2.3.1. Researcher and Analyst: The Prebuilt Reasoning Agents
💡 First Principle: Not every agent is one somebody built. Researcher and Analyst are first-party agents that come with a Microsoft 365 Copilot licence — you do not configure their knowledge sources, because they reach whatever you can already reach. They are the answer to "I need more than a chat reply" without anyone creating anything.
Section 2.3 described agents you configure. These two are the other kind, and the exam's audience profile names them directly — so a scenario that calls for deep research or number crunching is usually pointing at one of these rather than at a custom agent.
What each one is for:
| Researcher | Analyst | |
|---|---|---|
| Built for | Complex, multi-step research | Working with data and numbers |
| Draws on | The web and your work content — files, emails, meetings and chats you have access to | Spreadsheets and other data sources, across files |
| Produces | A structured, source-cited report with organised sections, charts and visuals | Analysis, summaries and Python-powered forecasts, enriching the workbook |
| Typical use | "Compare our last three quarterly reports against published competitor results and tell me where we are losing share" | "Clean this sales export, find the outliers, and forecast next quarter" |
Researcher trades speed for depth, deliberately. A simple query may return in under five minutes; a genuinely complex one can take 10 to 45 minutes. That is the design, not a fault — it spends the time retrieving and reasoning so the output is something you can act on and share. It may also ask clarifying questions before it starts, and engaging with them is how you steer the scope.
When to choose which:
| You need… | Use |
|---|---|
| A quick summary, a short reply, light brainstorming | Standard Copilot chat |
| A back-and-forth task without heavy analysis | Standard Copilot chat |
| Deep reasoning across multiple sources, web plus your work, in a report you can share | Researcher |
| Citations and a clean structure you can present or decide from | Researcher |
| Cleaning, summarising, forecasting or reasoning over numbers | Analyst |
Both stay inside the same boundary as the rest of Copilot. They are first-party Microsoft experiences operating within the Microsoft 365 commercial data processing boundary, inheriting the permissions, policies and compliance commitments that already apply to your tenant. Researcher cannot surface a document you could not open yourself — the depth changes, the access rules do not.
⚠️ Exam Trap: A scenario describing a specialised, recurring need does not automatically mean "build a custom agent." If the need is deep research or data analysis rather than your organisation's specific knowledge and rules, the right answer is a prebuilt agent that already exists. Building an agent is for scoped, org-specific, repeatable workflows — as 2.3 and 6.1 describe.
⚠️ Exam Trap: Researcher taking many minutes to answer is not a performance problem to be escalated, and its clarifying questions are not a failure to understand the prompt. Both are the feature working as intended. A distractor offering "switch to standard chat for a faster answer" trades away exactly the depth the scenario asked for.
Reflection Question: A strategy lead needs a shareable, cited competitive briefing that draws on both internal sales files and public market data, and a finance colleague needs next quarter's forecast from a messy spreadsheet export. Which experience should each use, and what would be lost by sending both requests to standard Copilot chat?
