🔒 Guided

Pre-launch preview. Authorised access only.

Incorrect code

Guided by A Guide to Cloud
Explore AB-900 AI-901
Guided AB-100 Domain 2
Domain 2 — Module 6 of 9 67%
13 of 29 overall

AB-100 Study Guide

Domain 1: Plan AI-Powered Business Solutions

  • Agent Requirements & Data Readiness
  • AI Strategy & the Cloud Adoption Framework
  • Multi-Agent Solution Design
  • Build, Buy, or Extend
  • Generative AI, Knowledge Sources & Prompt Engineering
  • Small Language Models & Model Selection
  • ROI, TCO & Business Case Analysis

Domain 2: Design AI-Powered Business Solutions

  • Copilot in D365 Customer Experience & Service
  • Agent Types: Task, Autonomous & Prompt/Response
  • Foundry Tools & Code-First Solutions
  • Copilot Studio: Topics, Flows & Prompt Actions
  • Power Apps, WAF & Data Processing
  • Extensibility: Custom Models, M365 Agents & Copilot Studio
  • MCP, Computer Use & Agent Behaviours
  • M365 Agents: Teams, SharePoint & Sales/Service in M365 Copilot
  • D365 AI Orchestration: Finance, SCM & Customer Experience

Domain 3: Deploy AI-Powered Business Solutions

  • Agent Monitoring: Tools, Metrics, and Processes
  • Telemetry Interpretation and Agent Tuning
  • Testing Strategy for AI Agents
  • Custom Model Validation and Prompt Best Practices
  • End-to-End Testing for Multi-App AI Solutions
  • ALM Foundations & Data Lifecycle for AI
  • ALM for Copilot Studio Agents
  • ALM for Microsoft Foundry Agents
  • ALM for D365 AI Features
  • Agent Security Free
  • Governance for AI Agents Free
  • Prompt Security & AI Vulnerabilities Free
  • Responsible AI & Audit Trails Free

AB-100 Study Guide

Domain 1: Plan AI-Powered Business Solutions

  • Agent Requirements & Data Readiness
  • AI Strategy & the Cloud Adoption Framework
  • Multi-Agent Solution Design
  • Build, Buy, or Extend
  • Generative AI, Knowledge Sources & Prompt Engineering
  • Small Language Models & Model Selection
  • ROI, TCO & Business Case Analysis

Domain 2: Design AI-Powered Business Solutions

  • Copilot in D365 Customer Experience & Service
  • Agent Types: Task, Autonomous & Prompt/Response
  • Foundry Tools & Code-First Solutions
  • Copilot Studio: Topics, Flows & Prompt Actions
  • Power Apps, WAF & Data Processing
  • Extensibility: Custom Models, M365 Agents & Copilot Studio
  • MCP, Computer Use & Agent Behaviours
  • M365 Agents: Teams, SharePoint & Sales/Service in M365 Copilot
  • D365 AI Orchestration: Finance, SCM & Customer Experience

Domain 3: Deploy AI-Powered Business Solutions

  • Agent Monitoring: Tools, Metrics, and Processes
  • Telemetry Interpretation and Agent Tuning
  • Testing Strategy for AI Agents
  • Custom Model Validation and Prompt Best Practices
  • End-to-End Testing for Multi-App AI Solutions
  • ALM Foundations & Data Lifecycle for AI
  • ALM for Copilot Studio Agents
  • ALM for Microsoft Foundry Agents
  • ALM for D365 AI Features
  • Agent Security Free
  • Governance for AI Agents Free
  • Prompt Security & AI Vulnerabilities Free
  • Responsible AI & Audit Trails Free
Domain 2: Design AI-Powered Business Solutions Premium ⏱ ~15 min read

Extensibility: Custom Models, M365 Agents & Copilot Studio

Design AI extensibility using custom Foundry models, M365 Copilot declarative agents with instructions, knowledge, and actions, and Copilot Studio plugins and connectors.

Three paths to extend AI capabilities

☕ Simple explanation

Think of prebuilt AI as a company car — it gets you where most people need to go.

Custom Foundry models are like building a custom vehicle for a specific job. Need an armoured truck for transporting cash? A refrigerated van for food delivery? You design and build it yourself because no off-the-shelf vehicle fits.

