Expand Fetch, from Tim Suchanek's Expand, reads rendered web pages and returns underlying data as clean JSON, Elvis Saravia writes. Flattening pages to text can drop details such as a small ✗ in a pricing table, leading agents to answer incorrectly.
Expand says its agents answered 74% of 1,094 questions across 326 pages correctly, versus 55% for the next best API, at $1 per 1,000 fetches.
Another great application of System One models.
I think much of what we call hallucination in web agents comes from misreading the page.
When a page is flattened to text, a small ✗ in a pricing table disappears, and the agent answers incorrectly with full confidence.
Expand Fetch reads the rendered page, returns the underlying data as clean JSON, and keeps a replay of exactly what your agent saw.
Introducing Expand Fetch, a new way to scrape and crawl the web. Your agent has never seen the web. No wonder it gets basic questions wrong. Traditional Markdown APIs lose critical details. So we trained two System one models to change that: Iris, a vision model that sees pages like you do, preserving tables, icons, and layouts. X-Ray, a JSON model that uncovers the hidden data behind every page. Every fetch also comes with a Wayback Machine. Every line links back to its source, so you can verify exactly what your agent saw. Three products. One API. On our benchmark of 1,094 questions across 326 challenging web pages, agents using Expand got 74% right. The next best API got 55%. Available today at $1 per 1,000 fetches. Try it at http://expand.ai
Source: elvis · x.comPublished · added here
