🔒 Guided

Pre-launch preview. Authorised access only.

Incorrect code

Guided by A Guide to Cloud
Explore AB-900 AI-901
Guided AB-900 Domain 3
Domain 3 — Module 5 of 8 63%
25 of 28 overall

AB-900 Study Guide

Domain 1: M365 Core Features & Objects

  • Welcome to Microsoft 365
  • Exchange Online: Mailboxes & Distribution
  • SharePoint: Sites, Libraries & Permissions
  • Microsoft Teams: Teams, Channels & Policies
  • Users, Groups & Licensing
  • Zero Trust: Never Trust, Always Verify
  • Authentication: Passwords, MFA & Beyond
  • Microsoft Defender XDR
  • Microsoft Entra: Your Identity Hub
  • PIM, Audit Logs & Identity Governance

Domain 2: Data Protection & Governance

  • Microsoft Purview: The Big Picture
  • Sensitivity Labels & Data Classification
  • Data Loss Prevention (DLP)
  • Insider Risk & Communication Compliance
  • DSPM for AI & Data Lifecycle
  • How Copilot Accesses Your Data
  • Responsible AI Principles
  • Compliance Manager & eDiscovery
  • Activity Explorer & Data Monitoring
  • Oversharing in SharePoint

Domain 3: Copilot & Agent Admin

  • What is Microsoft 365 Copilot? Free
  • What Are Agents? Free
  • Copilot vs Agents: When to Use Which Free
  • Copilot Licensing: Monthly vs Pay-as-You-Go Free
  • Researcher, Analyst & Real-World Use Cases Free
  • Managing Copilot: Billing, Monitoring & Prompts Free
  • Building Agents: Create, Test & Publish Free
  • Agent Lifecycle: Access, Approval & Monitoring Free

AB-900 Study Guide

Domain 1: M365 Core Features & Objects

  • Welcome to Microsoft 365
  • Exchange Online: Mailboxes & Distribution
  • SharePoint: Sites, Libraries & Permissions
  • Microsoft Teams: Teams, Channels & Policies
  • Users, Groups & Licensing
  • Zero Trust: Never Trust, Always Verify
  • Authentication: Passwords, MFA & Beyond
  • Microsoft Defender XDR
  • Microsoft Entra: Your Identity Hub
  • PIM, Audit Logs & Identity Governance

Domain 2: Data Protection & Governance

  • Microsoft Purview: The Big Picture
  • Sensitivity Labels & Data Classification
  • Data Loss Prevention (DLP)
  • Insider Risk & Communication Compliance
  • DSPM for AI & Data Lifecycle
  • How Copilot Accesses Your Data
  • Responsible AI Principles
  • Compliance Manager & eDiscovery
  • Activity Explorer & Data Monitoring
  • Oversharing in SharePoint

Domain 3: Copilot & Agent Admin

  • What is Microsoft 365 Copilot? Free
  • What Are Agents? Free
  • Copilot vs Agents: When to Use Which Free
  • Copilot Licensing: Monthly vs Pay-as-You-Go Free
  • Researcher, Analyst & Real-World Use Cases Free
  • Managing Copilot: Billing, Monitoring & Prompts Free
  • Building Agents: Create, Test & Publish Free
  • Agent Lifecycle: Access, Approval & Monitoring Free
Domain 3: Copilot & Agent Admin Free ⏱ ~13 min read

Researcher, Analyst & Real-World Use Cases

Microsoft built specialist agents for knowledge discovery and data analysis. Knowing when to recommend Researcher, Analyst, a prebuilt agent, or a custom agent is a core exam skill.

Meet the specialist agents

☕ Simple explanation

Think of a hospital.

Copilot is the GP — good at everything, handles most problems, and refers you when needed.

Researcher is the radiologist — an expert at finding things hidden in mountains of data. Give it a pile of documents, emails, and web pages, and it’ll extract exactly what you need.

Analyst is the lab technician — give it numbers, spreadsheets, and datasets, and it’ll spot patterns, run calculations, and produce charts that tell a clear story.

Neither replaces the GP. They each handle the work the GP isn’t specialised for.

Researcher is an AI-powered research assistant that gathers, analyses, and synthesises unstructured information (documents, emails, web pages, Teams chats) into structured, well-cited reports. It uses semantic search across Microsoft Graph data and the web.

Analyst is a virtual data scientist that transforms structured data (spreadsheets, databases, Power BI datasets) into actionable insights and visualisations. It uses advanced reasoning and Python-based analysis capabilities.

Both are prebuilt agents available to Microsoft 365 Copilot users. They represent Microsoft’s approach to role-specific AI assistance — specialised tools that go deeper than general Copilot can in their respective domains.

Researcher vs Analyst — the key comparison

Researcher vs Analyst — when to use each
FeatureResearcherAnalyst
Works withUnstructured data (docs, emails, chats, web)Structured data (spreadsheets, databases, Power BI)
What it doesFinds, filters, summarises, and cites informationAnalyses, calculates, visualises, and forecasts
OutputStructured reports with citationsCharts, visualisations, statistical insights
Think of it asResearch assistant / librarianData scientist / analyst
Best forMarket research, executive briefings, knowledge discoveryBudget analysis, trend identification, anomaly detection
Key technologySemantic search across Microsoft Graph + webPython reasoning, advanced calculations, Power BI integration

Exam tip: The exam often presents a scenario and asks “which agent should they use?” The deciding factor is always: Is the data unstructured (documents, emails) → Researcher or structured (spreadsheets, numbers) → Analyst?

