Copilots Explained

GitHub Copilot

Code Copilots: GitHub Copilot extensions in VS and VS Code.  Amazon Q Developer is an AWS code generator best for building code/ and solutions.  GitHub comes in 3 flavours: individual, Business and Enterprise.

GitHub explains code, optimises your code's performance, improves readability, generates unit tests, improves error handling, adds new code with requested functionality, ensures coding consistency, and improves modularisation to help with the DRY principle.

GitHub is the diggity bomb.

Microsoft 365 Copilot Chat (Is Free)

Basically, just allows access to ChatGPT-4 with web content

Microsoft 365 Copilot (+£20/month if bought as an add-on)  I believe it is also referred to as Microsoft 365 Copilot Pro

Copilot is grounded in the business data you have access to in your enterprise.

Inline copilots, including grounded business data inside the office applications.

Microsoft 365 Copilot is an AI-powered Agent that assists with Microsoft 365 apps like Word, PowerPoint, Outlook, Excel, and Teams. It leverages large language models (GPT-4 and GPT-4Pro) and your enterprise data through the Microsoft Graph.  To work with M365 Copilot, you need the M365 Copilot license, which is pricy, marked at $30 per user per month.  Access to Copilot studio

Copilots in M365

Optimise results by preparing content!  Like docx, pptx and pdf files.  PDF, DOCX, XLSX (kindof), PPTX. Also works on csv, text, html, md files and wav audio files.  Supported file type.

Microsoft Copilot does not allow uploading images/pictures like ChatGPT does as of March 2025, but I don't doubt it is coming.  ChatGPT also can redraw (using DALLe)

RAG - Retrieval-Augmentation Generation basically indexes data into a Vector Index. Then, users can ask questions of the data source, and it retrieves the data in a formatted way for the requesting user.

RAG Explained.

Retrieval  - query the index/Knowledge source (Vector index)

Source/Vector Index supporting AI (body on knowledge to use)

RAG Grounding - is where accuracy is improved by anchoring the model's output to verify correct information.  Stop hallucinations.

Note/Thoughts:

• Index SharePoint documents in the Copilot can be in German or about 100 languages, and I can ask for them in English or other languages.
• Best to keep the source documents short.  
• Copilots in SPO love formatting, i.e., title and header.
• It does not read doc files but limits itself to the main document types. I need to verify this, as it seems wrong.
• Folders have no influence on Vector Search results. They are helpful in choosing sources and managing content but have no effect on vector databases.
• Neither does the depth of a document inside folders.  Vector data is based on the data in the document & the metadata.
• Content works best in tables if it makes logical sense.
• It's better to move Excel document data into Dataverse. Excel is iffy, so don't expect it to be excellent. Or Excel to PDF can work better. Remember to mark tables as tables in Excel (small tables; don't do massive worksheets). Limits are reached quickly.
• Copilot can also return images; it's new, so no doubt more to come...
• Support for Sensitivity Labels, set up so M365 copilot won't access highly confidential data or whatever policy you want.
• Agents can access the MSGrapgh Data, including emails and SharePoint Onedrive.

Prompt Engineering

Cooking up a great prompt: Getting the most from Copilot - Microsoft Support - How to ask Agents / Copilots..

AI Copilot comparrison

 Lunchtime play ...  Claude.io was the best I used... Deepseek didn't work....

AI Engine Comparison Test:

I recently asked a few AI engines a complex tax query:

Perplexity Pro (paid): While I love the app, the answer was not great 6/10

ChatGPT (free): Excellent, factually correct, not too clear in one area 8/10 

DeepSeek: I registered and tried the search, but got the result "The server is busy. Please try again later."  I tried a few times, it is working for common queries, but I assume as this logic wouldn't be cached, it can't even have an attempt with the free version 2/10.

Bing/M365 Copilot: Got a fairly similar result to ChatGPT missing an option and not as well laid out 7/10 

Claud.io: Clean result that is factually correct and offered possible items that would affect the calculation 10/10

Perplexity is my default AI power Search Engine:

Perplexity and the others are great for teaching me this (I use a homemade flip learning type approach), and here are my "follow-on" questions. However, to truly understand something, I still use books (mixed with perplexity), but nothing beats a human-written or recorded topic to give the best understanding.

Prompt Engineering with Microsoft Copilot

Prompting Microsoft Copilot: Prompting is asking the copilot to give you information.

Four parts to cover in your prompt> 1. goal 2. context 3. source 4. expectation

1. Goal - what do I want, e.g., tell copilot what we want

I want tactics for pricing my SaaS products

2. Context - Why do I need it

e.g., this is a new product in the B2C space

3. Sources - optional - ask from specific resources

e.g. provide my company stats and ask to compare to my market (from the LLM)

4. Expectations - Table of info, summary, or even an image(maybe not)

M365 Copilot app.

Apps that M365 Copilot embedded with if you have the M365 licence include: 

1. Word, 2. Excel, 3. PowerPoint, 4. Outlook, and 5. Teams

1. Word

Word Copilot is part of the M365 copilot branding.  Generates scaffolding/first draft.

2. Excel

Use in Excel with your own data - allows easy query using English/natural language.

3. PowerPoint

Draft a presentation using org themes based on prompts. You can also use Copilot to add images you create using Copilot (DALL-e).

