Plan & manage an Azure AI solution · 25–30%

Responsible AI

~2 min read

Responsible AI is the practice of building AI systems that are fair, safe, private, and accountable — and proving it with process. The exam tests Microsoft’s version of that process.

Microsoft’s 6 principles

Fairness · Reliability & safety · Privacy & security · Inclusiveness · Transparency · Accountability

Memory hook: “FRPITA” — or just remember pairs: fair+reliable, private+inclusive, transparent+accountable.

The 4-stage process (maps to NIST AI RMF)

  1. Map — identify potential harms, prioritize them by likelihood × impact, red-team test them, then document and share.
  2. Measure — build a prompt suite likely to elicit each harm, run it, categorize the output against strict criteria, and record the result as your baseline. Start manual, then automate.
  3. Mitigate — layered (next section) + transparent communication.
  4. Manage — pre-release reviews (legal, privacy, security, accessibility), phased delivery, incident-response + rollback plans, block harmful responses/users, user feedback channel, telemetry.

The 4 mitigation layers (from the model up to the user)

LayerMitigations
1. ModelPick appropriate (smaller if sufficient) model; fine-tune
2. Safety systemGuardrails: content filters, prompt shields, abuse detection
3. System message & groundingPrompt engineering, RAG on trusted data
4. User experienceConstrain inputs/outputs in UI, transparent docs

Content filters — exact numbers

Content filters classify every prompt and response into harm categories and block anything above a severity threshold.

“User tries to override the system prompt” means prompt shields. “Block gory images” means a content filter, category violence. “Model invents facts” is not a filter problem — that’s groundedness (fix with RAG and evaluators).

Instrumentation & governance (agents too)