Global Head
February 28, 2025
But what can Microsoft Copilot really do, and how does it affect implementation and compliance with the corporate design? To get to the bottom of this, let’s take a closer look at this Technical White paper.
The research combined desk research with practical insights from Royal Cyber’s experts who rolled-out an effective approach to develope and integrate Copilot with BMC Software.
In essence, this document aspires to empower professionals with the knowledge to navigate the evolving landscape and capitalize on the opportunities presented by Copilot.
In an organization as vast and diverse as our client, managing employee queries across various departments can be a daunting task. With departments ranging from HR and IT to Finance and Supply Chain, each having its own set of policies and documentation in multiple languages, the challenge was to provide a seamless, efficient, and accurate response system for employees.
The traditional methods of handling queries were not only time-consuming but also prone to errors and inconsistencies. There was a critical need for a unified system that could handle queries efficiently and escalate unresolved issues appropriately.
How We Planned It
The solution was to develop an AI Copilot named “BCMBot” using Microsoft Copilot Studio. The primary objective was to create a chatbot that could connect to various SharePoint sites containing organizational policies and documents for different departments such as HR, IT, Finance, Supply Chain, Suppliers, PCards, Global Trade, Capital Assets, Customers, Travel, Risk Management, Communication, Commercial, Legal and Corporate Secretary, and Technical Library. Each site served as a knowledge source for BCMAgent to handle employee queries related to department-specific policies.
The Planning Stage
- Identifying the knowledge sources and integrating them with BMCBot.
- Designing Power Automate flows for different types of requests such as IT tickets, HR tickets, and purchase orders for laptops or desktops.
- Incorporating a ticketing system using BMC Ticketing Software to handle unresolved queries.
- Developing generative actions to understand user needs and provide accurate product suggestions based on role and usage.
The Implementation Stage
The implementation phase was systematically divided into several key steps:
Connecting SharePoint Sites
We began by linking numerous SharePoint sites to BCMAgent, each containing department-specific policy documents in various languages. This extensive repository allowed BCMAgent to access information quickly and provide precise answers to employee queries.
Integration with BMC Ticketing Software
The major standout feature of BCMAgent was its ability to raise tickets in the BMC Ticketing Software automatically. If BCMAgent was unable to resolve a query, it would guide the user to submit a ticket, capturing the necessary input and raising it directly through Power Automate flows.
Product Recommendations
BCMAgent was designed to assist employees in selecting and ordering the appropriate laptop or desktop based on their role and requirements. By leveraging generative actions, BCMAgent could understand the user’s needs and suggest the most suitable products.
Power Automate Flows
We developed specific Power Automate flows for different types of requests, ensuring that tickets and purchase orders were raised accurately and efficiently. This automation streamlined the process, reducing the time and effort required for manual interventions.
Development Structure
Instruction to Copilot:
Instructions are essential for guiding a copilot on how to respond to user inquiries. They provide direction on the appropriate actions and considerations necessary when preparing a response to user queries. Here is the below screen shot of Instruction which we provided to this copilot.
Below are the components utilized in developing this copilot:
Objective:
- Source Verification: Review content on provided SharePoint sites and documents to find accurate answers.
- Response Preparation: Craft responses based solely on the reviewed content, ensuring accuracy and completeness. If steps are provided, list all steps without omitting any.
Guidelines:
- Data Consistency: Retain all numeric data exactly as presented in the source.
- No Cross-Referencing: Do not cross-check or merge information between sources or documents.
- Answer Integrity: Responses must reflect accurate source information without personal interpretation or modification. if same response is available in multiple sources/documents then reference all sources in response as reference.
Response Instructions:
- Prepare, complete answers in details using a simple, professional tone and answers content should be correct as available in sources.
- Do not offer web-based, Al based or generalized answers.
- References and response should be accurate and aligned with query.
Step 1: Setup Knowledge Sources
Knowledge Sources is the section where we compile a knowledge base for the copilot. We have integrated all relevant SharePoint sites into this copilot knowledge base. Below is a screenshot illustrating a list of multiple sites that contain numerous documents within their libraries, representing various departments.
Step 2: Setup Topic Triggers
Knowledge Sources is the section where we compile a knowledge base for the copilot. We have integrated all relevant SharePoint sites into this copilot knowledge base. Below is a screenshot illustrating a list of multiple sites that contain numerous documents within their libraries, representing various departments.
Step 3: Defined Actions (Power Automate Based)
Actions play a crucial role in the development of Copilot, particularly regarding external system connectivity. We have defined actions based on Power Automate flows, which include multiple processes for raising tickets on the BMC Ticketing system.
Step 4: Setup Configurations and User Authentications
Authentication and configuration are essential for any application. We have set up Azure Active Directory V2 for user authentication and configured single sign-on with Microsoft Entra ID for seamless team authentication.
Challenges and Resolutions
Challenges Faced
While the development and implementation of BCMAgent were successful, we encountered several challenges:
Data Integration:
Ensuring seamless integration of data from various SharePoint sites, each with a different set of policies and documents, was a complex task. We had to ensure that the information was updated regularly and accurately fetched by BCMBot.
Language Translation
Handling multiple languages required robust translation features. We had to ensure that BCMBot could either provide translations of the retrieved articles or offer a translation feature, making the information accessible to all employees.
Security and Compliance
Maintaining high standards of data security while ensuring compliance with relevant data protection and privacy regulations was paramount. We had to implement stringent security measures to prevent any vulnerabilities.
Resolutions
We overcame these challenges through innovative solutions and collaborative efforts:
Enhanced Data Integration:
We developed advanced data integration techniques to ensure that SharePoint sites were seamlessly connected, and information was accurately retrieved, providing reliable responses to employee queries.
Robust Language Translation
By integrating powerful translation services, we ensured that BCMAgent could handle multiple languages effectively, making the chatbot more inclusive and user-friendly.
Stringent Security and Compliance
We implemented comprehensive security protocols and compliance checks to maintain data integrity and protect sensitive information, adhering to all relevant regulations.
Key Takeaways
The successful deployment of BCMAgent has provided us with several valuable insights:
Improved Efficiency
BCMAgent has significantly reduced the time and effort required for employees to seek information, enhancing overall productivity and satisfaction.
High User Adoption
The intuitive interface and accurate responses have led to high user adoption rates, with employees appreciating the ease of accessing information and raising tickets.
Scalability
The scalable architecture of BCMAgent allows for future enhancements, such as expanding the knowledge base and integrating additional company systems, ensuring that the chatbot can evolve with the organization’s needs.
Final words
Author
Zeeshan Mukhtar
Websites used to be something you built once and basically forgot about. That doesn’t work …Read More »- Learn how to plan an Optimizely CMS 13 upgrade with .NET 10, Optimizely Graph, Visual …Read More »
- Learn how AI meeting notes automate summaries, action items, and insights from video meetings using …Read More »
