Category: Azure AI

Agentic AI, AI, AI-103, Artificial Intelligence (AI), Azure AI, Generative AI, Microsoft Certification

Design workflows, tool-augmented flows, and multistep reasoning pipelines (AI-103 Exam Prep)

 
This post is a part of the AI-103: Develop AI Apps and Agents on Azure Exam Prep Hub. 
This topic falls under these sections:
Implement generative AI and agentic solutions (30–35%)
   --> Build generative applications by using Foundry
      --> Design workflows, tool-augmented flows, and multistep reasoning pipelines

Note that there are 10 practice questions (with answers and explanations) at the end of each section to help you solidify your knowledge of the material. Also, there are 2 practice tests with 60 questions each available from the hub's main page below the exam topics section.

Introduction

Modern AI systems are evolving beyond simple prompt-response interactions.

Today’s generative AI applications often:

  • Use external tools
  • Perform multistep reasoning
  • Orchestrate workflows
  • Retrieve enterprise data
  • Execute actions autonomously
  • Coordinate across services

These systems are commonly called:

  • Agentic systems
  • Tool-augmented AI systems
  • AI workflow pipelines

The AI-103: Develop AI Apps and Agents on Azure certification exam tests your understanding of designing intelligent workflows and reasoning pipelines.

For the AI-103 exam, you should understand:

  • AI workflows
  • Agent orchestration
  • Tool augmentation
  • Function calling
  • Multistep reasoning
  • Workflow pipelines
  • Retrieval integration
  • Memory integration
  • Planning and execution
  • Human-in-the-loop workflows
  • Monitoring and governance

What Are AI Workflows?

AI workflows are structured sequences of operations that combine:

  • AI reasoning
  • Data retrieval
  • Tool execution
  • Decision-making
  • Automation

Workflows coordinate multiple steps to complete complex tasks.

Why AI Workflows Matter

Simple prompts are often insufficient for:

  • Enterprise automation
  • Complex reasoning
  • Dynamic decision-making
  • Multi-system integration

Workflows allow AI systems to:

  • Break problems into steps
  • Use external tools
  • Validate outputs
  • Iterate toward solutions

What Is Tool Augmentation?

Tool augmentation allows AI systems to use external capabilities.

Examples include:

  • APIs
  • Databases
  • Search engines
  • Calculators
  • Business systems
  • Code interpreters

Why Tool Augmentation Is Important

Language models alone:

  • Cannot access real-time data
  • Cannot execute business actions directly
  • Cannot reliably perform all calculations

Tools extend AI capabilities.

Common Tool-Augmented Scenarios

Examples include:

  • Checking inventory
  • Booking appointments
  • Querying databases
  • Sending emails
  • Executing workflows
  • Calling REST APIs

What Is Function Calling?

Function calling enables models to:

  • Detect when a tool is needed
  • Generate structured tool requests
  • Invoke external services
  • Process returned results

Function Calling Workflow

Typical flow:

  1. User submits request
  2. Model determines tool requirement
  3. Model generates function call
  4. External tool executes
  5. Results return to model
  6. Model generates final response

Structured Tool Inputs

Function calling typically uses:

  • JSON schemas
  • Structured parameters
  • Validated inputs

This improves reliability.

Tool Selection

Agentic systems may dynamically choose:

  • Which tools to use
  • Which workflows to invoke
  • Which retrieval strategies to apply

Tool Orchestration

Tool orchestration coordinates multiple tools within a workflow.

Examples include:

  • Retrieval + summarization
  • Search + booking systems
  • Database queries + reporting

Sequential Workflows

Sequential workflows execute steps in order.

Example:

  1. Retrieve customer data
  2. Analyze account status
  3. Generate recommendations
  4. Send response

Parallel Workflows

Parallel workflows execute multiple tasks simultaneously.

Benefits include:

  • Faster execution
  • Better scalability
  • Reduced latency

Conditional Workflows

Conditional workflows branch based on:

  • User intent
  • Retrieved data
  • Safety evaluations
  • Confidence scores

What Is Multistep Reasoning?

Multistep reasoning breaks complex problems into smaller steps.

