Results for “forced-browsing”

Searches the internet via BrowserAct API when direct web access is restricted, extracting and structuring research data from multiple sources.

Builds reliable browser automation skills through iterative experimentation, running an inner agent to browse sites and improving navigation instructions until tasks pass consistently.

Search the web, extract URL content, enrich datasets with web-sourced fields, and run deep research reports, prioritizing academic and scientific sources.

Answers factual questions by searching the web, fetching primary sources, and cross-checking claims before citing them.

Builds reliable browser automation skills by iteratively running a browsing task, reading the trace, and improving the navigation strategy until it passes consistently.

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.

Performs AI-powered web searches with real-time information using Perplexity models via LiteLLM and OpenRouter, providing grounded answers with source citations.