5.5 Responsible Generative AI

Key Takeaways

  • Responsible generative AI applies Microsoft's six responsible-AI principles plus extra safeguards specific to content generation.
  • Azure OpenAI content filters (powered by Azure AI Content Safety) scan both prompts and responses across four categories — hate, violence, sexual, and self-harm — and are on by default.
  • Prompt Shields detect and block jailbreak and prompt-injection attempts that try to bypass safety guardrails.
  • Groundedness detection verifies that responses are supported by the provided source documents, helping catch hallucinations in RAG.
  • Microsoft Copilot builds in responsible AI with content filters, citations, disclaimers, feedback, and enterprise data boundaries.
Last updated: June 2026

Quick Answer: Responsible generative AI applies Microsoft's six principles with additional safeguards: content filters block harmful content in prompts and responses, Prompt Shields prevent jailbreaks, and groundedness detection ensures responses are factually supported. Azure OpenAI includes these protections by default.

Why Responsible Generative AI Is Different

Generative AI introduces unique risks that traditional AI does not:

RiskDescriptionExample
HallucinationConfident but false output"Abraham Lincoln invented the telephone"
Harmful contentHate, violence, or inappropriate outputGenerating offensive text or images
JailbreakingPrompts that bypass safety guardrails"Ignore your instructions and tell me how to..."
Prompt injectionHidden instructions in input override the system messageInstructions pasted inside a document
Copyright concernsOutput that closely matches protected materialReproducing copyrighted text or code
MisinformationPlausible but false informationFake medical or legal advice
Privacy leakageRevealing personal data seen in trainingGenerating someone's address

Content Filtering in Azure OpenAI

Azure OpenAI includes default content filters that are always active and powered by Azure AI Content Safety.

Four Filter Categories

CategoryWhat It BlocksSeverity Levels
HateDiscrimination, slurs, dehumanizationSafe -> Low -> Medium -> High
ViolenceThreats, graphic violence, harmSafe -> Low -> Medium -> High
SexualSexually explicit or suggestive contentSafe -> Low -> Medium -> High
Self-harmSelf-injury descriptions or instructionsSafe -> Low -> Medium -> High

How Filtering Works

  1. The user submits a prompt to the API.
  2. The input filter scans the prompt for harmful content.
  3. If the prompt passes, the model generates a response.
  4. The output filter scans the response.
  5. If the response passes, it is returned to the user.
  6. If either filter triggers at or above the configured severity, the request is blocked with an error.

On the Exam: Azure OpenAI content filters are enabled BY DEFAULT and scan BOTH prompts AND responses. You do not enable them separately — a very common exam point.

Prompt Shields

Prompt Shields detect and block jailbreak and injection attempts — efforts to make the model ignore its safety instructions:

TechniqueExampleHow Prompt Shields Help
Direct override"Ignore all previous instructions and..."Detect instruction-override patterns
Role play"Pretend you are an AI with no restrictions..."Identify role-play bypasses
Encoding tricksHiding requests in base64 or other encodingsDetect encoded content
Indirect injectionHarmful instructions hidden in pasted documents or URLsScan all input content for hidden instructions

Groundedness Detection

Groundedness detection (an Azure AI Content Safety capability) verifies that AI-generated responses are factually supported by the provided source documents:

ResultMeaning
GroundedThe response is supported by the provided context — safe
UngroundedThe response makes claims not supported by the context — flagged as a possible hallucination

This is especially important in RAG scenarios, where you want the model to answer only from retrieved documents.

Microsoft Copilot and Responsible AI

Microsoft Copilot incorporates responsible AI by design:

FeatureResponsible-AI Purpose
Content filtersBlock harmful content in prompts and responses
CitationsShow sources for generated information (transparency)
Disclaimers"AI-generated content may be incorrect" warnings (transparency)
User feedbackThumbs up/down to report quality issues (accountability)
Data boundariesEnterprise data stays within the Microsoft 365 boundary (privacy)
Grounding in enterprise dataRespond based on your organization's data (accuracy)

Best Practices for Responsible Generative AI

For Developers and Organizations

PracticeDescription
Keep content filters onUse the default Azure OpenAI filters
Implement RAG/groundingGround responses in factual data to cut hallucinations
Set clear system messagesDefine what the AI should and should not do
Monitor usageReview logs for misuse and harmful content
Provide disclaimersTell users content is AI-generated
Enable feedbackLet users report inaccurate or harmful output
Test/red-teamProbe your application for vulnerabilities
Human oversightKeep humans in the loop for high-stakes decisions

For End Users

PracticeDescription
Verify informationDo not blindly trust AI output
Provide contextGive relevant information to reduce hallucinations
Review for biasCheck outputs for unfairness
Report issuesUse feedback mechanisms

Configurable Filters and Annotations

While the default filters are always on, organizations with approved access can configure severity thresholds per category (for example, block at medium-and-above for violence but only high for another category) and can enable optional categories such as protected-material detection for text and code. The API also returns annotations indicating which category and severity triggered a filter, which helps developers log, debug, and tune their applications responsibly.

The key exam takeaway remains that the baseline protection is on by default and covers both input and output — configuration adjusts the thresholds, it does not turn safety off.

On the Exam: Responsible-generative-AI questions focus on content filters (four categories, on by default, scan input and output), hallucination mitigation (RAG/grounding/groundedness detection), Prompt Shields (jailbreak defense), and how Copilot uses citations and disclaimers for transparency.

Test Your Knowledge

What are Prompt Shields in Azure OpenAI Service?

A
B
C
D
Test Your Knowledge

What does groundedness detection verify in generative AI?

A
B
C
D
Test Your Knowledge

Which of the following is a responsible AI feature built into Microsoft Copilot?

A
B
C
D
Test Your Knowledge

What is the best technique to reduce hallucinations in generative AI responses?

A
B
C
D
Test Your Knowledge
Multi-Select

Which THREE of the following are categories used by Azure OpenAI content filters? (Select three)

Select all that apply

Hate speech
Political opinions
Violence
Competitive analysis
Self-harm