M365 Copilot agents are like adding a specialised GPS to the company car — it still uses the same engine (Microsoft 365 Copilot), but now it has custom instructions, maps (knowledge), and shortcuts (actions) for your specific business.

Copilot Studio extensibility is like adding aftermarket parts to the company car — custom connectors, extra tools, and plugins that make it do things the manufacturer didn’t plan for.

The AB-100 exam covers three distinct extensibility paths, each for different scenarios:

Custom Foundry models: Deploy and fine-tune models for domain-specific tasks where prebuilt capabilities are insufficient. This is the code-first path — requires ML expertise and infrastructure management.

M365 Copilot declarative agents: Extend Microsoft 365 Copilot with custom instructions, curated knowledge sources, and API-backed actions. No model training — you configure the agent’s behaviour on top of the existing Copilot engine.

Copilot Studio extensibility: Add custom connectors, actions, plugins, and external API integrations to Copilot Studio agents. This extends what the agent can DO, not what it KNOWS.

Comparing the three extensibility paths

Three extensibility paths in the Microsoft AI ecosystem
FeatureWhat You're ExtendingHow It WorksWhen to Choose It
Custom Foundry modelsThe AI model itself — custom training, fine-tuning, or deploying specialised modelsDeploy from the model catalogue, fine-tune with domain data, or build custom pipelines with prompt flowsWhen prebuilt models can't handle the domain-specific task — specialised classification, domain reasoning, or unique output formats
M365 Copilot agentsMicrosoft 365 Copilot's behaviour — adding custom instructions, knowledge, and actionsCreate declarative agents with a manifest that defines instructions, knowledge sources (SharePoint, web), and actions (API plugins)When users work in M365 and need Copilot to understand domain-specific knowledge or perform custom business actions
Copilot Studio extensibilityA Copilot Studio agent's capabilities — adding new tools, data sources, and integrationsAdd custom connectors, Power Automate actions, plugins, or external API endpoints to agent topicsWhen the Copilot Studio agent needs to interact with external systems, call APIs, or perform actions beyond its built-in connectors

Custom Foundry models

Use custom Foundry models when prebuilt AI capabilities don’t meet the requirement. Common scenarios:

ScenarioWhy CustomFoundry Approach
Credit risk scoring with proprietary algorithmsGeneric models lack domain-specific risk factorsFine-tune a model on historical credit decisions
Medical image analysisRequires specialised visual understandingDeploy a custom vision model trained on clinical images
Regulatory document classificationIndustry-specific taxonomy not covered by general NLUTrain a custom classifier with labelled regulatory documents
Multi-language customer intent for a niche industryStandard NLU models underperform on domain jargon in multiple languagesFine-tune a multilingual model with domain-specific training data

Architecture pattern: Deploy the custom model in Foundry → expose via a managed endpoint → consume from Copilot Studio, Power Apps, or D365 via a custom connector or API.

M365 Copilot declarative agents

Declarative agents extend Microsoft 365 Copilot without building a model. You declare:

  • Instructions — what the agent does, its persona, rules, and guardrails
  • Knowledge — where the agent looks for information (SharePoint sites, web URLs, files)
  • Actions — what the agent can do beyond answering questions (call APIs, trigger workflows)

Design decisions for declarative agents:

DecisionOptionsGuidance
ScopePersonal agent, shared agent, or org-wideStart narrow (team), expand after validation
Knowledge sourcesSharePoint, Graph connectors, web, filesKeep focused — too many sources dilute accuracy
Action complexitySimple (read data) or complex (write data, trigger processes)Start read-only. Add write actions after trust is established
GuardrailsInstructions that limit what the agent discussesAlways include “do not answer questions outside of…” instructions

Copilot Studio extensibility

Extend Copilot Studio agents to interact with the world beyond Microsoft’s built-in connectors:

  • Custom connectors — connect to any REST API (internal tools, SaaS platforms, databases)
  • Power Automate actions — trigger complex workflows that span multiple systems
  • Plugins — reusable capability packages that add skills to an agent
  • External API integration — direct HTTP calls to external services from within topics
💡 Scenario: Dev builds a custom credit risk model for Vanguard

Dev Patel (AI Platform Engineer at Vanguard Financial Group) designs a credit risk assessment solution. The prebuilt AI models can’t handle Vanguard’s proprietary risk scoring methodology.

