• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
AI
Announcement

Expand Fetch launches a web-scraping API for AI agents

Its launch post says Iris preserves tables and layouts, while X-Ray exposes hidden page data as JSON.

Robert ScobleRS
elvisEL
8 Sources, 1h ago, first seen 1h ago

TLDR

An October 14 announcement introduces Expand Fetch as a scraping and crawling API for AI agents. Its Iris model preserves visual page details; X-Ray exposes hidden data as JSON. The post says each fetch includes line-level source links and a Wayback Machine. On its own benchmark of 1,094 questions across 326 challenging pages, it says agents using Expand got 74% right versus 55% for the next-best API. The listed price was $1 per 1,000 fetches.

Combined views

4.7K

8 Sources, first seen 1h ago

27 likes16 comments18 saves3 reposts

Combined views

4.7K

8 Sources, first seen 1h ago

27 likes16 comments18 saves3 reposts
Image: @TimSuchanek on X

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Featured Source

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

8 Sources

Tim Suchanek@TimSuchanekIntroducing 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.ai1h
alana goyal@alanaagoyalRT @TimSuchanek: Introducing Expand Fetch, a new way to scrape and crawl the web. Your agent has never seen the web. No wonder it gets bas…1h
elvis@omarsar0Another 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.1h
Chubby♨️@kimmonismusAgents are only as good as the page they think they saw. A tiny ✗ in a pricing table means “not included.” Flatten the page to text and it vanishes, and the agent confidently gets it wrong. @TimSuchanek’s Expand Fetch keeps tables and icons intact and saves the page, so you can see exactly what the agent read. Pretty pretty useful! :)1h
Santiago@svpinoOne of the easiest ways to connect your agents to the web: 1. Add Expand's MCP server to your agent 2. Sign in when prompted 3. Ask the agent to use this server when fetching pages Any time your agent fetches a URL, Expand will return Markdown content while preserving its original format. This is huge, especially when you need to process tables, icons, or any layout that matters for understanding the content.1h
Rohan Paul@rohanpaul_aiThis looks like a big step for agents that read the web. Expand, a new AI startup, released Expand Fetch, a tool that lets AI agents read web pages without losing icons, tables and hidden data along the way. On Expand’s own private test, agents using it answered 74% of hard web questions correctly, against 55% for the next best tool. When AI agents read a website today, the page is usually converted to plain text first, and details like a ✗ next to a feature get thrown away, so the agent confidently gives wrong answers. Expand Fetch, uses its own vision model, Iris, to look at the page the way a person does and keep those details intact. Every fetch is also stored as a snapshot whose Markdown lines link back to their source, letting developers trace a wrong answer to what the agent saw.1h
Robert Scoble@ScobleizerHow much of an AI agent’s “reasoning problem” is actually missing information? Expand Fetch preserves tables, icons and layouts, with sources you can check. They report 74% accuracy vs. 55% for the next best API on their benchmark. Builders, this is worth testing.51m
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI

    8 Sources

    Tim Suchanek@TimSuchanekIntroducing 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.ai1h
    alana goyal@alanaagoyalRT @TimSuchanek: Introducing Expand Fetch, a new way to scrape and crawl the web. Your agent has never seen the web. No wonder it gets bas…1h
    elvis@omarsar0Another 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.1h
    Chubby♨️@kimmonismusAgents are only as good as the page they think they saw. A tiny ✗ in a pricing table means “not included.” Flatten the page to text and it vanishes, and the agent confidently gets it wrong. @TimSuchanek’s Expand Fetch keeps tables and icons intact and saves the page, so you can see exactly what the agent read. Pretty pretty useful! :)1h
    Santiago@svpinoOne of the easiest ways to connect your agents to the web: 1. Add Expand's MCP server to your agent 2. Sign in when prompted 3. Ask the agent to use this server when fetching pages Any time your agent fetches a URL, Expand will return Markdown content while preserving its original format. This is huge, especially when you need to process tables, icons, or any layout that matters for understanding the content.1h
    Rohan Paul@rohanpaul_aiThis looks like a big step for agents that read the web. Expand, a new AI startup, released Expand Fetch, a tool that lets AI agents read web pages without losing icons, tables and hidden data along the way. On Expand’s own private test, agents using it answered 74% of hard web questions correctly, against 55% for the next best tool. When AI agents read a website today, the page is usually converted to plain text first, and details like a ✗ next to a feature get thrown away, so the agent confidently gives wrong answers. Expand Fetch, uses its own vision model, Iris, to look at the page the way a person does and keep those details intact. Every fetch is also stored as a snapshot whose Markdown lines link back to their source, letting developers trace a wrong answer to what the agent saw.1h
    Robert Scoble@ScobleizerHow much of an AI agent’s “reasoning problem” is actually missing information? Expand Fetch preserves tables, icons and layouts, with sources you can check. They report 74% accuracy vs. 55% for the next best API on their benchmark. Builders, this is worth testing.51m
    Today's Rank

    #4

    Today's Rank

    #4