🔒 Guided

Pre-launch preview. Authorised access only.

Incorrect code

Guided by A Guide to Cloud
Explore AB-900 AI-901
Guided AI-103 Domain 1
Domain 1 — Module 1 of 8 13%
1 of 27 overall

AI-103 Study Guide

Domain 1: Plan and Manage an Azure AI Solution

  • Choosing the Right AI Model Free
  • Foundry Services: Your AI Toolkit Free
  • Retrieval, Indexing & Agent Memory
  • Designing AI Infrastructure
  • Deploying Models & CI/CD
  • Quotas, Scaling & Cost
  • Monitoring & Security
  • Responsible AI: Filters, Auditing & Governance

Domain 2: Implement Generative AI and Agentic Solutions

  • Connecting Your App to Foundry Free
  • Building RAG Applications
  • Workflows & Reasoning Pipelines
  • Evaluating AI Models & Apps
  • Agent Fundamentals: Roles, Goals & Tools Free
  • Building Agents with Retrieval & Memory
  • Agent Tools & Knowledge Integration
  • Multi-Agent Orchestration & Safeguards
  • Agent Monitoring & Error Analysis
  • Prompt Engineering & Model Tuning
  • Observability & Production Operations

Domain 3: Implement Computer Vision Solutions

  • Image & Video Generation
  • Multimodal Visual Understanding
  • Responsible AI for Visual Content

Domain 4: Implement Text Analysis Solutions

  • Text Analysis with Language Models
  • Speech, Translation & Voice Agents

Domain 5: Implement Information Extraction Solutions

  • Ingestion, Indexing & Grounding Pipelines
  • Extracting Content with Content Understanding
  • Exam Prep: Putting It All Together

AI-103 Study Guide

Domain 1: Plan and Manage an Azure AI Solution

  • Choosing the Right AI Model Free
  • Foundry Services: Your AI Toolkit Free
  • Retrieval, Indexing & Agent Memory
  • Designing AI Infrastructure
  • Deploying Models & CI/CD
  • Quotas, Scaling & Cost
  • Monitoring & Security
  • Responsible AI: Filters, Auditing & Governance

Domain 2: Implement Generative AI and Agentic Solutions

  • Connecting Your App to Foundry Free
  • Building RAG Applications
  • Workflows & Reasoning Pipelines
  • Evaluating AI Models & Apps
  • Agent Fundamentals: Roles, Goals & Tools Free
  • Building Agents with Retrieval & Memory
  • Agent Tools & Knowledge Integration
  • Multi-Agent Orchestration & Safeguards
  • Agent Monitoring & Error Analysis
  • Prompt Engineering & Model Tuning
  • Observability & Production Operations

Domain 3: Implement Computer Vision Solutions

  • Image & Video Generation
  • Multimodal Visual Understanding
  • Responsible AI for Visual Content

Domain 4: Implement Text Analysis Solutions

  • Text Analysis with Language Models
  • Speech, Translation & Voice Agents

Domain 5: Implement Information Extraction Solutions

  • Ingestion, Indexing & Grounding Pipelines
  • Extracting Content with Content Understanding
  • Exam Prep: Putting It All Together
Domain 1: Plan and Manage an Azure AI Solution Free ⏱ ~12 min read

Choosing the Right AI Model

Not all AI models are created equal. Learn how to pick the right model for each task — LLMs, SLMs, multimodal models, and Foundry Tools — so you don't overspend or underperform.

Why model selection matters

☕ Simple explanation

Picking an AI model is like hiring for a job — you wouldn’t hire a brain surgeon to stack shelves, and you wouldn’t hire a shelf-stacker to do surgery.

Large language models (LLMs) like GPT-4o are powerful but expensive. Small language models (SLMs) like Phi-4 are cheaper and faster but less capable. Multimodal models handle images, audio, and video — not just text. And Foundry Tools are pre-built AI services you don’t need to train at all.

