Microsoft Copilot - supporting research

 This article, was published mid-2025, providing an overview of the impact of Copilot researcher and analyst agents on work. 

Having now used both for 6 months plus, my take on these two agents, is that they can be useful, but need to used with care. 

1) working out what is to be done is important. Responses from researcher or analyst agents, arise through the prompts provided. Careful structuring of prompts is therefore essential in obtaining the types of actions required. Otherwise, researcher may go off topic quite easily.

2) providing context is important and delimiting the researcher/analyse agents to specific papers, websites or attachments help ringfence the direction of responses.

3) using the prompt writing agent in Copilot can be useful for tightening prompts.

4) ensuring that 'work or 'web' is selected, along with depth of responses (auto, quick, think deeper) helps again to ensure responses fit expectations.

5) Triangulation is always required, to check the validity of the responses. Limiting resources also help to save time, so that triangulation is restricted and does not have to go all over the place.

6) Draw on the advantages of AI. Summarising key points, comparison of key points across papers/sites, drilling deeper to extend insights, providing 'neutral' perspectives on conceptualisations, frameworks etc.

7) be aware of 'cognitive debt' / 'cognitive atrophy' and how this can come about very easily when your critical thinking is replaced by AI doing the work. You still need to read deeply, cogitate, make your own judgements and come up with your own synthesis. Then use AI to cross check these and see if it provides other insights which are viable.

8) Continue to learn how to manage AI to draw on it's ability to automate some research processes. The key is to use AI as a thinking partner, not to replace your own effortful thinking.

Copilot agents

A bit of 'research' into Copilot agents this morning, following on from yesterday's session on building agents in CoPilot. 

Microsoft 365 Copilot Premium (now often simply M365 Copilot) offers "declarative agents" designed for lightweight, personalized tasks using organizational data, managed within the M365 environment.  on the other hand Copilot Studio enables creation of advanced, custom agents with complex, multi-step workflows, API connections, and full lifecycle governance. 

Microsoft Copilot Studio in New Zealand is generally licensed as a tenant-wide capacity 

pack, starting at approximately NZ$323.60 per pack/month. This subscription provides 25,000 "Copilot Credits" monthly, which are consumed when agents complete actions or responses

The cost of Microsoft 365 Copilot in New Zealand varies depending on whether you are 

purchasing for an individual or a business, with prices generally starting around NNZ$34–$40 per user/month for business subscriptions

Microsoft 365 Copilot for Education is priced at approximately NZ$30–$32 for academic institutions. This specialized academic license provides AI-powered assistance for faculty, staff, and higher education students, acting as an add-on to existing Microsoft 365 A3/A5 license.

Templates for business type agents include a Quiz tutor template and a series of  'assistants' for various job tasks including travel planning, peer feedback agent, training content writer.

A guide for educators  provides ideas for using agents in educational settings. 

Overall, there are good possibilities :) 

Microsoft - introduction to building agents

 The last in the 'back to campus series' offered through Microsoft (based in Australia). 

As with the other two sessions I attended, Jennifer Ruan is the facilitator and Victor Kochetkov does the demonstration.

Notes taken during the session:

Covering what are agents, what tools exist, to through building an agent and Q & A. 

Explained Copilot as a user interface for AI. Currently there are agents accessible through Copilot and also customised agents can be build in individual copilot accounts.

Copilot is for human augmentation, private, personal assistant and 1:1 interaction.

Agents connected to Copilot, chat or autonomous and can contact with other agents.

Out of the box agents on Copilot include surveys, researcher, analyst etc. If (frontier) then they are in initial phase.

Copilot is off the shelf, retrieval only and connects to Microsoft 365 only. Copilot Studio provides task/autonomy and for developers with more complex task. Developers can also build customised agents with Copilot Studio + Azure AI.

Went through Copilot - using 'new agent' on the left menu to access. Generally, describe what you want to do, configure the agent by adding knowledge and capabilities, try out as it is being build and then use/share with others. 

Copilot agents can be shifted across to Copilot Studio to make them more sophisticated. Studio has more comprehensive tools, wide selection of models, able to publish to multiple channels and has more powerful orchestration. 

Agents generally retrieve information and reason, summarise etc. They can also take action to automate workflows and replace repetitive tasks. Automous agents will operate independently, plan, orchestrate other agents, learn and escalate. 

