
From the team
Blog
What we ship, how it performs,
and practical ways to put rtrvr to work.

Research
Protocol beats prompt injection for agent-site communication
Declared capabilities give agents a safer, inspectable contract. Hidden instructions inside page content do not.
Read articleResearch
The Agent-Web Protocol Stack: A Research Thesis
The web's protocol stack was designed for humans behind browsers. A new consumer is arriving: AI agents. This paper maps the emerging protocol landscape and positions Rover as the missing execution layer.
Read article
Product
Introducing agent analytics for Rover
See what users ask an on-site agent to do, where runs break, and which requests become successful product actions.
Read article
Product
Vibe Hacking: find the site API, then reuse the workflow
Use the page to discover its network contract, extract structured data, and keep the result as a repeatable browser workflow.
Read article
Product
Watchdogs, knowledge bases, and cheaper browser runs
A practical launch note on recurring checks, reusable context, mobile triggers, and lower-cost execution.
Read article
Research
The $10 Billion Proof Point: Why Every Website Needs Its Own AI Agent
Amazon's Rufus proved embedded agents are worth $10B annually. Google's WebMCP wants to intermediate your users. Here's why owning your agent is the only path forward.
Read article
Research
Chatbots Are Read-Only. The Web Isn't.
A technical teardown of why every RAG chatbot, vision agent, and CUA fails at the one thing websites actually need — and the DOM-native architecture that replaces them all.
Read article
Product
rtrvr v27: watch and take over a Cloud browser
Observe a remote run as it happens, step in when judgment is needed, and return control to the agent.
Read article
Playbooks
Retriever AI, Chat4Data, Thunderbit, Browse AI, or Bardeen?
Start with the job: collect a table, monitor a page, research prospects, or fill a form.
Read articlePUT IT TO WORK