The outcome

Operate a generative AI flow that has evidence-based quality thresholds and documented responses to unsafe or unsupported content.

Step by step

A workflow you can repeat.

  1. 01

    Create a versioned dataset covering normal tasks, prompt injection, sensitive data, harmful content, protected material, and unsupported-answer cases.

  2. 02

    Define task, groundedness, safety, latency, and cost metrics with pass thresholds and a human review rubric for ambiguous results.

  3. 03

    Configure system rules, content filters or Content Safety checks, Prompt Shields, network boundaries, and output validation for the use case.

  4. 04

    Run evaluations on the complete flow, inspect false positives and false negatives, and test tool calls and retrieved content as untrusted inputs.

  5. 05

    Version prompts, filters, models, and datasets together; monitor production signals, audit changes, and block promotion when regression thresholds fail.

Working standard

What good use looks like.

  • Evaluate the complete application flow.
  • Measure false positives and false negatives.
  • Version guardrails with prompts and models.

Official references

Check the current product documentation.