New reasoning agents: Researcher and Analyst in Microsoft 365 Copilot
Analyze data and research with expertise on demand, and automate workflows with intelligent agents in Microsoft 365 Copilot. Analyst thinks like a data scientist and Researcher like an expert, so you can uncover insights, validate logic, and generate expert-level reports in minutes.
And using Microsoft Copilot Studio, build your own autonomous AI agents to streamline multi-step processes with deep reasoning, like responding to RFPs or synthesizing internal knowledge, incorporating Copilot Flows as automated actions. No need for perfect prompts — just describe what you need, and Copilot will reason through the task, surface key insights, and deliver actionable results faster than ever.
Jeremy Chapman, Microsoft 365 Director, walks you through how to use these AI-driven agents step-by-step, from data analysis to research and automation.
Turn messy data into insights.
Perfected prompts not needed with Analyst in Microsoft 365 Copilot. Check out reasoning agents here.
AI-powered research at your fingertips.
Researcher finds, analyzes, and synthesizes work data and industry trends into detailed reports. Take a look.
Automate complex, repetitive tasks.
Intelligent agents that work autonomously, reasoning over the data you can access, and delivering results in minutes. See it here.
Watch our video here.
QUICK LINKS:
0:00 — Reasoning agents in Microsoft 365 Copilot
00:59 — Analyst
02:58 — Researcher
04:46 — How it differs from other models
05:29 — How to build your own deep reasoning agent
07:58 — Wrap up
Link References
To get started, check out https://aka.ms/CopilotReasoning
Unfamiliar with Microsoft Mechanics?
As Microsoft’s official video series for IT, you can watch and share valuable content and demos of current and upcoming tech from the people who build it at Microsoft.
- Subscribe to our YouTube: https://www.youtube.com/c/MicrosoftMechanicsSeries
- Talk with other IT Pros, join us on the Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog
- Watch or listen from anywhere, subscribe to our podcast: https://microsoftmechanics.libsyn.com/podcast
Keep getting this insider knowledge, join us on social:
- Follow us on Twitter: https://twitter.com/MSFTMechanics
- Share knowledge on LinkedIn: https://www.linkedin.com/company/microsoft-mechanics/
- Enjoy us on Instagram: https://www.instagram.com/msftmechanics/
- Loosen up with us on TikTok: https://www.tiktok.com/@msftmechanics
Video Transcript:
-Chain-of-thought reasoning is coming to Microsoft 365 Copilot. Today, I’ll show you an early look at two new reasoning agents for work, as well as how you can build your own deep reasoning agents in Microsoft Copilot Studio. Starting with Analyst, which uses reasoning to work alongside you as a data scientist, helping you to go from raw data to valuable insights in minutes using analytical reasoning while exposing its underlying query code. Then Researcher that works with internal information that you can access, together with powerful orchestration and deep search to tackle complex, multi-step research topics. Now, these agents both use OpenAI’s o3 model and can collaborate with you, prompting you along the way like a coworker to generate advanced responses. Both are designed to analyze large amounts of work information that you have permission to access to deliver on-demand expertise so that you can get more done.
-Let me show you Analyst first. So we built Analyst to think like a skilled data scientist. Now, Analyst leverages a state-of-the-art reasoning model that we’ve optimized for advanced data analysis at work. In this case, I’m trying to understand our most loyal customers. Now, here I have this messy dataset. It’s spread across multiple sheets, and in each, there are thousands of rows of information across customers. Now, here you can see the monthly revenue for each customer, and none of this has been cleaned or contextualized. And now I have an analytics expert available to me 24/7 that can help. Notice I don’t have to spend time writing the perfect prompt to get what I’m looking for. I only need to ask Copilot to use the data that I’ve referenced to give me insights on customer segments with a graph to visualize it.
-Now, you’ll see the agent takes my question and you can watch its reasoning as it processes. So first, it’s analyzing the data to look for the right columns for customer segmentation and revenue over time. Now it’s mapping out clusters and also grouping customers. It’s getting an understanding then of the sheet structure in my Excel file, standardizing the data, loading what it needs from the data, and then prepping it for further analysis. Now, it starts to work on data visualization, looking for patterns and also revenue trends in this case. It ensures that the data is complete, and while it’s working, you can also click in to expand any of these steps to see its chain-of-thought reasoning, as well as the Python code that it’s running in real time.
