Focus area
Web search and data APIs for AI agents
AI agents need live web data they can trust, through search APIs, scraping tools and MCP servers. Doccraft covers how agents get that data, where it fails, and what production teams build around it.
Research and guides
- AI in web scraping: what 2026 conferences agree on
I studied more than 60 web scraping talks, podcasts and AMAs and read 10 papers. The clearest finding is that teams use AI to build scrapers, not to run them.
- Hidden prompt injections that target scrapers: what a 2026 study found
A 2026 study found 15,387 prompt injections hidden in real web pages, aimed mostly at crawlers and scrapers. What they say, where they hide, what the top 1,000 sites do, and how to handle them.
- What Oxylabs learned from its AI parser agent
At OxyCon 2026, Oxylabs openly shared why its engineers stopped using an AI parser agent, and what its second agent did differently.
Published for clients
- Search APIs vs. Knowledge Supply Chains: Why Enterprise Agents Need More Than Just Search (opens in a new tab)brightdata.com
- MCP servers for web scraping: carry control, not data (opens in a new tab)scrapingbee.com
- AI agent infrastructure stack: from web data to retrieval (opens in a new tab)blog.apify.com
- Build an account research agent in Salesforce Agentforce with Bright Data (opens in a new tab)brightdata.com
- AI agent vs. MCP server: which one should you build? (opens in a new tab)blog.apify.com
- Giving self-hosted MiniMax M3 agents live web access with Bright Data (opens in a new tab)brightdata.com