Step 1 — Custom model: Dev fine-tunes a GPT model in Foundry with 10 years of anonymised credit decisions. The model learns Vanguard’s specific risk factors (industry exposure, counterparty relationships, regulatory capital requirements).

Step 2 — Evaluation: Runs the model against 500 known cases. Measures accuracy against human risk analyst decisions — achieves 91% agreement.

Step 3 — Deployment: Deploys the model as a managed endpoint in Foundry with content safety filters.

Step 4 — Copilot Studio integration: Natalie’s team builds a Copilot Studio agent for loan officers. When a loan officer asks “What’s the risk assessment for Application 4521?”, the agent:

  1. Retrieves the application from D365 Finance (custom connector)
  2. Calls the Foundry credit risk model (custom connector to the endpoint)
  3. Returns the risk score with reasoning

Step 5 — M365 Copilot agent: Adrienne wants the same capability in Teams. Dev creates a declarative agent that gives the investment team access to risk assessments directly in their M365 workflow — without leaving Teams.

Marcus Webb (CISO) reviews the architecture: all data stays within Vanguard’s tenant, the model endpoint is secured with managed identity, and every assessment is logged for audit.

💡 Exam tip: don't over-extend

The exam tests judgment on WHEN to use extensibility:

  • “Standard Copilot already does this well” → Don’t extend. Use prebuilt capabilities.
  • “The AI needs domain-specific knowledge that lives in SharePoint” → M365 declarative agent with knowledge source — no custom model needed.
  • “The AI needs to call a third-party API” → Copilot Studio custom connector or action — no custom model needed.
  • “The AI’s reasoning accuracy is insufficient for the domain” → Custom Foundry model with fine-tuning.

The simplest extensibility path that meets the requirement is usually the right answer.

Flashcards

Question

What are the three components of an M365 Copilot declarative agent?

Click or press Enter to reveal answer

Answer

Instructions (what the agent does, its persona and rules), Knowledge (where it looks for information — SharePoint, web, files), and Actions (what it can do — call APIs, trigger workflows). You declare these in a manifest — no model training required.

Click to flip back

Question

When should you choose a custom Foundry model over other extensibility options?

Click or press Enter to reveal answer

Answer

When prebuilt AI models cannot handle the domain-specific task — proprietary risk scoring, specialised image analysis, industry-specific classification, or custom reasoning that RAG alone doesn't achieve. Custom models require ML expertise, training data, and ongoing maintenance.

Click to flip back

Question

What forms of extensibility does Copilot Studio support?

Click or press Enter to reveal answer

Answer

Custom connectors (REST APIs), Power Automate actions (complex multi-system workflows), plugins (reusable capability packages), and external API integration (direct HTTP calls). These extend what the agent can DO — interact with systems beyond Microsoft's built-in connectors.

Click to flip back

Question

What is the key design principle for AI extensibility in the AB-100 exam?

Click or press Enter to reveal answer

Answer

Use the simplest extensibility path that meets the requirement. Don't build a custom model when a declarative agent with knowledge sources will do. Don't build a custom connector when a prebuilt connector exists. Extensibility adds complexity — justify every extension with a clear gap in prebuilt capabilities.

Click to flip back

Knowledge check

Knowledge Check

Adrienne wants to give Vanguard's compliance team an AI assistant that answers questions about the company's internal policies. The policies are stored in SharePoint. The assistant should work inside Teams. What is the most appropriate extensibility approach?

Knowledge Check

Dev needs to extend a Copilot Studio agent to check a customer's credit score from a third-party credit bureau API in real-time during a conversation. The API returns a JSON response with the score and risk factors. What extensibility approach should Dev use?

🎬 Video coming soon

Next up: MCP, Computer Use & Agent Behaviours — extending agents with Model Context Protocol, automating tasks with Computer Use, and designing reasoning and voice behaviours.

← Previous

Power Apps, WAF & Data Processing

Next →

MCP, Computer Use & Agent Behaviours

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.