-Now, that way, I can also validate the approach that it’s taking. Now, as Analyst runs its final step and finds key insights, it starts working on the visualization that I asked for. Now it’s created an Average Monthly Recurring Revenue by Customer Segment chart based on customer size and the state of their monthly revenue over time. Below that, there’s even a summary of its findings pointing out three key insights from the data that are easy to understand.
-Next, with Researcher, we’re using OpenAI’s deep research model, along with advanced orchestration in Copilot and vector-based search over the work data that you have access to, to deliver complex, multi-step research with high accuracy. Now, in this case, I work in product development and my company is actually entering a new market, so I need help developing a product strategy for our expansion. Now, I just need to write A Prompt Here And I’ll Ask Researcher to develop a product strategy to enter a new market segment for outdoor and adventure goods. Once I enter my prompt, Researcher goes to work. You can see that as part of its first response, it asks me clarifying questions about the scope and format of what I want to write.
-So I’m going to go ahead and respond to Researcher, answering both of its questions. And then it uses my response to move forward. The agent takes my prompts, understands the task, and starts to construct a plan of action that it will use to author a detailed report. Then it starts reasoning over multiple files that I can access from internal information sources. As it works, I can take a look at its chain-of-thought reasoning in real time, and it tells me what it’s doing, the topics it’s searching for, and the files and messages it’s using as it completes the task in real time. Now it’s building an understanding of my existing product lineup, referencing recent meetings, and also even researching industry trends from the web. Now, this process takes a few minutes, so let’s go ahead and jump ahead to the result. On the right side, you can see that it’s delivered a thorough response with fully-documented product strategy, in line with what I’d expect from an expert.
-Starting with an analysis of my existing business, it’s also analyzed the Outdoor and Venture Gear Sector, then built insights based on the intersection of our existing business, electronics, with our new Outdoor product segment, then Strategic Positioning, and also a detailed Go-to-Market plan. And this goes beyond what you can do with other models that are designed to reason primarily over content sourced from the web. So in this case, Researcher leveraged internal work files and information that I have access to to get the most recent and relevant data from files, email messages and meetings, in addition to information that it sourced from the web. And Researcher can even be connected to third-party data via connectors like Salesforce, ServiceNow, and Confluence, or even other agents like Sales Chat from Microsoft. Analyst and Researcher are, of course, prebuilt agents that you can use for Microsoft 365 Copilot.
-But now, why don’t we switch gears to how you can add deep reasoning to the agents that you build yourself using Microsoft Copilot Studio. Now, in this case, my team frequently receives requests for proposals, or RFPs, from its clients, and we’ll use Copilot Studio, which, if you’re new to it, is a platform to create, manage, and deploy agents. In this case, we can use it to build an agent that works independently to help automate the authoring of the initial proposal. Now, the thing about RFPs is that they often need extensive collaboration with people who also need access to the right information for pricing and scheduling, and the requesters, they expect detailed and accurate proposals to win their business.
-Now, agents in Copilot Studio can help your team complete an ambiguous or multi-part process like writing an RFP, and you can use deep reasoning in Copilot Studio to instruct an agent to create a formal proposal document based on that RFP. All you need to do is provide detailed instructions that break down the steps that you want it to take. For example, here, I’ve instructed the agent to use CRM data and product information stored across various files in SharePoint to find answers to our client’s questions. Next, I’m going to instruct the agent to use reasoning models for the process, and then moving into settings, I’ve already connected the agent to my knowledge sources, in this case, files in SharePoint, and I’ve also selected Actions which are connections to my CRM system and a Flow that I’ve built to create the proposal. I’ve also added a trigger to kick off the process when a new RFP email arrives in Outlook to make this an autonomous agent.
-And with everything configured, I can even test it using an RFP that was successfully processed previously to validate it’s running correctly. And I’m going to go ahead and choose this one here from 3:00 PM and now I can watch the agent’s process in realtime as it runs the steps to author the proposal document. The agent is capable of quickly analyzing large amounts of data to generate precise and well-thought-out responses and delivers a well-formatted RFP. And when I publish the changes I’ve made to the agent, it will become active. So now, once an RFP arrives in my inbox, the autonomous agent we just built will process the RFP to generate a matching proposal document, then send that as a first draft to the team so that we can finalize it and respond faster.
-So using this approach, you can build agents in minutes to complete processes for you using built-in deep reasoning capabilities. And to find out more about agents with deep reasoning available with Microsoft 365 Copilot and your options for using Copilot Studio, check out aka.ms/CopilotReasoning. And keep watching Mechanics for the latest updates from Microsoft, and we’ll see you soon.
