Form Inputs
Text Inputs
Fill any text field, search box, or textarea with context-aware content
Complex Forms
Complete multi-step forms with validation and dynamic fields
Dropdowns & Selects
Navigate dropdown menus and select appropriate options
Date & Time Pickers
Select dates, times, and navigate calendar interfaces seamlessly
Interactive Elements
Buttons & CTAs
Click buttons, submit forms, and trigger any interactive elements
Modal & Popups
Handle modal dialogs, popups, and overlay interactions
Tables & Data Grids
Extract and interact with complex table structures and data grids
Video & Media Players
Control playback and interact with embedded media
PDF Documents
Read, analyze, and extract data directly from embedded or linked PDF files
Authentication & Security
Authentication & OTP
Enter one-time passwords and complete two-factor authentication
CAPTCHAs
Solve image challenges, reCAPTCHAs, and verification systems
File Transfers
File Downloads
Download files from any website—documents, reports, images, CSVs, and more
File Uploads
Upload files to other websites and platforms, completing end-to-end file transfer workflows
Dynamic Content
Dynamic Content
React to AJAX updates, infinite scroll, and real-time changes
IFrames
Navigate and interact with embedded iframe content seamlessly
Why This Matters
Traditional automation tools like Playwright or Puppeteer require you to write explicit selectors for every element. When websites change their HTML structure, your scripts break. WebRun’s AI agent understands the visual and semantic context of web pages. It identifies elements by their purpose, not their code—so your automations keep working even when websites update their design. Example: Instead of writingdocument.querySelector('.btn-primary-v2'), you simply tell WebRun: “Click the submit button.”