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