The exam tests whether you can match the right model to the right task — balancing cost, speed, accuracy, and capability.

Microsoft Foundry provides access to thousands of models through its model catalog. As an AI engineer, your job is to select the model that best fits each task based on multiple factors: capability requirements, latency targets, cost constraints, data privacy, and deployment topology.

The four main model categories you need to understand are:

  • Large language models (LLMs) — GPT-4o, GPT-4.1, Claude, Llama 3 — general-purpose reasoning, complex tasks
  • Small language models (SLMs) — Phi-4, Phi-4-mini, Mistral Small — lighter, cheaper, edge-deployable
  • Multimodal models — GPT-4o (vision+text), Llama 4 — handle text, images, audio, video in a single model
  • Foundry Tools — Azure AI Search, Content Understanding, Speech, Translator — pre-built services that don’t require model training

The four model categories

The four model categories in Microsoft Foundry
FeatureLLMsSLMsMultimodalFoundry Tools
What they doComplex reasoning, generation, analysisSimpler tasks, fast inferenceProcess text + images + audio + videoPre-built AI capabilities (search, OCR, speech)
ExamplesGPT-4o, GPT-4.1, Llama 3.3Phi-4, Phi-4-mini, Mistral SmallGPT-4o (vision), Llama 4Azure AI Search, Content Understanding, Translator
CostHigher (more tokens, more compute)Lower (smaller, faster)Medium-high (depends on modalities)Pay-per-use (no model hosting)
Best forAgents, RAG, complex workflowsEdge devices, high-volume simple tasksApps that need to see, hear, and readStructured tasks: search, OCR, translation
DeploymentCloud (Foundry hosted or serverless)Cloud or edgeCloudManaged service (no deployment needed)

When to use what — decision framework

The exam loves “which model should you use?” questions. Here’s the decision tree:

ScenarioBest ChoiceWhy
Complex multi-step reasoning with toolsLLM (GPT-4o, GPT-4.1)Needs strong reasoning and function-calling
Summarising thousands of support ticketsSLM (Phi-4)Simple task at high volume — cost matters
Analysing medical images alongside patient notesMultimodal (GPT-4o vision)Needs to process both text and images
Extracting invoice fields from scanned PDFsFoundry Tool (Content Understanding)Purpose-built for document extraction
Real-time speech transcription in a call centreFoundry Tool (Azure Speech)Dedicated speech service, optimised for streaming
Building a chatbot that searches company docsLLM + Foundry Tool (GPT-4o + Azure AI Search)Combine reasoning with retrieval
💡 Exam tip: The 'cheapest correct option' trap

The exam often presents scenarios where multiple models could work. The correct answer is usually the one that meets the requirements at the lowest cost and complexity.

For example: “A company needs to classify customer emails as positive, negative, or neutral.” You might think GPT-4o — but Phi-4 or even a Foundry sentiment analysis tool would be cheaper and sufficient. The exam rewards right-sizing, not over-engineering.

Meet the characters

Throughout this course, you’ll follow four teams building AI solutions:

CharacterWho They AreAI Use Cases
🏥 NeuralMedHealth-tech startup, 25 engineersAI diagnostic assistants, medical record extraction, patient chatbots
🏦 Atlas FinancialEnterprise bank, 3000 employeesCompliance agents, fraud detection, customer service bots
🚀 MediaForgeContent operations platform, 40 developersImage/video generation, marketing content pipelines, prompt optimisation
👨‍💻 KaiAI engineer at a logistics companyInfrastructure decisions, CI/CD for AI, deployment troubleshooting
ℹ️ Real-world example: Kai's model selection

Kai needs to build three features for the logistics platform:

  1. Package label OCR — reads shipping labels from photos → Content Understanding (Foundry Tool — purpose-built, no model hosting)
  2. Route optimisation chatbot — answers complex questions about delivery routes → GPT-4o (LLM — needs reasoning over structured data)
  3. Automated status updates — generates short “your package is on its way” messages → Phi-4-mini (SLM — simple generation, high volume, low cost)

Three features, three different model choices. That’s model selection in practice.

