Copilot for Microsoft 365 How it ACTUALLY Works!

In this, the last of 3 special episodes featuring the Director of Microsoft 365 and the host of Microsoft mechanics, Jeremy Chapman and I discuss Microsoft 365 Copilot. Answering all of your questions, we’ll discuss everything you need to know about Copilot. Including how it works, what it can do and how to prepare your business and get ready for the AI revolution. This is a deep dive session. That aims to ask some hard hitting questions that goes beyond the fluffy marketing.

Timecodes

00:00 Introductions
02:53 Introducing Jeremy Chapman
03:53 How Copilot Works
04:31 Microsoft 365 Copilot Demo
05:54 How Copilot Works from the Backend
07:03 Understanding Copilot Architecture
09:00 Customising Copilot Prompts
10:30 Building your own Copilot with Azure AI Studio
18:30 Customising Copilot Thresholds & Filters
19:42 Security & Compliance Controls
21:51 How to Prepare your Organisation for Copilot
24:30 Auditing Copilot
26:35 How do I get started and learn more?
30:19 Check out the NEW Copilot Dashboards
31:11 Session conclusions and next steps

[nocodecreative]

Excellent Andy, some of the best content I've seen to date on the subject!

[YN-wvrd]

Great overview, thank you! This is the information I was looking for.

[Daniel_alejandro]

Finally an employee that doesn't take lunch breaks or coffee mornings.

[.Golden]

Thank you for this. I have been trying to figure this out for a while now.

[yankeeee]

Great summary of copilot in general and copilot for M365 in particular. Thank you both!

[saurabhvkadam]

Thanks mr. Andy, for the educational video on copilot, we have purchase license for copilot and soon delivered to india. Happy see ms mechanic giving such info abt copilot. Waiting for some deep dive from you.

[driver]

We were supposedly the first company to get Copilot licenses through CSP in Europe and are doing a pilot now 😊

[xyberfunk]

Congrats on the Silver Award! Look forward to many more tech videos. Thank you.

[tonyelliott]

wait, @ 7:23 when the architect diagram is presented, I see that step 3 is to take the massaged prompt and put it into the LLM. However the disclaimer on the LLM is that it does not learn from prompts, responses or grounding data. So how do LLM's get improved to operate better? How does the RAI get improved to run better? A see a circular argument occurring with LLM and RAI maintainers: "Boss: I'd like you to make the XYZ LLM run more efficiently and to be able to handle more complex requests" "Maintainer: sure, give me some real world data models to study" "Boss: oh no, we don't use actual user prompts, responses, etc to study". I feel it would be easy enough to de-identify user metadata to allow enough information to be used by LLMs and RAIs.

[tHsteg]

My biggest gripe of the release of co-pilot is the cost. Working with in education the benefits of this solution is unparalleled. But at a cost of £30 per FTE per month is just not doable for most schools.

Sadly trying to keep schools in the Microsoft ego system as the costs increase against Google’s offering is becoming a weekly struggle.

[mukundthaker]

Excellent insights into the subject. Thanks so much

[abe]

I've been using it, and I find it way less powerful that chat GPT plus, no way to easily build custom gpt's, copilot studio feels basic and more tuned for public facing gpt's

[noreply]

This of course raises huge security and privacy concerns, can you make a presentation on the dangers of sharing data with an AI controlled by an external business. I am both thinking about the dangers this poses for individuals and of course the security concerns it poses for businesses.

[iamalfofficial]

Congratulations on your 100k subs and yt award.

[tjubczg]

Nice video. Hate that noise at 22:11 though!

[jsmtcdt]

Would be nice if it actually did some real work for a change.

[man]

Another question that needs to be asked is how does Microsoft handle companies compliance needs? Such as NIST 800, PUB 1075, HIPA etc....

[vaprtranz]

Great walk-thru of custom bot building in Studio. Most vids never step through building a custom copilot (small "c"), which is the REAL power of Copilot & Graph. What Jeremy steps-thru is RAG (Retrieval Augmented Generation) and a lot of AI research is saying Hybrid semantic search with re-ranking and backed by a vectorDB of embedded document contents and a frontend custom prompt is THE most accurate response (aka. least LLM hallucinations).

I thought Copilot Studio would be the no-code alternative to AI Studio for Business/Enterprise customers?

[Teramos]

Would love to see Semantic Index in action, is it indexing the files metadata or the content within the file also? For example, Word or PDF Files in a SharePoint library.

[georgedubberc]

At 28.26 Jeremy talks about public web content. Forgive me if this is a silly question; I am not tech qualified/ an admin. If the business is buying Copilot for Microsoft 365 and wants to keep its data within the M365 service boundary, can you (1) explain the relationship between "Copilot for M365" and "Microsoft Copilot formerly known as Bing Chat Enterprise"?  and (2) if you check the box on Jeremy's slide in the Admin centre "Allow Copilot to reference public web content" are you thereby enabling web connection via M365 Chat or are you using Bing Chat Enterprise (which has different T&Cs)? (3) Aren't you losing some of your M365 protection of your data?