AI Engines

NexGeo.ai monitors your product visibility across 6 AI engines. Each engine has different strengths, biases, and data sources.

Supported Engines

Google AI Overview

google_ai

Google's AI-powered search summaries that appear at the top of search results.

Uses the Gemini API. Requires GOOGLE_GEMINI_API_KEY.

ChatGPT

chatgpt

OpenAI's conversational AI. The most widely used AI assistant for product research.

Uses the OpenAI API. Requires OPENAI_API_KEY.

Perplexity

perplexity

AI-powered answer engine with real-time web search and source citations.

Uses the Perplexity API. Provides native source citations. Requires PERPLEXITY_API_KEY.

Claude

claude

Anthropic's AI assistant, known for nuanced and detailed responses.

Uses the Anthropic API. Requires ANTHROPIC_API_KEY.

Gemini

gemini

Google's multimodal AI with web grounding capabilities.

Uses web grounding for real-time information. Requires GOOGLE_GEMINI_API_KEY.

Meta AI

meta_ai

Meta's AI assistant powered by Llama models.

Uses the Llama API. Requires META_AI_API_KEY.

How Scanning Works

When you run a scan, NexGeo.ai sends product-relevant prompts to each selected engine. For each response, we analyze:

Mention detection — Is the product mentioned by name?
Position — Where in the response does the mention appear?
Sentiment — Is the mention positive, neutral, or negative?
Citations — Does the engine cite a source URL for the product?
Recommendation — Does the engine explicitly recommend the product?
Competitor mentions — Which competing products appear in the same response?

Engine Configuration

Each engine requires its own API key, configured via environment variables. Engines without a valid API key are automatically skipped during scans. See .env.example for the full list of required variables.