noorsy/RubricHQ Agent Tests
Run RubricHQ voice/text agent test scenarios and gate the workflow on the result
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| api_key | RubricHQ API key (create one under Settings → API Keys) | yes | — |
| agent_id | ID of the agent under test | yes | — |
| scenario_ids | Comma-separated scenario IDs to run (at least one of scenario_ids / tags required) | no | "" |
| tags | Comma-separated scenario tags to run (at least one of scenario_ids / tags required) | no | "" |
| frequency | How many times to run each scenario (1-5) | no | 1 |
| success_threshold | Minimum pass rate percentage (0-100) for the run to pass | no | 100 |
| timeout | Maximum seconds to wait for the test run to finish | no | 3600 |
| poll_interval | Seconds between status polls | no | 15 |
| channel | Channel to test over: phone, web, or text (default: the agent's configured channel) | no | "" |
| api_url | RubricHQ API base URL | no | https://api.rubrichq.io |
Outputs
| name | description |
|---|---|
| test_run_id | ID of the triggered test run |
| verdict | Final verdict: passed or failed |
| pass_rate | Pass rate percentage |
| report_url | Link to the full report in the RubricHQ app |