Tell your AI what to do

You don't write code to use Scout. Just tell your AI what you need, in Cursor, Claude, VS Code, or any agent client.

Data Extraction

“Go to techcrunch.com and extract the top 5 headlines with their URLs as JSON”

Form Filling

“Navigate to the signup page, fill in the form with test data, and submit it”

Visual Testing

“Take screenshots of our landing page at mobile, tablet, and desktop sizes”

Debugging

“Open staging.example.com and report any console errors or failed network requests”

Research

“Crawl our docs site and list every page that mentions "rate limiting"”

Multi-step Workflow

“Log into the dashboard, navigate to billing, and download the latest invoice as PDF”

Monitoring

“Check if the hero banner on our homepage is rendering correctly in both light and dark mode”

Competitive Analysis

“Go to three competitor pricing pages and extract their plan names, prices, and feature lists”

Examples

Code examples

Real-world automation patterns using Scout's MCP tools. Copy these directly into your agent code.

extract-data.tsTYPESCRIPT
// Extract product listings from an e-commerce page
await client.callTool({
  name: "browser-navigate",
  arguments: { action: "goto", url: "https://store.example.com/products", sessionRef },
});

// Extract article content (uses Defuddle)
const article = await client.callTool({
  name: "browser-extract",
  arguments: { property: "article", sessionRef },
});
// → { title: "...", content: "...", excerpt: "..." }

// Extract text from a specific element
const text = await client.callTool({
  name: "browser-extract",
  arguments: { property: "text", selector: ".product-list", sessionRef },
});

Scout uses analytics to understand which pages are useful and where visitors drop off.

See our Privacy Policy and Terms of Service for details.