This improves:

  • Accuracy
  • Planning
  • Decision quality

Examples of Multistep Reasoning

Examples include:

  • Research workflows
  • Financial analysis
  • Travel planning
  • Technical troubleshooting

Chain-of-Thought Reasoning

Chain-of-thought reasoning encourages models to:

  • Reason step-by-step
  • Decompose problems
  • Validate intermediate steps

Planning and Execution Models

Agentic systems often separate:

  • Planning
  • Execution

The planner decides:

  • What steps are needed
  • Which tools to use

The executor performs actions.

Planner-Executor Architectures

Planner-executor architectures support:

  • Dynamic workflows
  • Adaptive reasoning
  • Task decomposition

ReAct Pattern

The ReAct (Reason + Act) pattern combines:

  • Reasoning
  • Tool usage
  • Observation
  • Iterative decision-making

Reflection and Self-Correction

Some systems support:

  • Self-evaluation
  • Output refinement
  • Error correction

Retrieval-Augmented Workflows

Workflows often integrate:

  • Vector search
  • RAG pipelines
  • Enterprise grounding

Memory in Agentic Systems

AI systems may use memory for:

  • Conversation history
  • User preferences
  • Workflow state
  • Long-running tasks

Short-Term Memory

Short-term memory stores:

  • Current conversation context
  • Immediate workflow information

Long-Term Memory

Long-term memory stores:

  • Persistent preferences
  • Historical interactions
  • Learned context

Workflow State Management

State management tracks:

  • Current task progress
  • Intermediate outputs
  • Pending actions

Human-in-the-Loop (HITL) Workflows

High-risk workflows may require:

  • Human approvals
  • Validation checkpoints
  • Escalation paths

Approval Gates

Approval gates can prevent:

  • Unsafe actions
  • Unauthorized tool usage
  • Harmful outputs

Safety and Governance

Organizations should enforce:

  • Tool restrictions
  • Permission boundaries
  • Safety filters
  • Approval workflows

Autonomous vs Semi-Autonomous Agents

Autonomous Agents

Can:

  • Make decisions independently
  • Execute workflows automatically

Semi-Autonomous Agents

Require:

  • Human review
  • Approval checkpoints

Workflow Monitoring

Organizations should monitor:

  • Tool usage
  • Failures
  • Safety violations
  • Latency
  • Costs

Trace Logging

Trace logging helps track:

  • Workflow execution
  • Tool calls
  • Reasoning steps
  • Agent decisions

Error Handling in Workflows

Workflow pipelines should handle:

  • API failures
  • Missing data
  • Timeout errors
  • Invalid outputs

Retry Strategies

Common retry strategies include:

  • Automatic retries
  • Fallback workflows
  • Alternative tool selection

Fallback Models

Applications may use fallback models when:

  • Primary models fail
  • Costs exceed thresholds
  • Latency becomes excessive

Workflow Optimization

Optimization strategies include:

  • Parallel processing
  • Caching
  • Smaller models
  • Efficient retrieval

Latency Considerations

Complex workflows may increase latency due to:

  • Multiple model calls
  • Tool invocations
  • Retrieval operations

Cost Considerations

Tool-augmented systems may increase:

  • Token usage
  • API calls
  • Infrastructure costs

Azure AI Foundry Workflow Capabilities

Azure AI Foundry supports:

  • Model orchestration
  • Tool integration
  • Agent workflows
  • Evaluation pipelines
  • Monitoring

Common AI-103 Workflow Scenarios

Scenario 1: Enterprise Research Assistant

Requirements:

  • Multi-document retrieval
  • Summarization
  • Citation generation

Recommended Workflow:

  • RAG + multistep reasoning

Scenario 2: Customer Service Agent

Requirements:

  • CRM access
  • Ticket management
  • Escalation workflows

Recommended Workflow:

  • Tool-augmented agent

Scenario 3: Financial Approval System

Requirements:

  • Risk evaluation
  • Human approvals
  • Audit logging

Recommended Workflow:

  • HITL approval pipeline

Scenario 4: AI Coding Assistant

Requirements:

  • Code generation
  • Code execution
  • Documentation retrieval

Recommended Workflow:

  • Code model + tool orchestration

Common AI-103 Exam Tips

Understand Workflow Patterns

Know:

  • Sequential workflows
  • Parallel workflows
  • Conditional workflows

Learn Tool-Augmented AI Concepts

Understand:

