Faster, reliable web and PDF intelligence with built-in search and extraction

We introduced ParallelTools with Search and Extract APIs to deliver LLM-ready excerpts and robust markdown from the open web and PDFs — including JS-heavy pages. This removes the need for custom scrapers, accelerates onboarding, and improves the reliability of downstream RAG and automation workflows.

Details

Handles JavaScript-rendered sites and PDFs, returning clean, structured markdown
Produces concise, citation-friendly excerpts optimized for LLM consumption
Reduces integration and maintenance risk by eliminating bespoke scraping infrastructure
Fully opt-in with no changes required to existing workflows

Who this is for: Teams building research agents, RAG pipelines, due diligence, or monitoring workflows that depend on high-quality external content.