Researcher use cases

Researcher excels at turning scattered, unstructured information into clear, organised reports:

💡 Scenario: Clearfield Council's compliance audit

Officer Patel needs to prepare a briefing on all data breaches reported in the last 12 months. The information is scattered across:

  • SharePoint incident logs
  • Teams channel discussions
  • Email threads with external auditors
  • Published guidance documents on the web

Without Researcher: Officer Patel spends 3 days manually searching each system, copying notes, and writing the report.

With Researcher: Officer Patel prompts: “Compile all data breach incidents from the past 12 months. Include root causes, departments affected, and resolution timelines. Cite all sources.”

Researcher searches across Graph data and the web, produces a structured report with citations, and Officer Patel spends 2 hours reviewing and refining — instead of 3 days.

Other Researcher use cases:

  • Market research — “What are competitors saying about AI adoption in government?”
  • Executive briefings — “Summarise everything discussed about Project Phoenix this quarter”
  • Contract review — “Find all references to liability clauses across our uploaded contracts”
  • Onboarding — “Compile a new-hire guide from our HR SharePoint site, training docs, and Teams FAQs”

Analyst use cases

Analyst excels at turning raw numbers into actionable business insights:

💡 Scenario: Northwave's quarterly budget review

Alex (Northwave’s CEO) asks: “Where are we overspending compared to forecast?”

The data sits in 8 Excel workbooks across different departments, plus 2 Power BI dashboards.

Without Analyst: The finance team spends a week consolidating spreadsheets, running pivot tables, and building charts.

With Analyst: Alex prompts: “Compare actual Q3 spend vs forecast across all departments. Identify the top 3 areas of overspend, show the trend over the last 4 quarters, and suggest where to cut.”

Analyst processes the data, generates visualisations, and even provides a narrative: “Marketing overspent by 15%, driven by unplanned agency costs in August. Travel expenses dropped 22% vs forecast.”

Other Analyst use cases:

  • Sales forecasting — “Based on the last 2 years, what should we expect in Q4?”
  • Anomaly detection — “Flag any unusual transactions in this expense dataset”
  • Power BI dashboards — “Break down shipping delays by region and supplier”
  • Budget planning — “Model three scenarios: flat growth, 10% growth, 20% growth”

Other prebuilt agents

Beyond Researcher and Analyst, Microsoft provides additional prebuilt agents:

AgentWhat It Does
Prompt CoachHelps craft better prompts — feedback, examples, and suggestions
Writing CoachGives constructive feedback on any writing task
Career CoachProfessional development advice, interview prep, skill planning
Ideas CoachBrainstorming support — generates, ranks, and refines ideas

These are lower stakes for the exam but worth knowing. They’re also available as templates when creating custom agents.

The decision framework — which tool for which problem?

Choosing the right tool — the decision framework
ToolBest For
Copilot (in-app)Interactive tasks in a single app — draft, summarise, analyse in context
Copilot Chat (Business Chat)Cross-app knowledge search — 'What's the latest on X across all channels?'
ResearcherDeep unstructured research — compile reports from docs, emails, web
AnalystStructured data analysis — trends, forecasts, visualisations from spreadsheets
Prebuilt agentCommon scenarios — writing help, career advice, brainstorming
Everyday user agentDepartment Q&A bots, guided processes, simple lookups
SharePoint agentSite-specific content discovery, document help, navigation
Custom advanced agentMulti-step workflows, cross-system automation, API integrations
💡 Northwave's decision matrix — 5 problems, 5 tools

Each Northwave department has a different need. Here’s what Maya recommends:

  1. Sam (Marketing): “Help me write this blog post” → Copilot in Word (interactive, single-app)
  2. Jordan (CISO): “Compile all security incidents from the last year” → Researcher (unstructured data across multiple sources)
  3. Priya (Compliance): “Show me DLP violation trends by quarter” → Analyst (structured data, visualisations needed)
  4. New hires: “Where do I find the expense policy?” → SharePoint agent (site-specific content lookup)
  5. Finance team: “Auto-process 500 invoices monthly” → Custom agent (multi-step workflow, API integration)

🎬 Video walkthrough

🎬 Video coming soon

Researcher, Analyst & Use Cases — AB-900 Module 25

Researcher, Analyst & Use Cases — AB-900 Module 25

~10 min

Flashcards

Question

What kind of data does the Researcher agent work with?

Click or press Enter to reveal answer

Answer

Unstructured data — documents, emails, Teams chats, SharePoint files, and web pages. It uses semantic search to find, filter, and summarise information into structured, well-cited reports.

Click to flip back

Question

What kind of data does the Analyst agent work with?

Click or press Enter to reveal answer

Answer

Structured data — spreadsheets, databases, and Power BI datasets. It analyses numbers, identifies trends, generates visualisations, and provides narrative insights using advanced reasoning and Python.

Click to flip back

Question

When should you recommend a custom advanced agent over a prebuilt one?

Click or press Enter to reveal answer

Answer

When the workflow involves multiple steps, cross-system integration (APIs, external services), or highly customised logic specific to the organisation. Prebuilt agents handle common scenarios; custom agents handle unique business processes.

Click to flip back

Knowledge Check

Knowledge Check

Clearfield Council needs to identify which departments had the highest variance between budget forecast and actual spending over the last 3 years. The data is in Excel spreadsheets and a Power BI dashboard. Which tool should they use?

Knowledge Check

Northwave's legal team needs to review 200 contracts and identify all clauses related to data processing agreements. The contracts are stored as Word documents in SharePoint and some are shared via email. Which tool is BEST suited?


Next up: Managing Copilot — the day-to-day admin tasks: assigning licenses, monitoring billing, tracking adoption, and governing prompts.

← Previous

Copilot Licensing: Monthly vs Pay-as-You-Go

Next →

Managing Copilot: Billing, Monitoring & Prompts

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.