  • Function calling
  • Tool orchestration
  • Dynamic tool selection

Understand Multistep Reasoning

Know:

  • Chain-of-thought reasoning
  • Planner-executor patterns
  • ReAct workflows

Learn Governance Concepts

Understand:

  • HITL workflows
  • Approval gates
  • Monitoring
  • Trace logging

Summary

Modern AI applications increasingly rely on:

  • Workflow orchestration
  • Tool augmentation
  • Multistep reasoning
  • Agentic architectures

For the AI-103 exam, you should understand:

  • AI workflow design
  • Function calling
  • Tool orchestration
  • Sequential and parallel workflows
  • Multistep reasoning
  • Planner-executor architectures
  • ReAct patterns
  • Memory integration
  • HITL workflows
  • Monitoring and governance

These concepts enable organizations to build:

  • Intelligent
  • Autonomous
  • Scalable
  • Governed AI systems

They are foundational for modern generative AI and agentic solutions on Azure.

Practice Exam Questions

Question 1

What is the primary purpose of tool augmentation in AI systems?

A. Reduce storage costs
B. Extend model capabilities using external tools
C. Eliminate prompts
D. Replace vector search

Answer

B. Extend model capabilities using external tools

Explanation

Tool augmentation enables AI systems to interact with APIs, databases, and other services.

Question 2

What does function calling enable a model to do?

A. Generate only static responses
B. Invoke external tools using structured inputs
C. Eliminate workflows
D. Replace embeddings

Answer

B. Invoke external tools using structured inputs

Explanation

Function calling allows models to interact with external services.

Question 3

Which workflow type executes tasks simultaneously?

A. Sequential workflow
B. Parallel workflow
C. Manual workflow
D. Static workflow

Answer

B. Parallel workflow

Explanation

Parallel workflows improve speed by running tasks concurrently.

Question 4

What is multistep reasoning?

A. Compressing vector indexes
B. Breaking complex tasks into smaller reasoning steps
C. Increasing GPU memory
D. Reducing prompt size only

Answer

B. Breaking complex tasks into smaller reasoning steps

Explanation

Multistep reasoning improves problem-solving accuracy.

Question 5

What does the ReAct pattern combine?

A. Compression and storage
B. Reasoning and acting
C. Replication and scaling
D. Encryption and backup

Answer

B. Reasoning and acting

Explanation

ReAct combines reasoning steps with tool usage.

Question 6

What is the purpose of workflow state management?

A. Monitor GPU temperature
B. Track task progress and intermediate outputs
C. Disable logging
D. Replace semantic search

Answer

B. Track task progress and intermediate outputs

Explanation

State management helps maintain workflow continuity.

Question 7

Which architecture separates planning from execution?

A. Static inference architecture
B. Planner-executor architecture
C. Batch storage architecture
D. Compression architecture

Answer

B. Planner-executor architecture

Explanation

Planner-executor systems divide reasoning and execution responsibilities.

Question 8

Why are approval gates important in AI workflows?

A. They increase vector dimensions
B. They prevent unsafe or unauthorized actions
C. They reduce indexing speed
D. They eliminate monitoring requirements

Answer

B. They prevent unsafe or unauthorized actions

Explanation

Approval gates enforce governance and human oversight.

Question 9

Which concept allows AI systems to remember previous interactions?

A. Semantic ranking
B. Memory integration
C. Static chunking
D. GPU partitioning

Answer

B. Memory integration

Explanation

Memory enables contextual continuity and long-running workflows.

Question 10

What is a major challenge of complex AI workflows?

A. Eliminating all costs
B. Increased latency from multiple operations
C. Removing all need for monitoring
D. Preventing all hallucinations automatically

Answer

B. Increased latency from multiple operations

Explanation

Complex workflows may require multiple model calls and tool executions.

Go to the AI-103 Exam Prep Hub main page

AI, AI-103, Azure AI, Microsoft Certification

Implement Retrieval-Augmented Generation (RAG) in an application (AI-103 Exam Prep)

 
This post is a part of the AI-103: Develop AI Apps and Agents on Azure Exam Prep Hub. 
This topic falls under these sections:
Implement generative AI and agentic solutions (30–35%)
   --> Build generative applications by using Foundry
      --> Implement Retrieval-Augmented Generation (RAG) in an application

Note that there are 10 practice questions (with answers and explanations) at the end of each section to help you solidify your knowledge of the material. Also, there are 2 practice tests with 60 questions each available from the hub's main page below the exam topics section.