Foundry Tools vs models

A common exam confusion: Foundry Tools are not models you deploy — they’re managed services you call.

Foundry ToolWhat It DoesWhen to Use Instead of a Model
Azure AI SearchSemantic, vector, and hybrid searchWhen you need retrieval/grounding for RAG
Content UnderstandingOCR, layout analysis, field extraction from documentsWhen extracting structured data from PDFs, forms, images
Azure SpeechSpeech-to-text, text-to-speechWhen you need dedicated speech processing
Azure TranslatorText and document translationWhen you need reliable multilingual translation
💡 Exam tip: Foundry Tools vs prompting an LLM

The exam tests whether you know when to use a dedicated Foundry Tool versus prompting an LLM to do the same task. Key rule: if a Foundry Tool exists for the task, it’s usually the correct answer — it’s cheaper, more reliable, and purpose-built.

Example: “Translate a 500-page legal document from English to Japanese.” Answer: Azure Translator (Foundry Tool), NOT “prompt GPT-4o to translate.”

The model catalog and Model Router

Microsoft Foundry’s model catalog gives you access to 11,000+ models from OpenAI, Meta, Mistral, Anthropic, and more. You don’t have to use only Microsoft models.

Model Router is a deployable model in the Foundry catalog — you deploy it like any other model and call it via the Chat Completions API. It automatically selects the best underlying model for each request based on cost-performance trade-offs. Think of it as “auto-scaling for model intelligence” — simple requests get routed to cheaper models, complex ones to more capable models.

Key terms

Question

What is a Large Language Model (LLM)?

Click or press Enter to reveal answer

Answer

A neural network trained on vast text data that can understand and generate human language. Examples: GPT-4o, GPT-4.1, Llama 3.3. Best for complex reasoning, agents, and multi-step tasks.

Click to flip back

Question

What is a Small Language Model (SLM)?

Click or press Enter to reveal answer

Answer

A compact language model optimised for speed and cost over maximum capability. Examples: Phi-4, Phi-4-mini, Mistral Small. Best for high-volume simple tasks and edge deployment.

Click to flip back

Question

What is a multimodal model?

Click or press Enter to reveal answer

Answer

A model that can process multiple input types — text, images, audio, and video — in a single interaction. Example: GPT-4o with vision can analyse photos while answering questions about them.

Click to flip back

Question

What are Foundry Tools?

Click or press Enter to reveal answer

Answer

Pre-built Azure AI services (Search, Content Understanding, Speech, Translator) that you call as APIs. They don't require model deployment — you pay per use and they're optimised for specific tasks.

Click to flip back

Question

What is Model Router in Microsoft Foundry?

Click or press Enter to reveal answer

Answer

A deployable model in the Foundry catalog that you deploy and call like any other model. It automatically routes each request to the most cost-effective underlying model that can handle the task. Simple requests go to cheaper models; complex ones go to more capable models.

Click to flip back

Knowledge check

Knowledge Check

NeuralMed needs to extract patient names, dates of birth, and medication lists from scanned handwritten prescriptions. Which approach should they use?

Knowledge Check

Atlas Financial processes 50,000 customer emails daily and needs to classify each as 'complaint', 'enquiry', or 'compliment'. Which model type is most cost-effective?

Knowledge Check

MediaForge is building a content review tool that analyses both marketing images and their accompanying ad copy together. Which model type should they choose?

🎬 Video coming soon

Next →

Foundry Services: Your AI Toolkit

Guided

I learn, I simplify, I share.

A Guide to Cloud YouTube Feedback

© 2026 Sutheesh. All rights reserved.

Guided is an independent study resource and is not affiliated with, endorsed by, or officially connected to Microsoft. Microsoft, Azure, and related trademarks are property of Microsoft Corporation. Always verify information against Microsoft Learn.