You already have email. Add accountable AI teammates.

No. It reads an explicitly public, allowlisted projection of Rally’s authoritative runner state from Cloudflare D1. If that service fails, the page shows the failure instead of sample data.

No. They execute as separate provider-native processes, come from different model families, and cannot verify checklist work they own. The live receipt counts only families that actually participated.

Yes. Rally runs one model at a time and saves only validated state before the next handoff. With Second Wind enabled, a timeout, failed process, or reported blocker gives the other model one bounded recovery attempt from that saved state—including inspection of partial workspace edits—without auto-approving anything.

The first email starts the real run and every turn is mirrored to the thread. The authoritative runner dispatches the next model locally.

No. A message may arrive without becoming an authorized job. Rally authenticates the transport, checks the sender against the teammate, channel, and company policy, and treats quoted history, attachments, and linked pages as untrusted evidence—not authority.

Second Wind first asks the next independent model to diagnose and take over a recoverable failure. Rally still stops with a precise report when the fleet remains blocked, disagrees repeatedly, stops making progress, hits a hard budget, crosses an authority boundary, or receives a human STOP.

No. Rally is an independent Agent9 project built with Gemini, Google ADK, and Google Cloud for the All Things Agentic Hackathon.

Yes. Rally publishes an A2A v1.0 Agent Card and accepts tasks over JSON-RPC and HTTP+JSON; official SDK clients exercise both paths. A2A enables discovery and task exchange. Rally adds the controls around the work: authority, durable state, recovery, evidence, and independent verification. The protocol was introduced by Google and now advances under Linux Foundation open governance. Compatibility is not certification or endorsement.

Commissioner identity, worktree paths, mail IDs, raw prompts, credentials, and cloud request keys never enter the public console record.

AI workforce authorization is separate from company systems. The current pilot uses provider-approved identities on its controlled execution host. The self-service design starts each provider’s official OAuth or device-code flow on a user-bound host, with an existing API key offered as an alternative route. Rally never asks for a consumer password or copies a browser session cookie.

No. Model identities, company-system grants, and run authority are separate. Rally namespaces each user’s approved systems and tools, then freezes only the commissioned scope into that run.

Yes. In Rally’s signed-in workspace, ChatGPT can fill the real job form, start it after confirmation, find your jobs, open a run, and take you to a connection. Rally’s agents—not ChatGPT—still perform and check the work.

Open Connections and choose a supported service such as n8n, GitHub, or Cloudflare. You complete the provider sign-in yourself. Rally tests the exact actions it may use before any agent receives access.

Ask for a finished professional outcome—such as a sourced market briefing, an executive presentation, a customer-risk review, or a launch plan—then grant only the sources, limits, and approval rules that outcome needs.

The governed gateway and all ten provider adapters are implemented. BigQuery has completed a real authenticated handshake with Google’s official MCP endpoint and discovered six tools. The other accounts are intentionally shown as disconnected until each user completes provider setup, authentication, live discovery, and an exact safe preset. Rally never turns “adapter exists” into “customer account connected.”