Introduction

Large language models (LLMs) are powerful, but they have limitations.

LLMs may:

  • Hallucinate information
  • Generate outdated responses
  • Lack organization-specific knowledge
  • Produce unverifiable answers

Retrieval-Augmented Generation (RAG) addresses these issues by combining:

  • Information retrieval
  • Vector search
  • Enterprise knowledge grounding
  • Generative AI

The AI-103: Develop AI Apps and Agents on Azure certification exam tests your understanding of how to implement RAG-based applications.

For the AI-103 exam, you should understand:

  • RAG architecture
  • Vector search
  • Embeddings
  • Chunking strategies
  • Indexing
  • Semantic search
  • Grounding techniques
  • Prompt augmentation
  • Retrieval pipelines
  • RAG optimization
  • Monitoring and evaluation
  • Security considerations

What Is Retrieval-Augmented Generation (RAG)?

RAG is an AI architecture that combines:

  1. Information retrieval
  2. Context augmentation
  3. Generative AI

Instead of relying only on model training data, RAG retrieves relevant information from external sources and injects it into prompts.

Why RAG Matters

RAG improves:

  • Accuracy
  • Grounding
  • Freshness of information
  • Enterprise knowledge integration
  • Explainability

Common RAG Use Cases

Typical RAG applications include:

  • Enterprise chatbots
  • Knowledge assistants
  • Internal documentation search
  • Customer support systems
  • Research assistants
  • AI copilots

Core Components of a RAG System

A RAG solution typically includes:

  • Data sources
  • Chunking pipeline
  • Embedding model
  • Vector database or search index
  • Retrieval engine
  • Large language model
  • Prompt orchestration layer

RAG Workflow Overview

The general workflow is:

  1. Ingest data
  2. Split data into chunks
  3. Generate embeddings
  4. Store embeddings in an index
  5. Receive user query
  6. Convert query to embeddings
  7. Retrieve relevant chunks
  8. Add retrieved context to prompt
  9. Generate grounded response

What Are Embeddings?

Embeddings are numerical vector representations of data.

Embeddings capture:

  • Semantic meaning
  • Contextual similarity
  • Relationships between concepts

Embedding Models

Embedding models convert:

  • Text
  • Documents
  • Queries

Into vectors for similarity comparison.

Vector Similarity Search

Vector search identifies content that is semantically similar.

Unlike keyword search, vector search understands:

  • Meaning
  • Intent
  • Context

What Is Chunking?

Chunking divides documents into smaller sections.

Chunking is essential because:

  • Models have token limits
  • Smaller chunks improve retrieval precision
  • Large documents are difficult to process efficiently

Chunking Strategies

Common chunking methods include:

  • Fixed-size chunking
  • Sliding window chunking
  • Semantic chunking
  • Paragraph-based chunking

Fixed-Size Chunking

Documents are split into equal-sized chunks.

Advantages:

  • Simple
  • Predictable

Disadvantages:

  • May break context unexpectedly

Sliding Window Chunking

Chunks overlap partially.

Benefits include:

  • Better context preservation
  • Improved retrieval continuity

Semantic Chunking

Semantic chunking groups logically related content.

Advantages:

  • Better contextual integrity
  • Higher retrieval quality

Metadata in RAG Systems

Metadata may include:

  • Document title
  • Author
  • Date
  • Category
  • Security labels

Metadata improves filtering and retrieval.

Indexing in RAG Systems

Indexes store:

  • Embeddings
  • Metadata
  • Searchable content

Indexes enable efficient retrieval.

Vector Databases and Search Indexes

RAG systems commonly use:

  • Azure AI Search
  • Vector indexes
  • Hybrid search systems

Semantic Search

Semantic search improves relevance using:

  • Meaning
  • Intent
  • Natural language understanding

Hybrid Search

Hybrid search combines:

  • Keyword search
  • Semantic ranking
  • Vector similarity search

This often improves retrieval quality.