Example in education, an IT helpdesk agent, devise refresh agent, research tracker agent, budget management agent, study guide agent, student support agent etc.

Note: agents build in premium cannot be used by others who only have access to Copilot basic without extra billing!!

Demonstrated how to create an agent. I create one to compare Learning Outcomes against NZQA criteria in 2 minutes! Also, ask prompt agent or chat to help create the agent, providing the best prompts to use. Copilot studio has help and examples, along with templates for creating agents. Analytics are also available. Evaluation also possible, to test an agent. Remember to use AI to do the work where required. 

Discussion on who will see or have access to the agent as various people in the institution have access to various type of Copilot (basic/premium). Also with each type, there are functions that some have access to and others do not :(

A link from Moodle for a agent will work - if the learners have the right version of Copilot and use it within their Ara digital environment. Otherwise, Copilot Studio needs to be used. 

Another series later this year is seeking pre-registration - Future ready with Copilot.

Cowork by microsoft - alternatives

 Yesterday's microsoft presentation introduced Cowork. To have this available in my institution's Copilot premium, requires the turning on of access to Claude. I can see some advantages to having Cowork, as it automates tasks which are carried out, often across several apps, regularly.

An AI query (on Google) reveals that all the other main LLMs have equivalents. Claude itself has Claude Cowork. Open AI has 'operator' which costs US$200 a month. Google has Project Mariner. Manus and even Amazon (Nova Act) also have similar capabilities. 

Plus, there are a whole host of  enterprise tools - Eigent, OpenClaw,  Composio etc. O-mega offers an overview of 10 Claude Cowork alternatives 

Therefore, agentic AI is now mainstream and will have further reaching implications on work and education than Gen AI itself. 

Cogniti mini symposium - link to video of presentations

Was unable to 'attend' the recent Cogniti mini symposium. Videos of the presentations are now available via this link. 

Almost all of the presentations are from universities, withe several from Chile.

Listened to the presentation from Associate Professor James Oldfield from Unitec on their collaborative project with Toi Ohomai and Manukau Institute of Technology on using agents in nursing. (12 minutes)

Detailed the various agents that were worked on - drug calculations, scenarios in nursing - de-escalation and dealing with difficult situations. Presented on student feedback on their perspectives on usefulness of the agents, usability and improvements that can be made to enhance the experience. 

CoPilot with M365 (premium - with access to researcher and analyst agents

I have had a few weeks to get to know the premium subscriber version of Microsoft Copilot or Copilot M365. This version costs an extra NZ$500 + a year and not available to everyone within the institution.

Fellowmind, provides an overview along with pros and cons of the system. Microsoft Insider Track  provides 10 tips to improve productivity using Copilot - generally to use it as a personal assistant to plan one's day, review the week's work, brainstorm, etc.

This youtube provides a more generalised introduction along with examples. The video provides a  good overview of the key functions in CoPilot - Chat, generate images, use it like google and question the information and change the information into bar chart, Code, upload documents and summarise/ask questions based on the document (extract certain items e.g. financial information).  Covers:

- Create - posters, select a created poster as a template. 

- Using Copilot in Word, PowerPoint and Excel. 

- Use and leverage existing agent examples with researcher and analyst (includes data visualisation).

- Creating custom AI agent to configure your own agent - able to achieve all the above. 13 minutes in.

This youtube summarises the uses of CoPilot for teachers.  Covers:

- Using apps - outlook, word, excel etc. 

- Search bar, Chat and how to use this for supporting teaching work.

- Copilot prompt gallery / and prompt agent. Use /to refer to files or put up files to refer to. 

- Demonstrated how to convert a ppt into a blog post!

- Copilot has memory - which can be updated. Use settings / personalisation to adjust copilot memory. 

- Use pages that can be an interactive 'page' - i.e. onenote page with AI overlayed

- Agents - the included ones (researcher/analysts), prompt coach etc. and ability to create your own agents. 

- Create connects to usual microsoft apps -word etc. that allow creation of a range of resources. Plus using CoPliot in 'normal' word, excel or other apps. demonstration on how Copilot integrates into these.

