community)
- **Categories:** SEO tools, Marketing, AI
- **Features:** Limited permissions
- **Stats:** 18 total users, 0 monthly users, 100.0% runs succeeded, 4 bookmarks
- **User rating**: No ratings yet

## Pricing

from $30.00 / 1,000 prompt researcheds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
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.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## 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.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

## GEO Prompt Research — AI Keyword Research

**GEO Prompt Research** is the AI equivalent of keyword research — but for generative engines. Give it seed keywords, and it generates hundreds of realistic AI prompts, then scores each one by **difficulty** (how competitive it is), **opportunity** (how underserved it is), and whether your brand already appears. Find the exact prompts where you can win AI visibility today.

The same insight as Semrush Keyword Magic Tool, but for ChatGPT, Claude, and Perplexity.

> ⭐ **Found this useful?** Click the **Bookmark** button at the top of [this page](https://apify.com/dltik/geo-prompt-research) — it helps the scraper stay visible to others who need it. Takes 1 click. No signup beyond your existing Apify account.

***

### What can GEO Prompt Research do with your keywords?

- 🔍 **Prompt generation** — transforms seed keywords into realistic questions users send to AI assistants (discovery, comparison, how-to, review, alternative intents)
- 📊 **Difficulty score** — how competitive is this prompt? (0–100, higher = harder to rank)
- 💎 **Opportunity score** — how underserved is this prompt? (0–100, higher = more room to grow)
- 🎯 **Combined score** — single metric to prioritize: `opportunity × 0.6 + (100 - difficulty) × 0.4`
- 🏷️ **Intent classification** — discovery / recommendation / comparison / review / how-to / alternative
- 🤖 **Brand presence check** — is your brand already mentioned when AI answers this prompt?
- 🏢 **Competitor mentions** — which brands currently dominate this prompt

***

### What data does GEO Prompt Research extract?

| Field | Description |
|-------|-------------|
| `prompt` | The full AI prompt text |
| `seed_keyword` | Source keyword that generated this prompt |
| `intent` | `discovery` / `recommendation` / `comparison` / `review` / `how_to` / `alternative` |
| `difficulty` | Competition level 0–100 (based on how many brands are mentioned) |
| `opportunity` | Underserved space 0–100 (inverse of difficulty + brand coverage) |
| `combined_score` | Prioritization score: `opportunity × 0.6 + (100 - difficulty) × 0.4` |
| `brand_present` | `true` / `false` — is your brand mentioned? |
| `brands_mentioned` | Brands currently dominating this prompt |

***

### How to find high-opportunity AI prompts for your industry

1. **[Create a free Apify account](https://apify.com/sign-up)**
2. **Open [GEO Prompt Research](https://apify.com/dltik/geo-prompt-research)** in Apify Store
3. **Enter your industry and seed keywords** (e.g. `SaaS tools`, `["project management", "team collaboration"]`)
4. **Add your brand name** (optional, but enables brand presence detection)
5. **Add your OpenRouter API key** (get one at [openrouter.ai/keys](https://openrouter.ai/keys))
6. **Click Start** — generates and scores all prompts in 1–2 minutes
7. **Sort by `combined_score` descending** — your best opportunities are at the top
8. **Download in CSV or Excel** to plan your content calendar

***

### How much does AI keyword research cost?

**$0.03 per prompt researched** via Apify Pay-Per-Event. Plus your own OpenRouter API usage.

| Run size | Prompts generated | Apify cost | OpenRouter cost |
|----------|-------------------|------------|----------------|
| Quick test (3 seeds, 5 prompts each) | 15 | ~$0.45 | ~$0.02 |
| Standard (5 seeds, 10 prompts each) | 50 | ~$1.50 | ~$0.05 |
| Full research (10 seeds, 10 prompts each) | 100 | ~$3.00 | ~$0.10 |

> For $3, you can research 100 AI prompts across 10 seed keywords — the equivalent of hours of manual research.