Retrieval Pipelines

Retrieval pipelines:

  • Process user queries
  • Retrieve relevant information
  • Rank search results
  • Filter irrelevant content

Query Embeddings

User queries are converted into embeddings.

The query vector is compared against stored vectors.

Similarity Metrics

Common similarity calculations include:

  • Cosine similarity
  • Euclidean distance
  • Dot product similarity

Top-K Retrieval

Top-K retrieval returns the most relevant results.

Choosing the right K value is important:

  • Too few results may miss context
  • Too many results may add noise

Prompt Augmentation

Retrieved content is inserted into prompts.

This process is called:

  • Prompt grounding
  • Context injection
  • Prompt augmentation

Grounded Responses

Grounded responses:

  • Reference trusted data
  • Reduce hallucinations
  • Improve reliability

System Prompts in RAG

System prompts may instruct the model to:

  • Use only retrieved sources
  • Cite references
  • Avoid unsupported claims

Citation Generation

Many RAG applications provide:

  • Source references
  • Citations
  • Linked documents

This improves transparency.

Hallucination Reduction

RAG reduces hallucinations by:

  • Providing factual context
  • Using enterprise knowledge
  • Restricting unsupported generation

RAG Architecture Patterns

Common patterns include:

  • Basic RAG
  • Hybrid RAG
  • Multi-stage retrieval
  • Agentic RAG

Basic RAG

Basic RAG:

  • Retrieves documents
  • Injects them into prompts
  • Generates responses

Hybrid RAG

Hybrid RAG combines:

  • Vector search
  • Keyword search
  • Semantic ranking

Multi-Stage Retrieval

Multi-stage retrieval uses:

  • Initial retrieval
  • Re-ranking
  • Filtering
  • Secondary refinement

Agentic RAG

Agentic RAG systems may:

  • Choose retrieval tools dynamically
  • Perform iterative searches
  • Validate retrieved data
  • Orchestrate workflows

Azure AI Search in RAG

Azure AI Search commonly provides:

  • Vector search
  • Semantic ranking
  • Hybrid search
  • Index management

Data Ingestion Pipelines

RAG ingestion pipelines may process:

  • PDFs
  • Web pages
  • Databases
  • Office documents
  • Structured data

Data Freshness

Organizations should ensure indexes remain current.

Strategies include:

  • Scheduled reindexing
  • Incremental ingestion
  • Event-driven updates

Access Control in RAG

Enterprise RAG systems should enforce:

  • Role-based access
  • Document-level security
  • Identity-aware retrieval

Security Considerations

Organizations should secure:

  • Data ingestion pipelines
  • Search indexes
  • Embedding endpoints
  • Model endpoints

Monitoring RAG Systems

Organizations should monitor:

  • Retrieval quality
  • Grounding quality
  • Latency
  • Hallucinations
  • Search relevance

Evaluating RAG Performance

Key evaluation metrics include:

  • Precision
  • Recall
  • Relevance
  • Groundedness
  • Citation accuracy

Groundedness Evaluation

Groundedness measures whether responses are supported by retrieved content.

Retrieval Quality Evaluation

Organizations should evaluate:

  • Search result relevance
  • Ranking effectiveness
  • Missing context

Latency Optimization

RAG pipelines can introduce additional latency.

Optimization strategies include:

  • Caching
  • Smaller embeddings
  • Efficient indexing
  • Query optimization

Cost Optimization

Cost reduction strategies include:

  • Limiting retrieved chunks
  • Smaller embedding models
  • Efficient indexing
  • Intelligent caching

Responsible AI Considerations

Developers should:

  • Validate sources
  • Prevent data leakage
  • Monitor hallucinations
  • Enforce safety policies

Common AI-103 RAG Scenarios

Scenario 1: Enterprise Knowledge Chatbot

Requirements:

  • Internal document access
  • Accurate answers
  • Source citations

Recommended Solution:

  • RAG with Azure AI Search

Scenario 2: Legal Document Assistant

Requirements:

  • High factual accuracy
  • Traceability
  • Large document support

Recommended Solution:

  • Semantic chunking
  • Hybrid search
  • Citation generation

Scenario 3: Customer Support Copilot

Requirements:

  • Fast retrieval
  • Grounded answers
  • Updated knowledge

Recommended Solution:

  • Incremental indexing
  • Real-time retrieval

Scenario 4: Agentic AI Workflow

Requirements:

  • Dynamic retrieval
  • Multi-step reasoning
  • Tool orchestration

Recommended Solution:

  • Agentic RAG architecture

Common AI-103 Exam Tips

Understand the RAG Workflow

Know all stages:

  • Ingestion
  • Chunking
  • Embeddings
  • Indexing
  • Retrieval
  • Prompt augmentation
  • Generation

Learn Embedding Concepts

Understand:

  • Semantic vectors
  • Similarity search
  • Embedding models

Understand Search Types

Know the differences between:

  • Keyword search
  • Vector search
  • Semantic search
  • Hybrid search

Understand Grounding

Know how grounding:

  • Reduces hallucinations
  • Improves factual accuracy
  • Supports explainability

Summary

Retrieval-Augmented Generation (RAG) is one of the most important generative AI architectures.

For the AI-103 exam, you should understand:

  • RAG architecture
  • Embeddings
  • Chunking
  • Indexing
  • Vector search
  • Semantic search
  • Hybrid search
  • Prompt grounding
  • Retrieval pipelines
  • Groundedness evaluation
  • Security considerations
  • Monitoring and optimization

RAG enables organizations to build:

  • Accurate
  • Explainable
  • Grounded
  • Enterprise-aware AI applications

These concepts are foundational for modern AI systems on Azure.

Practice Exam Questions

Question 1

What is the primary goal of Retrieval-Augmented Generation (RAG)?

A. Reduce storage replication
B. Improve factual grounding using retrieved data
C. Eliminate vector search
D. Replace all language models

Answer

B. Improve factual grounding using retrieved data

Explanation

RAG improves accuracy by injecting retrieved information into prompts.

Question 2

What are embeddings?

A. GPU drivers
B. Numerical vector representations of data
C. Network security policies
D. Storage replication methods

Answer

B. Numerical vector representations of data

Explanation

Embeddings represent semantic meaning as vectors.

Question 3

Why is chunking important in RAG systems?

A. To increase network latency
B. To divide documents into manageable sections
C. To disable semantic search
D. To eliminate embeddings

Answer

B. To divide documents into manageable sections

Explanation

Chunking improves retrieval efficiency and contextual relevance.

Question 4

Which search method understands semantic meaning instead of exact keywords?

A. Static indexing
B. Vector search
C. Archive retrieval
D. Compression balancing

Answer

B. Vector search

Explanation

Vector search retrieves semantically similar content.

Question 5

What does hybrid search combine?

A. GPU clusters and storage accounts
B. Keyword search and vector search
C. Virtual machines and containers
D. Authentication and authorization

Answer

B. Keyword search and vector search

Explanation

Hybrid search combines lexical and semantic retrieval methods.

Question 6

What is prompt augmentation?

A. Increasing storage capacity
B. Adding retrieved context to prompts
C. Compressing vectors
D. Removing metadata

Answer

B. Adding retrieved context to prompts

Explanation

Prompt augmentation injects retrieved content into model prompts.

Question 7

What is groundedness?

A. GPU allocation efficiency
B. Whether responses are supported by retrieved sources
C. Network bandwidth usage
D. Storage replication speed

Answer

B. Whether responses are supported by retrieved sources

Explanation

Groundedness measures factual support from retrieved content.

Question 8

Which Azure service is commonly used for vector and semantic search in RAG systems?

A. Azure AI Search
B. Azure DNS
C. Azure Backup
D. Azure Batch

Answer

A. Azure AI Search

Explanation

Azure AI Search supports vector, semantic, and hybrid search.

Question 9

What is a major advantage of semantic chunking?

A. It eliminates embeddings
B. It preserves contextual meaning better
C. It disables retrieval
D. It reduces authentication requirements

Answer

B. It preserves contextual meaning better

Explanation

Semantic chunking groups logically related content.

Question 10

Which metric evaluates whether retrieved results are relevant?

A. Groundedness
B. Retrieval quality
C. GPU utilization
D. Storage redundancy

Answer

B. Retrieval quality

Explanation

Retrieval quality measures the relevance of retrieved documents.

Go to the AI-103 Exam Prep Hub main page