Of note for all users, is the ability to create agents - see this youtube for creating agents for education based around CoPilot chat (published April 2025). Versions for educational institutions also include 'Teach' which has 'agents' to support the drafting of lesson plans, and the development of marking rubrics and flash cards to support learning or teaching. This video summarises these tools. 

For the paid premium version, the addition of the researcher and analyst agents are game changers. Future Savvy  provides an overview and good examples of prompts and user cases. The researcher agent responses can be verbose, so careful prompting is required to attain relevant results. The agent provides a 'chain of thought' which makes the ways in which the AI has come up with the response visible. This is useful to be able to see sources as depending on the context, the AI will draw from what is already in your OneDrive, other work files and also the web (if the option is selected). Asking researcher agent to only refer to peer reviewed sources is still hit and miss and for collation of in-house reports etc. researcher agent does save time as it collates the many sources of information, some of which have been forgotten! 

Overall, CoPilot has improved markedly this year and is a viable alternative to other AI platforms. The key as always is to use it circumspectly, not expect miracles, and to be targeted in how it is used. As CoPilot draws from the localised resources, authenticity is tighter. Putting time into learning how to use it well will pay dividends. 

Cogniti mini symposium - notes from a few presentations and summaries from some recorded presentations

 Cogniti users and administrators organised a mini symposium, offered both online and f2f on 5th November 2024.

Three streams of presentations taking place over 2 1/2 hours. I could only get to a few in between meeting and facilitating workshops.

Notes taken from a few presentations.

- Personalised exam preparation using AI in large cohorts - Dr. Helen Mcquire and  Dr. Angela Sun (University of Sydney) context of microbiology/ immunology course. A bespoke AI agent was used to increase teacher presence with students. Went through the rationale and processes to build the chatbot. The important learning from this one, is how it is used by the lecturers, to identify knowledge gaps amongst their learners. Shared AI limitations - repetitive questions, Ai not providing direct exemplar responses. Invited potential collaborators to get in touch.

- Practice makes perfect: AI powered oral assessment preparation with Jim Ennion from Toi Ohomai. Presented on how a virtual client prepares students to become immigration advisers.Used Cogniti to help students prepare for an oral assessment. Cogniti was set up to act as a client. Prompts were set up with scenario information, set the tone to informal/not educated, have uncertain outcomes. Unfortunately, the agent hallucinated and provided incorrect information. However, student engagement was high with positive outcomes. assessment outcomes were marginally better for students who took the opportunity to use the agent.

- Always on teacher: AI brings business studies to life with James Cooper from Scots College, Sydney. Here the teacher formed an AI version of himself  (Cooper Jr.) to support students learning business at school (Year 11 and 12). The AI tutor could provide practice questions, mark student responses and help deepen content understanding. The curriculum is very prescribed, so that helped to ring fence the content. Main guide was to provide student support - replacing emails to students, generate revision questions and generate sample responses that are achievable by the students. Described process taken to built the agent. Student feedback was positive. Challenges around imprecision and working beyond the sylllabus scope. Short answers were 'double barrelled' and 'US style'. Shared the work currently to refine the agent, improve short-answer reliability, and mark essays and reports.

Last week, the various recordings of presentations was made available. Below are summaries of a few of relevance at present to my projects.

Notes from videos of presentations

- Reimagining research and writing learning through AI assistants with Dr. Lucy MacNaught and Dr. Kiri Hunter from Auckland University of Technology. Used Cogniti to help guide Masters of Nursing Science students to write research proposals. An intensive programme with many assessments. The view was that students did not have time to even look at feedback from one assessment to the next. Cogniti agents were used to encourage drafting and ongoing gradual improvement of their research proposal. Used Humphrey (2016) teaching and learning sequence to ground their work. Basically, used AI to provide feedback at each stage of the research proposal workflow. 

Christie Oldfield from Auckland University of Technology presented on 'enhancing subjective interview skills through AI role-play' in a physiotherapy context. Health care interviews are important to establish rapport with the patient but also to ensure that patient information is obtained to support the therapy sessions. Agent was created to monitor how student progressed through a patient interview. 

Plenary closed the symposium. This is presented by Danny Liu, Leitizia Wan, Sam Clarke, Minh Hubyn and Kria Coleman from the University of Sydney DVC (education).

Reflections from the symposium and work undertaken and ideas to take things into the future were covered. Overall, good examples of using Gen AI to support constructivist learning.