Roadmap

Formalized open protocol for AI agents, CLIs, and autonomous systems to interact with any Rover-enabled website.

• •POST /v1/tasks with a URL and a natural-language prompt
• •Structured results via JSON polling, SSE, or NDJSON streaming
• •Continuation input for multi-turn agent workflows
• •Discovery marker for automatic endpoint detection
• •No Playwright, no MCP servers, no middleware — the page is the API

First-party visibility into AI agent traffic on your site. Direct signal from real interactions — not estimates from third-party GEO or AI SEO tools.

• •Which AI agents visit your site and what they attempt
• •Success and failure rates per agent, per workflow
• •Rover accepts the calling agent's identity — see exactly who is acting on your page
• •Intent analytics: what are AI agents trying to do on your site?
• •Replace guesswork from third-party AI traffic estimators with ground truth

Connect user identity (PPID), geography, and agent identity to Rover. Customize the agent experience for every context.

• •Personalize agent behavior per user, per region, per calling AI
• •A user in Tokyo gets a different experience than one in New York
• •Claude gets different capabilities than a custom enterprise agent
• •Link PPID to Rover sessions for unified user + agent insights
• •Site owners control what each agent can see and do

Sites surface their actions and capabilities as discoverable tools other AI agents can invoke natively.

• •Your site publishes what it can do — other agents call those actions directly
• •No server changes, no API wrappers needed
• •Turn any web app into a composable building block for agent workflows
• •Auto-index site capabilities for agent discovery

Browser-native voice-driven workflows for hands-free interaction with any Rover-enabled site.

• •Speech-to-action: speak a task, Rover executes it
• •Browser-native dictation — no external services required
• •Configurable silence detection and auto-stop
• •Full voice-first experiences for accessibility and mobile