Google Workspace
For Google WorkspaceDocument AgentsConcisenessToneTask Completion

Gmail Calendar Coordination V1

Inbox and Calendar Coordinator · Google Workspace

Eval for Gmail triage, response drafting, and calendar scheduling when multiple stakeholders and time zones are involved.

About Google Workspace

Google Workspace is Google's cloud-based productivity suite including Gmail, Docs, Sheets, Meet, and Drive. Gemini for Workspace brings generative AI directly into these tools, enabling employees to draft, summarize, and search across their work data.

Employees

~182,000

Industry

Cloud Productivity & AI

Headquarters

Mountain View, CA

Sample tests· showing 3 of 4

#InputExpected behaviorCheck
01urgent inbox triage

Google Workspace / Inbox and Calendar Coordinator: Triage a CEO email thread requesting a same-day response. Draft a reply that acknowledges the request and assigns the next step without sounding robotic. Respond for persona `exe…

outcome_label: draft_reply · confidence: high · required_actions: prioritize the urgent thread, draft a concise reply…

Pass / Fail
02timezone scheduling

Google Workspace / Inbox and Calendar Coordinator: Schedule a follow-up meeting across San Francisco, London, and Tokyo while avoiding the stated lunch block and the exec's travel window. Respond for persona `project_manager`.

outcome_label: find_valid_slot · confidence: high · required_actions: honor all time-zone constraints, avoid the lunch block…

Pass / Fail
03hostile or legal email

Google Workspace / Inbox and Calendar Coordinator: A customer email contains a legal threat and demands immediate action. Escalate rather than drafting a normal support reply. Respond for persona `support_manager`.

outcome_label: escalate · confidence: high · required_actions: flag the legal threat, escalate to the right owner…

Pass / Fail

How this eval is graded

Evaluate triage judgment, scheduling accuracy, and escalation discipline. Passing responses should avoid hallucinated availability or unsafe inbox actions.

Pass threshold: a criterion passes at a judge score of 4 or higher.

Rubric criteria

  • Inbox Triage
  • Calendar Coordination
  • Response Drafting

Recommended for

Inbox TriageCalendar CoordinationResponse Drafting

Works with

Related evals

Run this eval in your workspace

Connect your data, configure thresholds, and review results with your team.