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.

---

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
2. Open 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)
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

[
  {
    "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:

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:

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 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 or contact us through Apify.

---

Complete your GEO analysis with the full suite

Actor	What it does	Start with this if...
✅ GEO Site Audit	Technical AI readiness score	Always start here
📊 GEO Visibility Score	GEO Score, mention rate, citation rate	You want your baseline AI visibility
⚔️ GEO Competitor Research	Share of Voice vs competitors	You know which competitors to track
🔍 GEO Prompt Research	AI keyword research & prompt scoring	You want to find new AI ranking opportunities
💬 GEO Brand Sentiment	How AI models describe your brand	You want to understand AI brand perception