Website scam risk detector with GPT-4o and SerpAPI

What It Does This intelligent workflow simplifies the complex task of determining whether a website is legitimate or potentially a scam. By simply submitting a URL through a form, the system initiates a multi-agent evaluation process. Four dedicated AI agents—each powered by GPT-4o and connected to SerpAPI—analyze different dimensions of the website: domain and technical details, search engine signals, product and pricing patterns, and on-site content analysis. Their findings are then passed to a fifth AI agent, the Analyzer, powered by GPT-4o mini, which consolidates the data, scores the site on a scale of 1–10 for scam likelihood, and presents the findings in a clear, structured format for the user.

Who It's For This workflow is ideal for anyone who needs to quickly and reliably assess the trustworthiness of a website. Whether you're a consumer double-checking a store before making a purchase, a small business owner validating supplier sites, a cybersecurity analyst conducting threat assessments, or a developer building fraud detection into your platform — this tool offers fast, AI-powered insights without the need for manual research or technical expertise. It's designed for both individuals and teams who value accurate, scalable scam detection.

How It Works The process begins with a simple form submission where the user enters the URL of the website they want to investigate. Once submitted, the workflow activates four specialized AI agents—each powered by GPT-4o and connected to SerpAPI—to independently analyze the site from different angles:

Agent 1 examines domain age, SSL certificates, and TLD trustworthiness.

Agent 2 reviews search engine results, forum mentions, and public scam reports.

Agent 3 analyzes product pricing patterns and brand authenticity.

Agent 4 assesses on-site content quality, grammar, legitimacy of claims, and presence of business info.

Each agent returns its findings, which are then aggregated and passed to a fifth AI agent—the Analyzer. This final agent, powered by GPT-4o mini, evaluates all the input, assigns a scam likelihood score from 1 to 10, and compiles a neatly formatted summary with organized insights and a disclaimer for context.