***

### Input

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `industry` | string | ✅ | — | Your industry (e.g. `SaaS project management tools`) |
| `seedKeywords` | array | ✅ | — | Seed keywords (e.g. `["project management", "team wiki", "task tracking"]`) |
| `brand` | string | ❌ | — | Your brand name — enables brand presence detection |
| `domain` | string | ❌ | — | Your domain — used for citation detection |
| `promptsPerSeed` | integer | ❌ | `10` | Prompts to generate per seed keyword |
| `country` | string | ❌ | `US` | Country context |
| `language` | string | ❌ | `en` | Language |
| `openrouterApiKey` | string | ❌ | env var | Your OpenRouter API key |
| `perplexityApiKey` | string | ❌ | env var | Your Perplexity API key |

***

### Output example

```json
[
  {
    "prompt": "Best no-code project management tool for small teams",
    "seed_keyword": "project management",
    "intent": "recommendation",
    "difficulty": 35,
    "opportunity": 78,
    "combined_score": 61,
    "brand_present": false,
    "brands_mentioned": ["Trello", "Asana"]
  },
  {
    "prompt": "What is the best tool to manage a remote team wiki?",
    "seed_keyword": "team wiki",
    "intent": "discovery",
    "difficulty": 22,
    "opportunity": 85,
    "combined_score": 60,
    "brand_present": true,
    "brands_mentioned": ["Notion", "Confluence"]
  },
  {
    "prompt": "Notion alternatives for non-technical users",
    "seed_keyword": "project management",
    "intent": "alternative",
    "difficulty": 68,
    "opportunity": 42,
    "combined_score": 30,
    "brand_present": false,
    "brands_mentioned": ["Coda", "Airtable", "ClickUp"]
  }
]
```

***

### Use GEO Prompt Research via API

Automate AI keyword research for multiple clients, build content calendars programmatically, or trigger research after publishing new pages.

**Python:**

```python
import requests

run = requests.post(
    "https://api.apify.com/v2/acts/dltik~geo-prompt-research/runs",
    headers={"Authorization": "Bearer YOUR_APIFY_TOKEN"},
    json={
        "industry": "SaaS project management",
        "seedKeywords": ["project management", "team wiki", "task tracking"],
        "brand": "Notion",
        "promptsPerSeed": 10,
        "openrouterApiKey": "YOUR_OPENROUTER_KEY"
    }
).json()

print(run["data"]["id"])
```

**curl:**

```bash
curl -X POST "https://api.apify.com/v2/acts/dltik~geo-prompt-research/runs" \
  -H "Authorization: Bearer YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "industry": "SaaS project management",
    "seedKeywords": ["project management", "team wiki"],
    "brand": "Notion",
    "openrouterApiKey": "YOUR_KEY"
  }'
```

***

### How to use the combined_score to prioritize content

The **combined score** formula is: `opportunity × 0.6 + (100 - difficulty) × 0.4`

- **Score 70–100** → Quick wins — easy to rank, high demand. Create this content first.
- **Score 50–69** → Medium priority — competitive but doable. Great for next sprint.
- **Score 0–49** → Long-term plays — highly competitive. Come back after you've built authority.

Sort your results by `combined_score` descending, filter for `brand_present: false`, and you have your AI content roadmap.

***

### FAQ

**How is GEO Prompt Research different from traditional keyword research?**
Traditional SEO keyword research (Google Keyword Planner, Semrush) tells you how many people search on Google. GEO Prompt Research tells you what people ask AI assistants — which is increasingly where buying decisions are made. These prompts are longer, more conversational, and often different from Google queries.

**What's a "good" opportunity score?**
Opportunity 70+ means few established brands dominate this prompt — you have real room to grow. Opportunity below 40 means the prompt is saturated with well-known brands; ranking there requires significant authority.

**My brand has `brand_present: false` on high-score prompts. What should I do?**
These are your best opportunities. Create a dedicated page or blog post that directly answers the prompt — AI models surface content that directly matches the user's question. Then use [GEO Visibility Score](https://apify.com/dltik/geo-visibility-score) in 2–4 weeks to measure improvement.

