Microsoft Developing AI Apps and Agents on Azure (AI-103) Exam Questions

Microsoft Developing AI Apps and Agents on Azure Exam Objectives

1. 1

   1.0 Plan and manage an Azure AI solution (25-30%)

   • Task 1.1: , including large language models (LLMs), small language models, multimodal models, and Foundry Tools Choose the appropriate Foundry services for generative tasks, grounding, vector search, agent workflows, or multimodal processing Choose an appropriate method for retrieval and indexing Choose appropriate memory, tool, and knowledge integration services for agent solutions Set up AI solutions in Foundry Design Azure infrastructure for AI apps and agent-based solutions Choose appropriate deployment options Configure model and agent deployments Integrate Foundry projects with continuous integration and continuous deployment (CI/CD) pipelines Manage, monitor, and secure AI systems Manage quotas, scaling, rate limits, and cost footprints for model and agent workloads Monitor model performance, drift, safety events, and grounding quality Monitor data ingestion quality, search index health, and relevance performance Configure security, including managed identity, private networking, keyless credentials, and role policies Implement responsible AI across generative AI and agentic systems Configure safety filters, guardrails, risk detection, and content moderation Apply responsible AI instrumentation, including evaluators, safety evaluations, and explanation tooling Implement auditing through trace logging, provenance metadata, and approval workflows Govern agent behavior with oversight modes, constraints, and tool-access controls
2. 2

   2.0 Implement generative AI and agentic solutions (30-35%)

   • 2.1Build generative applications by using Foundry
   • 2.2Deploy and consume LLMs, small models, code models, and multimodal models
   • 2.3Implement retrieval-augmented generation (RAG) in an application
   • 2.4Design workflows, tool-augmented flows, and multistep reasoning pipelines
   • 2.5Evaluate models and apps, including detecting fabrications, relevance, quality, and safety
   • 2.6Integrate generative workflows into applications by using Foundry SDKs and connectors
   • 2.7Configure an application to connect to a Foundry project
   • 2.8Build agents by using Foundry
   • 2.9Define agent roles, goals, conversation-tracking approach, and tool schemas
   • 2.10Build agents that integrate retrieval, function-calling, and conversation memory
   • 2.11Integrate agent tools, including APIs, knowledge stores, search, content understanding, and custom functions
   • 2.12Implement orchestrated multi-agent solutions
   • 2.13Build autonomous or semiautonomous workflows with safeguards and approval flow controls
   • 2.14Integrate monitoring into deployed agents, evaluate agent behavior, and perform error analysis
   • 2.15Optimize and operationalize generative AI systems
   • 2.16Tune generation behavior, such as prompt engineering and adjusting model parameters
   • 2.17Implement model reflection, chain-of-thought evaluations, and self-critique loops
   • 2.18Set up observability by implementing tracing, token analytics, safety signals, and latency breakdowns
   • 2.19Orchestrate multiple models, flows, or hybrid LLM and rules engines
3. 3

   3.0 Implement computer vision solutions (10-15%)

   • Task 3.1: and pro mode Content Understanding pipelines Implement solutions that identify objects, components, or regions within images or video Implement responsible AI for multimodal content Implement filters to classify unsafe or disallowed visual content Detect and mitigate indirect prompt injection by using embedded text in images Enforce visual policy rules, such as applying watermarks, flagging prohibited symbols, upholding brand usage requirements, and detecting potentially inappropriate content
4. 4

   4.0 Implement text analysis solutions (10-15%)

   • 4.1Apply language model text analysis
   • 4.2Implement solutions to extract entities, topics, summaries, and structured JSON outputs by using generative prompting and Foundry Tools
   • 4.3Configure detection of sentiment, tone, safety issues, and sensitive content
   • 4.4Build solutions that translate text by using Azure Translator in Foundry Tools or LLM powered translation flows
   • 4.5Customize language model outputs for domain tasks, such as compliance summarization and domain extraction
   • 4.6Implement speech solutions
   • 4.7Implement workflows to convert speech to text and text to speech for agentic interactions
   • 4.8Integrate speech as an agent modality, including custom speech models
   • 4.9Enable multimodal reasoning from audio inputs
   • 4.10Translate speech into other languages by using language models and Foundry Tools
5. 5

   5.0 Implement information extraction solutions (10-15%)

   • 5.1Build retrieval and grounding pipelines
   • 5.2Ingest and index content, such as documents, images, audio, and video
   • 5.3Configure semantic search, hybrid search, and vector search for grounding
   • 5.4Implement enrichment by using custom or built-in skills for text, images, and layout
   • 5.5Configure RAG ingestion flow, including documents and using optical character recognition (OCR)
   • 5.6Connect retrieval pipelines directly to workflows and agent tools