Official datasetProvider-published evidence
WorkflowEvals Customer Service
A 204-case dataset for customer-service routing and actions under three policy settings.
This official EvalSafe dataset captures customer-service cases, policy questions, and published model decisions for action-level comparison.
- Publisher
- TypeSafe AI
- Published or submitted
- Not specified by the source
- Last verified
- October 8, 2026
Type Safe catalogs sources and evidence boundaries. Provider datasets and third-party preprints do not become an independent leaderboard.
Key facts
- Cases
- 204
- Question instances
- 3,287
- Published run results
- 1,836
- Dataset license
- Not specified in the reviewed source
Task and scope
Customer-service routing and actions under three policies.
Dataset schema
cases · questions · run_results · 5,327 rows
Evaluation metrics
exact_actions
Dataset license
Not specified by the source
Method and usage
- The workflow evaluates routing and customer-service actions under three policy configurations.
- Customer service has no primary-action score in the repository, so cross-workflow averages use exact_actions.
Limitations and evidence boundaries
- The reviewed dataset card did not specify a dataset license; the repository code license does not fill that gap.
- Policy and action coverage may not match a production support team's tools, escalation rules, or service levels.