**Can I research prompts in languages other than English?**
Yes. Set the `language` parameter to your target language (e.g. `fr`, `de`, `es`). The prompts and scoring will adapt.

**How often should I run GEO Prompt Research?**
Quarterly is a good starting cadence — AI model behavior shifts as they're updated. After major product launches or industry events, run it again to capture new prompt patterns.

**I want to research a very specific niche. How granular should `industry` be?**
Be specific: `"B2B SaaS project management for construction"` gives better prompts than `"software"`. The more context you give, the more targeted and useful the generated prompts.

**I need help or a custom solution.**
Open an issue on the [Issues tab](https://apify.com/dltik/geo-prompt-research/issues) or contact us through Apify.

***

⭐ **Found GEO Prompt Research useful? Bookmark it** — Apify ranks actors by bookmarks, so it's the strongest signal for Store visibility. One click = directly helps this actor stay surfaced for new users.

***

### Complete your GEO analysis with the full suite

| Actor | What it does | Start with this if... |
|-------|-------------|----------------------|
| ✅ [GEO Site Audit](https://apify.com/dltik/geo-site-audit) | Technical AI readiness score | **Always start here** |
| 📊 [GEO Visibility Score](https://apify.com/dltik/geo-visibility-score) | GEO Score, mention rate, citation rate | You want your baseline AI visibility |
| ⚔️ [GEO Competitor Research](https://apify.com/dltik/geo-competitor-research) | Share of Voice vs competitors | You know which competitors to track |
| 🔍 [GEO Prompt Research](https://apify.com/dltik/geo-prompt-research) | AI keyword research & prompt scoring | You want to find new AI ranking opportunities |
| 💬 [GEO Brand Sentiment](https://apify.com/dltik/geo-brand-sentiment) | How AI models describe your brand | You want to understand AI brand perception |

# Actor input Schema

## `industry` (type: `string`):

Your industry (e.g. 'real estate tech', 'project management SaaS')

## `seedKeywords` (type: `array`):

Starting keywords to generate prompts from

## `brand` (type: `string`):

To check your presence in each prompt result

## `domain` (type: `string`):

Your domain to track citation presence (e.g. apify.com)

## `country` (type: `string`):

Target country for prompts (e.g. US, FR, DE)

## `language` (type: `string`):

Language for generated prompts (e.g. en, fr)

## `promptsPerSeed` (type: `integer`):

Number of prompt variants generated per seed keyword

## `llmsToTest` (type: `array`):

2 LLMs recommended for prompt research (speed/cost tradeoff)

## Actor input object example

```json
{
  "industry": "web scraping and data extraction",
  "seedKeywords": [
    "web scraping",
    "data extraction",
    "web automation"
  ],
  "country": "US",
  "language": "en",
  "promptsPerSeed": 20,
  "llmsToTest": [
    "openai/gpt-4o-mini",
    "google/gemini-2.5-flash"
  ]
}
```

# Actor output Schema

## `results` (type: `string`):

All scored prompts sorted by opportunity score descending.

# 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 '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "industry": "web scraping and data extraction",
    "seedKeywords": [
        "web scraping",
        "data extraction",
        "web automation"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("dltik/geo-prompt-research").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 '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = {
    "industry": "web scraping and data extraction",
    "seedKeywords": [
        "web scraping",
        "data extraction",
        "web automation",
    ],
}

# Run the Actor and wait for it to finish
run = client.actor("dltik/geo-prompt-research").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "industry": "web scraping and data extraction",
  "seedKeywords": [
    "web scraping",
    "data extraction",
    "web automation"
  ]
}' |
apify call dltik/geo-prompt-research --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,dltik/geo-prompt-research"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/uM2kOYrfeFEOqjW1i/builds/PuGgLNj9WsZSShrz7/openapi.json