AI-103 Practice Question 9: Conversation PII Redaction

Microsoft Azure AI Apps and Agents Developer Associate (AI-103) · Test 1 · question 9 of 10

Implement text analysis solutionsmedium

A contact centre stores the previous day's chat and voice transcripts in an overnight job so analysts can study them. Compliance requires that customer names, phone numbers, and payment card numbers be masked before the transcripts land in the analytics store. The transcripts arrive as turn-based exchanges with speaker attribution, and masking decisions must take the turn boundaries and conversational context into account. Nobody has labelled any training data.

Which capability should the ingestion job call?

Show answer and explanation

Answer:

B. Conversation PII in Azure Language, which processes turn-based transcript payloads asynchronously

PII detection is grouped into feature types by the shape of the input. Conversation PII processes multi-turn exchanges and transcript-oriented payloads where turn boundaries and conversation context affect detection and masking behaviour, and it is the feature intended for asynchronous workloads over chat and transcript structures: contact centres, meetings, and voice transcripts. It uses predefined entity categories, so no labelled data is needed.

- A is wrong because custom NER requires exactly the labelled training data the team does not have, and it rebuilds recognizers for names, phone numbers, and card numbers that the predefined PII categories already cover. - C is wrong because Text PII is optimized for synchronous, string-based input such as messages, prompts, and log fields. Flattening a conversation into one string discards the turn structure that the stem says must inform masking. - D is wrong because Document-based PII targets native files (.pdf, .docx, .txt), and preserves document fidelity. Converting chat logs to PDF adds a lossy step purely to reach the wrong feature type.

Reference: What is the Personally Identifiable Information (PII) detection feature in Azure Language?

Practice Test 1 ›

Study guides for AI-103

AI engineer roadmap 2026: skills, certs and the orderAI engineer roadmap for 2026: skills to learn in order, AI engineer vs ML engineer, which certifications fit each stage, and what to skip.

AI-200 exam guide: Azure AI Cloud Developer AssociateAI-200 replaced AZ-204: what the Azure AI Cloud Developer exam tests, how it differs from AI-103, price in USD and INR, format and how to prepare.

How AI Is Changing Software Jobs: Where to PrepareHow AI is changing software jobs: what history shows, the evidence on junior developers, what Klarna learned, new AI roles and five domains to prepare for.

AI-901 exam guide: Azure AI Fundamentals after AI-900AI-901 replaced AI-900: learn what changed, how much Python and Microsoft Foundry you need, exam costs in India, and how to prepare.

Best AI certifications 2026: AWS, Google, Microsoft, ClaudeThe best AI certifications in 2026 from AWS, Google, Microsoft, Claude and Databricks, by level, with price, status and which one to take first.

Microsoft AI certification path 2026: which exam firstMicrosoft AI certification path for 2026 - AI-901, AB-730, AI-103, AI-200, AI-300, AB-100, AI-500 and GH-300 by role, and which exam to take first.

AI-103 Certification Guide: What Changed From AI-102The AI-103 certification replaced AI-102 in 2026. Exam format, cost, the five skill domains, what changed and how to prepare, with free practice questions.

What Is RAG? How Retrieval-Augmented Generation WorksWhat RAG is and how it works: chunking, embeddings, vector search, hybrid search, reranking, GraphRAG and agentic RAG on AWS, Google and Azure.

Prompt engineering vs RAG vs fine-tuningWhen to use prompt engineering, retrieval-augmented generation, fine-tuning or continued pre-training, compared on cost, freshness, hallucination and privacy.