Microsoft Certified: Azure AI Apps and Agents Developer

1.1 Choose the appropriate Foundry services

• · Select generative models by class — LLMs, small language models, multimodal models, code models
• · Choose Foundry services for grounding, vector search, agent workflows, and multimodal processing
• · Distinguish Foundry Tools (prebuilt point-solution APIs) from Foundry Agent Service (the agent runtime)
• · Select retrieval and indexing methods appropriate to the data and latency requirements
• · Choose memory, tool, and knowledge integration patterns for agents

1.2 Design and deploy AI infrastructure

• · Design Azure infrastructure for hosting AI apps and agents
• · Choose deployment options for models and agents (managed, serverless, standard vs provisioned)
• · Configure model and agent deployments in a Foundry project
• · Integrate CI/CD pipelines for promoting Foundry project deployments across environments

1.3 Manage cost, scale, and performance

• · Manage quotas, scaling, and rate limits (throttling) as distinct from cost management (billing)
• · Right-size cost footprints for model and agent workloads
• · Monitor model performance, drift, safety events, and grounding quality in production
• · Monitor data ingestion quality, search index health, and retrieval relevance

1.4 Secure an AI solution

• · Configure managed identity and keyless credentials (credential-free auth via Azure AD, not no-auth)
• · Configure private networking to isolate Foundry endpoints
• · Apply role-based access policies for projects, deployments, and connections

1.5 Apply responsible AI controls

• · Configure safety filters, guardrails, risk detection, and content moderation
• · Run evaluators and safety evaluations (pre-deployment) vs production monitoring
• · Enable explanation tooling, trace logging, and provenance metadata
• · Design approval workflows and agent oversight modes, constraints, and tool-access controls

2.1 Build generative AI applications with Foundry

• · Deploy and consume LLMs, small language models, code models, and multimodal models
• · Implement retrieval-augmented generation (RAG) against grounded knowledge
• · Design tool-augmented and multistep reasoning workflows
• · Evaluate models for fabrications, relevance, quality, and safety
• · Integrate via Foundry SDKs and connectors; configure app-to-Foundry-project connections

2.2 Build agents with Foundry Agent Service

• · Define agent roles, goals, conversation tracking, and tool schemas
• · Integrate retrieval, function calling, and memory into an agent
• · Integrate agent tools — APIs, knowledge stores, Azure AI Search, Content Understanding, custom functions
• · Implement orchestrated multi-agent solutions (router/planner, sequential handoff, parallel/concurrent)
• · Build autonomous and semiautonomous workflows with safeguards and approval flows

3.1 Generate and edit visual content

• · Generate images and video from text and reference media
• · Edit images — inpainting (fill masked regions), mask-based targeted edits, prompt-driven modifications
• · Implement video editing workflows and generation/editing controls

3.2 Implement multimodal understanding

• · Analyze visual context and caption single or multiple images
• · Implement visual question answering over images
• · Generate accessibility alt-text (concise) and extended descriptions
• · Extract visual characteristics with Azure Content Understanding (single-task vs pro-mode pipelines)
• · Run video analysis workflows and object/region identification

3.3 Apply responsible AI for multimodal content

• · Filter unsafe and disallowed visual content
• · Defend against indirect prompt injection via text embedded in images
• · Enforce visual policy rules — watermarks, prohibited symbols, brand usage, inappropriate content detection

4.1 Analyze text with language models and Foundry Tools

• · Extract entities, topics, summaries, and structured JSON via generative prompting and Foundry Tools
• · Detect sentiment, tone, safety, and sensitive content as distinct classification tasks
• · Translate with Azure Translator in Foundry Tools or with LLM-powered translation flows
• · Customize for domains (e.g., compliance summarization)

4.2 Implement speech solutions

• · Implement speech-to-text and text-to-speech for agentic interactions
• · Use speech as a first-class agent modality, including custom speech models for domain jargon
• · Perform multimodal reasoning from audio input
• · Implement speech translation via language models or Foundry Tools

5.1 Build retrieval and grounding pipelines

• · Ingest and index documents, images, audio, and video for grounding
• · Implement semantic, vector, and hybrid search with Azure AI Search
• · Enrich indexing with built-in skills (native) and custom skills (hosted function/API)
• · Design RAG ingestion flows including OCR, chunking, embeddings, and grounding metadata
• · Connect retrieval pipelines to workflows and agent tools

5.2 Extract information from documents

• · Combine OCR, layout analysis, and field extraction as distinct pipeline stages
• · Build multimodal extraction pipelines with Azure AI Document Intelligence
• · Produce grounded representations via Content Understanding for agents and RAG
• · Configure analyzers for structured and markdown outputs