🔒 Guided

Pre-launch preview. Authorised access only.

Incorrect code

Guided by A Guide to Cloud
Explore AB-900 AI-901
Guided AI-103 Domain 2
Domain 2 — Module 10 of 11 91%
18 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 2: Implement Generative AI and Agentic Solutions Premium ⏱ ~12 min read

Prompt Engineering & Model Tuning

The difference between a good AI response and a great one is often the prompt. Learn how to tune generation behaviour, engineer effective prompts, and implement self-critique techniques like chain-of-thought and reflection.

Tuning AI behaviour

☕ Simple explanation

A model is like a talented musician — it can play anything, but it needs direction. Prompt engineering is the sheet music. Model parameters are the volume and tempo knobs.

The same model can give wildly different responses depending on how you ask (prompt) and what settings you use (temperature, max tokens, etc.). Mastering these controls is what separates a demo from a production AI app.

AI output quality depends on two control surfaces:

  • Prompt engineering — crafting instructions that guide the model’s reasoning and output format
  • Model parameters — numerical settings that control generation behaviour (temperature, top_p, max_tokens, etc.)

Advanced techniques like chain-of-thought and self-critique loops add a third dimension: reasoning quality — helping the model think better, not just respond differently.

Model parameters

ParameterWhat It ControlsRangeDefaultWhen to Adjust
TemperatureRandomness/creativity0.0 - 2.0~1.0Lower for factual tasks, higher for creative
Top PDiversity of token selection0.0 - 1.0~1.0Lower to constrain vocabulary, higher for variety
Max tokensMaximum response length1 - model limitVariesSet to prevent runaway responses
Frequency penaltyReduces repetition of tokens0.0 - 2.00Increase if responses are repetitive
Presence penaltyEncourages new topics0.0 - 2.00Increase for more diverse content
Stop sequencesTokens that end generationCustom stringsNoneUse to control output format
💡 Exam tip: Temperature is the most tested parameter

Temperature exam questions follow a pattern:

  • Temperature 0 = deterministic, same input gives same output. Best for: factual Q&A, extraction, classification
  • Temperature 0.3-0.7 = balanced. Best for: most production applications
  • Temperature 1.0+ = creative, varied. Best for: brainstorming, creative writing, diverse options

If the scenario needs consistency and accuracy, the answer is low temperature. If it needs creativity and variety, the answer is higher temperature.

Prompt engineering techniques

TechniqueWhat It DoesExample
System promptSets the model’s role, rules, and context”You are a compliance analyst. Always cite regulations.”
Few-shotProvides example input/output pairs”Q: What is DLP? A: Data Loss Prevention prevents…”
Chain-of-thoughtAsks model to show reasoning steps”Think step by step before answering.”
Output formattingSpecifies response structure”Respond in JSON format with fields: answer, confidence, sources”
Grounding instructionConstrains model to use provided context”Answer ONLY from the provided documents.”
PersonaGives the model a specific expert identity”You are a senior Azure architect with 15 years experience.”

Chain-of-thought and self-critique

Advanced reasoning techniques that improve output quality:

Advanced reasoning techniques
FeatureChain-of-ThoughtSelf-CritiqueReflection
What it isModel explains its reasoning step by stepModel reviews its own response and identifies errorsModel evaluates whether it achieved the task goal
How to trigger'Think step by step''Review your response. Are there any errors?''Did your answer fully address the question? What did you miss?'
Best forComplex reasoning, math, multi-step problemsCatching factual errors and inconsistenciesEnsuring completeness and accuracy
CostMore tokens (reasoning + answer)Double the tokens (answer + review)Additional tokens for evaluation step
ℹ️ Real-world example: Atlas Financial's self-critique loop

Atlas Financial’s compliance agent uses a two-pass approach:

Pass 1: Generate assessment

  • Agent reviews loan application against regulations
  • Produces initial compliance assessment with citations

Pass 2: Self-critique

  • Same agent reviews its own assessment with the prompt: “Review your compliance assessment. Check: (1) Are all citations accurate? (2) Did you miss any applicable regulations? (3) Is the risk assessment justified?”
  • Agent corrects errors and fills gaps

Result: 23% reduction in false compliance flags after adding the self-critique loop. The extra tokens are worth it for high-stakes financial decisions.

Key terms

Question

What is temperature in model parameters?

Click or press Enter to reveal answer

Answer

A number (0-2) controlling response randomness. Temperature 0 = deterministic (same input = same output). Temperature 1+ = more creative and varied. Lower for factual tasks, higher for creative tasks.

Click to flip back

Question

What is chain-of-thought prompting?

Click or press Enter to reveal answer

Answer

A technique where you instruct the model to explain its reasoning step by step before giving the final answer. Improves accuracy on complex reasoning tasks by forcing the model to 'show its work.'

Click to flip back

Question

What is a self-critique loop?

Click or press Enter to reveal answer

Answer

A pattern where the model generates a response, then reviews its own response to identify and correct errors. Costs more tokens but significantly improves accuracy for high-stakes outputs.

Click to flip back

Knowledge check

Knowledge Check

MediaForge's content generation tool produces the same headline every time for similar briefs. The marketing team wants more creative variety. Which parameter should they adjust?

Knowledge Check

NeuralMed's patient chatbot sometimes makes reasoning errors when answering multi-step medical questions (e.g., 'If the patient has condition A AND takes medication B, what are the risks?'). Which technique would most improve accuracy?

🎬 Video coming soon

← Previous

Agent Monitoring & Error Analysis

Next →

Observability & Production Operations

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.