Google Workspace
For Google WorkspaceDocument AgentsCorrectness

Calendar Scheduling Conflicts V1

Calendar Scheduling Conflicts · Google Workspace

Schedule meetings across time zones, detect conflicts, and ask for clarification when constraints cannot be satisfied.

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 6

#InputExpected behaviorCheck
01

Google Workspace exec_assistant needs to schedule a 45-minute review with attendees in San Francisco, London, and Tokyo. Offer the best candidate time and note any conflicts in the request.

resolution_label: schedule · should_escalate: false · risk_level: medium

Pass / Fail
02

Google Workspace project_coordinator needs to schedule a 45-minute review with attendees in San Francisco, London, and Tokyo. Offer the best candidate time and note any conflicts in the request.

resolution_label: schedule · should_escalate: false · risk_level: medium

Pass / Fail
03

Google Workspace operations_manager needs to schedule a 45-minute review with attendees in San Francisco, London, and Tokyo. Offer the best candidate time and note any conflicts in the request.

resolution_label: schedule · should_escalate: false · risk_level: medium

Pass / Fail

How this eval is graded

Evaluate whether the response is grounded, policy-aligned, and operationally useful. Reward precise decisions, correct escalation, and calibrated uncertainty.

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

Rubric criteria

  • Conflict Detection
  • Time Zone Accuracy
  • Clarifying Questions

Recommended for

Conflict DetectionTime Zone AccuracyClarifying Questions

Works with

Related evals

Run this eval in your workspace

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