Ignite 2023 - Microsoft Fabric - Introduction

GA: Prepare your data for AI innovation with Microsoft Fabric—now generally available | Microsoft Fabric Blog

Everything is brought in and available for analysis in a single Service.  Microsoft Fabric is a unified platform that brings all your analytics under a single service.

OneLake - per Fabric instance.  Stores all data within the SaaS data lake (scales itself), automatically indexes data, and abides by AIP rules/labels.  Intelligent data foundations.

All data is held in the Delta Parquet format (same format for any source).  Data is ready to use.  One copy of data.

SaaS single service, no need to bring pieces together; one data source doesn't need to moved to slice data.  Data stays at the original source but can be worked with, this all falls under the OneLake concept.  Can query using multiple approaches. Create a shortcut to files/folders/databricks, and it becomes part of OneLake while the underlying data resides in the original location that is now linked (only works on Parquet and specific file types).  

Mirroring in MS Fabric - get same benefits of shortcuts, but can connect to databases including SnowFlake, Dataverse, AWS S3 buckets & CosmosDB.  Mirroring is always up to date in real time.  Data is stored in Delta Parquet format so can now use.  With these 2 approaches can use nearly any source. lots of connectors so you could use: Dataverse, Cosmos, Snowflake, SQL Server, blobs on S3,..  Then can write queries across all the data. 

Copilot in Microsoft Fabric will help bring and analyse all the data.

Copilot for Power BI is impressive for building reports, but I need to play with it more.

Power BI is basically becoming Microsoft Fabric. The report generation piece is still called Power BI, but it falls under the MS Fabric product. Licensing for PowerBI Pro is converted to MS Fabric, and you cannot stay on Power BI Premium.

MS Fabric has a new way to access data. It is impressive in that it is fast, real-time, stores data once, carries ACLs/permissions with a lot of the data.  The ETL capabilities are amazing and configured for development.

MS Fabric also supports Real-Tile Intelligence (RTI) and SQL Azure integrated.

Last updated: Feb 2025

Ignite 2023 - Keynotes - Summary

15 & 16 November 2023

Good Keynote: AI is driving a lot of innovation.

Microsoft Fabric in GA (25k instances already).  New feature is 'Mirroring' - copy cosmos/SQL et al into Fabric.  OneLake.  Can bring lots of data from multiple sources into Fabric in near rela time.

MS Teams (320 million users):  Bring everything to the user in one place, not just communications but a canvas for apps.  Good place to build line of business applications.  New teams app - way faster, easier to use.  Teams Premium - intelligent meeting recap is working well, can integrate recap with copilot. 

Copilots - needed for nearly everything you do.  understand context of where you are.  MS has hundreds of copilots.

Copilot Studio - Custom GPT's, can add plugin's to add your own data, can hook into an enterprises unique data.

Copilot for Service - allows agents to get information to provide support, looks interesting.

Personal thoughts: AI is going to be a mega trend that will influence the world hugely, there will be lots of weird decisions on the journey. Currently, it is mainly proving useful as another tool to help improve existing processes.  AI helps me work faster and spend my time on exploration rather than bring base understanding together.

Part 2 Keynote:

Microsoft Graph gives the copilot context within an organisation.  Use plugins to add enterprise data or Open AI GPT's.

Surface Pro Hub 3 released  - looks good, rest of the hardware looks higher spec.

SharePoint Premium - improved knowledge and content management on SharePoint.

Copilot Studio - useful to build internal copilots.  1. Connect copilot to other systems using plugins or GPTs 2. create workflows 3.  Controlled by IT.

Copilot Studio overview

Mesh - Teams can join immersive experience/events, not sure what this means.  GA expected Jan 2024.

Microsoft 365 copilot release to GA 1 November. 

Why Copilot? MS are describing it as a productivity multiplier.  Allows users to be more productive and more creative.  Improves quality of work, avoids searching - as expected.  Makes mistakes but is getting better.

Microsoft Copilot - Bing chat is just MS copilot

So when logging use Entra Id (Azure AD), get contextual enterprise information.  Inherits security and privacy policies.  ACL controlled.  Includes MS graph and Apps.

Try it out: Copilot.microsoft.com  - Chat data is not saved/stored by MS.  Change from "web" to "work".  Also available in Windows taskbar

Ability to use copilot to pull in information, show more graphs, get data.  Good word example getting data from a pptx.

Great example of querying Excel using copilot, created a pivot table. Contrived but looks good, added rainfall from web to look at sales.  Powerful.

Never thought of copilots for being a participant in a meeting - might us amazing.  In teams meeting, takes real time notes, and pulls in info and summaries points for next meeting.  Add as a collaborative partner, can visualize discussions on a meeting whiteboard.

Loop - flexible collaboration, now with copilot.  Not my area but sounds impressive - i don't get it.  People, working with people, now also working with copilot.  Okay.

Copilot for Sales - looks promising.  Hooks into existing CRMs.

Copilot for Service - working with customers, get data that is correct to solve customers problems.  Concise summary, helps craft emails, updates CRM.  Looks very interesting!

Viva - Microsoft copilot dashboard powered by Viva - not sure on this topic.

Summary: People using copilot don't want to loose it.  AI is bringing big changes to many industries.  Promise is to take the grind out of work - sounds great let's see.  Copilot/AI will be a tool and shape how we work.