0% found this document useful (0 votes)
12 views

Notes for Copilot Studio and Copilot

The document outlines the functionalities and components of Copilot Studio, emphasizing the importance of a dialogue manager, intent, and entities in natural language processing. It discusses the integration of custom copilots with Microsoft 365 applications, the use of APIs for automation, and the challenges of indexing modern websites. Additionally, it suggests various copilot ideas for training, meetings, and client interactions, along with specific flows for user queries and ticketing processes.

Uploaded by

murebyousef
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
12 views

Notes for Copilot Studio and Copilot

The document outlines the functionalities and components of Copilot Studio, emphasizing the importance of a dialogue manager, intent, and entities in natural language processing. It discusses the integration of custom copilots with Microsoft 365 applications, the use of APIs for automation, and the challenges of indexing modern websites. Additionally, it suggests various copilot ideas for training, meetings, and client interactions, along with specific flows for user queries and ticketing processes.

Uploaded by

murebyousef
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 7

Notes for copilot studio and copilot

 The above shows why we need a dialogue manager, we need a


way to take specific actions such as generating responses comes
from generic question. If you want to take actions you go to the
last layer and the second layer allows you to give context to the
copilot.


 Two parts are typically present in natural language processing.
First is intent which is what action do you want to do. Secondly it
is entities that define what the intent is acting on.
 Within copilot studio, you can define the intent and entities when
creating your own copilot. You can define how it answers and
also specify specific responses for specific questions. From there
you can create a flow and link that with another application that
can handle the actions.

 You may need to use a 365 copilot for things like finding specific
emails, answering general questions and having a wide scope
but still have the integrations with m365 apps and services. We
can use the custom copilots for these specific reasons:


 Search copilotsimplementationguide by Microsoft to get help on
how to work with copilotstudio.
 Copilot studio offers the capabilities to just simply give
commands to your copilot as context and it will create it by
managing the backend and infrastructure. This makes for a very
fast deployment of a copilot to be integrated in a companies
ecosystem. It can be part of Microsoft teams too as an addiontal
app to be used as a personalized company companion.
 Under the actions feature, we can add APIs that allow the copilot
to take actions. This makes process automation duable.
 When using a search engine to be used as a source for your
copilot, do not enable knowledge since it will make the search
engine useless.
 The way the copilot retrieves data from websites to be used as
content is through indexing a simple HTML structure. Problem
with this is that modern websites typically use javascript to make
the websites more appealing and thus it makes it hard for the
copilot to index the information.
 Data than can be fed into a copilot is knowledge (things like
excel, documents, sharepoint), topics where you define what
things to discuss (tailor convos), and actions where I can do
things with APIS.
 When doing topics in copilot studio, we can add a question node,
which defines what it is you want the copilot to respond with for
a specific question.
 When you use part of the new entities synonym as a question to
the copilot, it might skip the question and not register the entity
or topic you had.
 the question isn't asked and is skipped. This is because you've
used entities and slot filling to retrieve the information from
utterance the user submitted. This approach avoids you needing
to ask the user a question that they've already provided
information for
 Different types of variables in Microsoft Copilot Studio include:
 System – These variables are normally populated with system
data. System variables aren't user-made and are part of the
platform.
 Topic – These variables are user-made from either topic Inputs,
the Set a Variable Value node, the Question node or as the
output of other nodes or actions (e.g., cloud flows, HTTP
requests, connectors, custom prompts, plugin actions, etc.).
 Global – These variables are user-made and are available from
any topic, and they're a good way to store data that multiple
topics use to help the conversation, regardless of how many
topics are triggered within it.
 Variables are the best way to store dynamic data or data that
you want to perform conditions or checks on to drive
conversational behavior in a particular way, as you'll observe in
the next task.
 Conditions directly work with variables which you can pick out
from your topics and responses of the copilot.
 One thing with copilot is that when you enter one flow, its hard to
go back to another flow, it doesn’t have the ability to go back.

Maybe use linekdin conjector to get infor about companies.

Maybe use an adaptive card a json file for better looking personal details.

We can test a speech copilot when pushing It to teams or a phone number.

Without a generative method, if the agent detects one entity, it will stay
there in that flow.

Classic methods understands one intent only.

When tryung to browse and use a sharepoint file, it only detects the pdf and
not the excel file.

Indexing a scanned pdf might not be possible to do this. We can maybe use
power automate flow, make it into text and then use that as a word doc or
excel to be used in the knowledge.

Figure out a way to be able to index a javascript website with different


ordering and format to index it in a nice way.

AI builder might be useful.

Look into the youtube videos with indexing schemes.

Linekding sales navigator to get info on people and employees.

Uses appolo software to get more details about people.


Make some of the list divided with emails or numbers and other list without
that.

Use that with a CRM to send emails and info to clients.

People with no emails or numbers we use dripify for, we can use


endorsement on them to add them as a friend and when they accept we say
hello to get a client interaction. Main part of this is to make an initial
interaction to connect with them

Go extrovert might be able to do AI generated comments on their posts to


make more engagement with clients.

Would be a good idea to have a chatbot specific for client interaction.

This is also connected with a sales CRM to keep a history of the people.

Maybe add a process to start interacting with people on linkdin.

Maybe use a copilot studio for sales to intergatr with our main copilot.

Sales navigator and appolo to be used for search criterias.

Amal sabri.

Gather details from user for the issue details section.

Try to fill out details and send a form as a query.

Take the users input as an email and send it to the email given (optional
Flow)

Two main flows:

First one: make a flow for the user to ask a specific query and the chatbot
will reply back with the details of how to solve such issue. This info can be
taken from the company website itself.
Second flow: you can ask the user again for the details of the queries
themselves and then use that information to make the person get sent to a
specific number tailored to that query.

Do I include another subcondition even for the subcondition to talk about the
error type as its own thing?

Copilot ideas:

 Copilot for training: instead of needing to text the talent team or


schedule meetings with people to understand training plans, we can
use a copilot that provides information on what certificates to get for
certain fields, the training plans, and helpful resources to learn.
 Copilot for meetings: have a copilot when people have meetings, it will
summarize the key points being said in the meeting and what the next
steps should be.
 We want to make a copilot that is able to search a sharepoint folder,
from there have access to only the technical documents, be able to
access them and read them and gather information regarding what the
person asked.

Americano notes:
To open a ticket, check the teams name if they have accces to it.

Figure out the categories (ask)

3 main options pop up in the selection, when selecting IT, you can select a
ticket number and add the number, from there add the service for it. To
resolve unlocking account issues, a link shows up to select it. You can make a
ticket if the issue still remains

Maybe add a layer to check if its an information or an issue.

You can ask service request and different options show such as sotware,
security hardware etc

This man flow Is for end users (non restaurant users)

Maybe have a decision tree early on in the flow to check if it’s a user or non
user.

Main problem they face is all of the logic is in one topic

To do:

Redo topics in smaller topics

Ensure the flow is dynamic following variables

Use knowledge to get information from HR for basic enquiries.

Make sure you can build upon the project and add more use cases.

You might also like