Developing AI Apps and Agents on Azure
Practice Exam Questions & Study Guide
Plan and manage an Azure AI solution (25–30%)Free
Covers choosing appropriate Foundry services, setting up AI solutions, managing and monitoring AI systems, and implementing responsible AI practices. (25–30% of scored content)
1.1: Choose the appropriate Foundry services for generative AI and agents
Covers selecting appropriate models, Foundry services, retrieval methods, and integration services for agent solutions.
- Choose an appropriate model for each task, 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
1.2: Set up AI solutions in Foundry
Covers designing Azure infrastructure, choosing deployment options, configuring deployments, and integrating with CI/CD pipelines.
- 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
1.3: Manage, monitor, and secure AI systems
Covers managing quotas and costs, monitoring model and data performance, and configuring security for AI workloads.
- 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
1.4: Implement responsible AI across generative AI and agentic systems
Covers configuring safety filters, applying responsible AI instrumentation, implementing auditing, and governing agent behavior.
- 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
Implement generative AI and agentic solutions (30–35%)
Covers building generative applications, building agents, and optimizing and operationalizing generative AI systems using Foundry. (30–35% of scored content)
2.1: Build generative applications by using Foundry
Covers deploying and consuming models, implementing RAG, designing workflows, evaluating models, and integrating generative workflows into applications.
- Deploy and consume LLMs, small models, code models, and multimodal models
- Implement retrieval-augmented generation (RAG) in an application
- Design workflows, tool-augmented flows, and multistep reasoning pipelines
- Evaluate models and apps, including detecting fabrications, relevance, quality, and safety
- Integrate generative workflows into applications by using Foundry SDKs and connectors
- Configure an application to connect to a Foundry project
2.2: Build agents by using Foundry
Covers defining agent roles, building agents with retrieval and memory, integrating agent tools, implementing multi-agent solutions, and monitoring deployed agents.
- Define agent roles, goals, conversation-tracking approach, and tool schemas
- Build agents that integrate retrieval, function-calling, and conversation memory
- Integrate agent tools, including APIs, knowledge stores, search, content understanding, and custom functions
- Implement orchestrated multi-agent solutions
- Build autonomous or semiautonomous workflows with safeguards and approval flow controls
- Integrate monitoring into deployed agents, evaluate agent behavior, and perform error analysis
2.3: Optimize and operationalize generative AI systems
Covers tuning generation behavior, implementing model reflection, setting up observability, and orchestrating multiple models or flows.
- Tune generation behavior, such as prompt engineering and adjusting model parameters
- Implement model reflection, chain-of-thought evaluations, and self-critique loops
- Set up observability by implementing tracing, token analytics, safety signals, and latency breakdowns
- Orchestrate multiple models, flows, or hybrid LLM and rules engines
Implement computer vision solutions (10–15%)
Covers designing and implementing image and video generation solutions, multimodal understanding workflows, and responsible AI for multimodal content. (10–15% of scored content)
3.1: Design and implement image- and video-generation solutions
Covers generating and editing images and videos from prompts and reference media using platform generation and editing controls.
- Implement a solution that generates images from text prompts and reference media
- Implement a solution that generates videos from text prompts and reference media
- Configure image-editing workflows, including inpainting, mask‑based edits, and prompt‑driven modifications
- Implement workflows to edit generated videos
- Select and apply appropriate generation and editing controls provided by the platform
3.2: Design and implement multimodal understanding workflows
Covers building solutions for visual context analysis, image captioning, visual question-answering, accessibility descriptions, video analysis, and object identification.
- Build a solution that analyzes visual context by using multimodal models
- Configure apps to produce concise or detailed captions for single or multiple images
- Implement a solution that enables question‑answering grounded in visual evidence
- Configure generation of alt‑text and extended image descriptions aligned to accessibility guidelines
- Implement visual understanding by configuring Azure Content Understanding in Foundry Tools to extract visual characteristics
- Implement video analysis workflows to process and interpret video segments
- Configure single‑task and pro‑mode Content Understanding pipelines
- Implement solutions that identify objects, components, or regions within images or video
3.3: Implement responsible AI for multimodal content
Covers implementing filters for unsafe visual content, detecting indirect prompt injection, and enforcing visual policy rules.
- 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
Implement text analysis solutions (10–15%)
Covers applying language model text analysis and implementing speech solutions using Azure AI services and Foundry Tools. (10–15% of scored content)
4.1: Apply language model text analysis
Covers extracting entities and summaries, detecting sentiment and safety issues, translating text, and customizing language model outputs for domain tasks.
- Implement solutions to extract entities, topics, summaries, and structured JSON outputs by using generative prompting and Foundry Tools
- Configure detection of sentiment, tone, safety issues, and sensitive content
- Build solutions that translate text by using Azure Translator in Foundry Tools or LLM‑powered translation flows
- Customize language model outputs for domain tasks, such as compliance summarization and domain extraction
4.2: Implement speech solutions
Covers converting speech to text and text to speech, integrating speech as an agent modality, enabling multimodal audio reasoning, and translating speech.
- Implement workflows to convert speech to text and text to speech for agentic interactions
- Integrate speech as an agent modality, including custom speech models
- Enable multimodal reasoning from audio inputs
- Translate speech into other languages by using language models and Foundry Tools
Implement information extraction solutions (10–15%)
Covers building retrieval and grounding pipelines and extracting content from documents using multimodal pipelines and Content Understanding. (10–15% of scored content)
5.1: Build retrieval and grounding pipelines
Covers ingesting and indexing content, configuring various search types, implementing enrichment, configuring RAG ingestion, and connecting retrieval pipelines to agent tools.
- Ingest and index content, such as documents, images, audio, and video
- Configure semantic search, hybrid search, and vector search for grounding
- Implement enrichment by using custom or built-in skills for text, images, and layout
- Configure RAG ingestion flow, including documents and using optical character recognition (OCR)
- Connect retrieval pipelines directly to workflows and agent tools
5.2: Extract content from documents
Covers extracting information using multimodal pipelines, producing grounded representations for agents and RAG, and implementing analyzers for structured outputs.
- Extract information by using multimodal pipelines that combine OCR, layout analysis, and field extraction
- Produce clean, grounded representations to use with agents and RAG by using Content Understanding
- Implement analyzers for generating structured or markdown outputs for downstream reasoning by using Content Understanding