Serenity BDD Report
Home > Requirements > Data-science > Critique advice
Report generated 28-07-2025 14:05

Feature: Critique advice

The advisor is an LLM agent, therefore:

  • The output may not be deterministic
  • The output may differ between runs
  • The output may differ as the base model is updated
  • The advisor should indicate its level of confidence

Scenarios

Given There are archive results for "{Site}"

When Des generates recommendations for "{Site}"

Then Des sees that the recommendations for "{Site}" are consistent over time

Given Des updates the base model

OldNew
1.31.4

When Des generates recommendations for "Site 1"

Then Des sees that the advice for Zone "{Zone}" is for "{Set Point}" to be "{Recommended Value}"

Feature Coverage By Scenario

Test Outcomes

Test Performance

Key Statistics

Number of Scenarios 2 Total Duration 1s
Total Number of Test Cases 5 Fastest Test 17ms
Number of Manual Test Cases 0 Slowest Test 495ms
Tests Started Jul 28, 2025 14:05:13 Average Execution Time 208ms
Tests Finished Jul 28, 2025 14:05:14 Total Execution Time 1s

Automated Tests

feature Scenario Context Steps Started Total Duration Result
Critique advice Explainer recommendations are consistent between runs
3 pending test cases
3 14:05:13 058ms PENDING
Critique advice Explainer recommendations are consistent after the base model is updated
2 passing test cases
3 14:05:13 989ms SUCCESS

Manual Tests

No manual tests were recorded
Serenity BDD version 4.2.34