Back to Prompt Library
testing

End-to-End Testing and Compliance Reporting

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: Multimodal Content Generator for Brand Safety

Format
Code-aware
Lines
12
Sections
3
Linked challenge
Multimodal Content Generator for Brand Safety

Prompt source

Original prompt text with formatting preserved for inspection.

12 lines
3 sections
No variables
1 code block
Perform end-to-end testing of your ADK agent via the Voiceflow interface (or simulated API calls). Ensure that generated content concepts are creative, relevant, and consistently adhere to brand safety and platform policies. The final output should include a clear 'compliance_report' and an 'agent_reasoning_trace' demonstrating the self-correction process.

```python
# Simulate an API call from Voiceflow
input_data = {
    "topic": "The Future of Space Travel",
    "target_audience": "Science enthusiasts, all ages",
    "brand_safety_rules": ["factual accuracy", "inspire wonder", "avoid speculation as fact"],
    "platform_policies_url": "https://example.com/youtube-policies-simulated"
}

# ... call your ADK agent's endpoint ...
# Ensure the returned JSON matches the output_format for evaluation.
```

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Preserve the rubric, target behavior, and pass-fail criteria as the baseline for evaluation.

Tune next

Adjust fixtures, mocks, and thresholds to the system under test instead of weakening the assertions.

Verify after

Make sure the prompt catches regressions instead of just mirroring the happy-path examples.