- Microsoft and Cloudflare want sites to behave as conversation -Ai -apps
- CloudFlares Authorag indexes content automatically, promising seamless updates to site data
- NLWEB introduces structured MCP endpoints for AI agents seeking reliable access
Microsoft and Cloudflare have announced a new collaboration seeking to make sites easier for both humans and automated systems to inquire.
The initiative merges Microsoft’s “NLWEB” standard with CloudFlares “autorag” infrastructure, giving a model for conversation search.
Instead of key word -based navigation, the system allows natural language interaction that presents direct answers rather than lists of links.
From search engines to answer engines
The goal of the new launch is to make any site act as an AI app where human visitors and AI agents can ask questions and receive structured answers.
“Together, NLWEB and authors let publishers go beyond search fields, making conversation interfaces to websites that are easy to create and implement,” said RV GUHA, creator of NLWEB, CVP and technical scholarship at Microsoft. “This integration allows any site to be easy to become AI clear to both humans and trusted agents.”
Traditional search depends on keywords, leaving users to silence through multiple links to reach relevant information, but advocates of this new approach claim that the model no longer matches expectations shaped by tools such as Chatgpt, Copilot and Claude.
These systems provide immediate answers and people are increasingly expecting sites to do the same.
Although this framing is convincing, it does, however, assume that all users prefer conversation -answers rather than browsing.
The partnership also emphasizes the role of AI agents as a new class of “visitors.”
These automated systems typically scrape pages or follow key words, but NLWEB introduces a structured “MCP” point that gives them controlled access to site data.
This can reduce the inefficiency of scraping while giving site owners the opportunity to define access conditions.
Nevertheless, there are still questions about whether place operators will see concrete benefits or primarily additional technical burdens.
CloudFlares Authorag Component handles searching, indexing and embedding site content in an administered vector database.
The system promises to keep information fresh with continuous updates and give observability through cloudflares AI Gateway.
While this sounds effective, it effectively places indexing and access pipelines in the hands of a third -party infrastructure provider.
It raises concerns about costs, addiction, and whether site owners will give up too much control over how their data is handled.
By frameing websites as first-class data sources for AI tools, Microsoft and Cloudflare place themselves in direct competition with traditional search engines, especially Google.
If AI author models and LLM systems are increasingly dependent on structured access rather than scraping, search traffic patterns can change significantly.
To enable conversation -search on a site through CloudFlares authors logs users into the cloudflare -dashboard, creates a new Authorag instance using the NLWEB Web site Quick Deploy -Setting, select the desired domain and start indexing.
Once the process is completed, the content of the site becomes searchable through natural language requests, and owners can preview or integrate the conversation interview to test how it seems to visitors.
