Roadmap

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

• •POST /v1/tasks with a canonical goal-native envelope plus compatibility aliases
• •Structured results via JSON polling, SSE, or NDJSON streaming
• •Continuation input for multi-turn agent workflows
• •Discovery marker plus rover-site.json and agent-card.json for endpoint detection
• •No Playwright, no MCP servers, no middleware required for the base protocol

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
• •Five trust tiers: verified_signed, signed_directory_only, self_reported, heuristic, anonymous
• •Rover accepts the calling agent's identity and records verification method, discovery surface, capability ID, page ID, execution path, and workflow lineage
• •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

Browser-native Rover tools compiled from the same capability graph, without making WebMCP the only path.

• •WebMCP stays an optional accelerator for live-tab execution, not the base standard
• •The same capabilities remain reachable through rover-site.json, agent-card.json, and ATP
• •Turn any web app into a composable building block for agent workflows
• •Auto-index site capabilities for browser-native tool discovery

Ship the Rover discovery ladder and compatibility suite publicly before pushing the model into formal standards bodies.

• •Beacon-first UX spec with silent, beacon, integrated, and debug modes
• •Compatibility tests for raw HTTP, agent-card consumers, DOM/a11y agents, screenshot/VLM agents, and WebMCP-capable browsers
• •Clear distinction between rover-site.json as the rich profile and agent-card.json as the interop card
• •Standards work follows deployment reality rather than blocking product rollout

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