Module 13: Researcher, Analyst, and Microsoft-Built Agents
Lesson 13.1: What Are Microsoft 365 Copilot Agents?
Lesson Promise
Understand what agents are, where they appear, and why they should be chosen by task, source, and risk.
Real-World Scenario
A business user sees Researcher, Analyst, and several installed agents in Microsoft 365 Copilot and does not know which one to use.
Core Concept
Microsoft describes agents as extending what you can do with Microsoft 365 Copilot by connecting to knowledge and data sources and, in some cases, automating or executing business processes.
Agents can be built-in, installed by an organization, added from an agent store, or created by users where enabled. Availability depends on tenant and admin controls.
A good agent decision starts with the job: conversation, research, data analysis, app-specific assistance, repeatable process, or custom workflow.
Step-By-Step Workflow
- Define the task outcome.
- Identify source types: web, files, emails, meetings, chats, datasets, or app content.
- Check whether the task needs deep research, data analysis, a repeatable process, or simple chat.
- Check agent availability and approval status.
- Run a small test prompt before using sensitive or important data.
- Review output for sources, assumptions, limitations, and human decision points.
Prompt Lab
Bad Prompt
Use an agent for this.
Better Prompt
Help me choose whether Copilot Chat, Researcher, Analyst, or an installed agent is the best fit for this task.
Expert Prompt
Create an agent selection recommendation for this work request. Compare Copilot Chat, Researcher, Analyst, app-specific Copilot, installed agents, Agent Builder, and Copilot Studio. Include task fit, data needed, risk level, availability checks, governance concerns, and human review steps.
Hands-On Exercise
List five work requests and choose chat, Researcher, Analyst, app Copilot, or an agent for each.
Deliverable
An agent selection table with task, best tool, source boundary, risk, and review step.
Agent Selection Review Checklist
Common Mistakes
- Using an agent because it sounds advanced instead of matching the task to the right tool.
- Treating Researcher reports, Analyst reports, or agent answers as final without reviewing sources, assumptions, and limits.
- Attaching sensitive data to an agent before checking purpose, permissions, and governance.
- Confusing built-in agents, organization-installed agents, Agent Builder agents, and Copilot Studio agents.
- Promising agent availability before checking license, admin approval, tenant controls, language, platform, and rollout.
Quiz / Checkpoint
What is the first question before using an agent?
What job needs to be done and what sources, risks, and review steps does that job require?
Official Sources To Verify
- Get started with agents in the Microsoft 365 Copilot app
- Get more agents in the Microsoft 365 Copilot app
- Get started with Researcher in Microsoft 365 Copilot
- Get started with Analyst in Microsoft 365 Copilot
- Build your own agent with Microsoft 365 Copilot
- Agent Builder in Microsoft 365 Copilot
- Build agents by using Agent Builder in Microsoft 365 Copilot
- Microsoft 365 Copilot Chat overview
- What Copilot license do I have
Want your AI product explained to a large AI-native audience?
Kingy AI helps AI companies turn complex products into clear, useful YouTube videos that drive awareness, product understanding, demos, clicks, and search visibility.
