SysAid’s CoPilot is an AI-powered suite designed to transform ITSM workflows by automating tasks, improving efficiency, and providing valuable insights for admins and end-users alike.
With features like chatbots, ticket summarization, and automation, CoPilot empowers users to streamline operations, reduce workload, and enhance productivity. Since its launch, over 100 companies have adopted SysAid CoPilot, showcasing its impact and innovative capabilities.
One of the most significant challenges was designing pioneering features that were not only new to the ITSM industry but also groundbreaking on a global scale. These AI tools had to:
As the Lead Product Designer, I managed a small team of two additional product designers, guiding the project through all phases of the design process. My responsibilities included:
Our research and discovery phase was critical in shaping the design and development of SysAid CoPilot’s AI tools. By gathering qualitative and quantitative feedback, we were able to refine and adjust key features based on user insights and market analysis.
This iterative process involved close collaboration with design partners, continuous customer feedback, and research into broader AI market trends.
Throughout the alpha and beta phases, we collaborated with key design partners to gather high-touch qualitative feedback. These sessions focused on usability testing and feature discovery, surfacing opportunities for improvement early in the development cycle. For example, A/B testing helped determine whether the admin chatbot should appear as an overlay or in a dedicated section, and prototyping sessions shaped the AI ticket summarization feature. The feedback received was instrumental in identifying blockers, improving usability, and aligning the product with end-user expectations.
High-touch qualitative feedback from design partners.
Surface issues early, address blockers for adoption, usability, and feature discovery.
Weekly feedback sessions, usability tests, and design feedback forms.
Our feedback channels included in-app surveys, customer-facing feedback forms, and Pendo usage analytics. This feedback helped identify discoverability issues, track AI performance, and fine-tune the chatbot’s responses to fit different organizational needs. One critical finding from this stage was the need for deeper customization options in the admin chatbot, which led to the development of the Fine Tune tools for senior admins.
SysAid’s CoPilot serves three distinct user groups: end users, admins, and system admins. Each group interacts with different parts of the platform, tailored to meet their specific needs. The majority of requests come from end users, while admins and system admins play crucial roles in managing and fine-tuning the system.
While end users represent the majority and handle simpler tasks, admins and system admins, though fewer, manage more complex tasks and rely heavily on CoPilot’s AI tools. The system tailors support based on role, ensuring efficient task management across varying complexity levels.
Profile
Most service requests come from the IT department but can also involve HR, Finance, or other departments, depending on how the company integrates SysAid.
Familiarity
End users are comfortable using the platform to open service tickets and track their status.
Needs
Easy ticket submission, fast responses, and clear communication with IT or other relevant departments.
Tools
Self-service portal (SSP) or Microsoft Teams chatbot, which assists with common requests and service ticket submissions.
Profile
Managing service requests, automating workflows. using CoPilot’s AI features to enhance productivity. using the admin chatbot to get help (via LLM question-answers) and to perform system actions.
Familiarity
Well-versed in ticket management and automation tools. Familiar with AI-driven features like ticket summarization and categorization.
Needs
Streamlined service record management, AI-assisted resolutions, and automation for daily tasks.
Tools
Admin chatbot for performing actions, LLM-powered question-answer system, AI-driven features like ticket summarization and auto-categorization.
Profile
System admins control and define the system’s settings, including managing AI tools, fine-tuning system performance, and overseeing overall usage. They often use the system as regular admins as well.
Familiarity
Highly experienced with customizing AI settings, managing advanced workflows, and analyzing data from system performance metrics.
Needs
Fine-tuning AI tools, customizing system settings, and optimizing overall system performance.
Tools
Usage analytics, fine-tune tools, (Data pool, Monitoring, etc..) AI customization settings, and access to regular admin tools for daily operations.
The design approach for SysAid’s CoPilot centered on creating a seamless, AI-driven experience that integrates efficiently with the existing platform. The goal was to simplify task management for different user roles while ensuring advanced functionalities for admins and system admins. Through iterative testing and feedback loops, the design was refined to enhance user engagement and system performance.
User-Centric AI Interface
Focused on providing AI tools that adapt to the user’s role, offering task-specific features for end users, admins, and system admins.
Minimalistic Layout
The interface was designed to reduce clutter, presenting relevant information and actions at a glance for quicker task completion.
Consistent Visual Hierarchy
Leveraged familiar SysAid design elements to maintain continuity while improving discoverability and navigation.
Adaptive Functionality
Different levels of users experience varying depths of the system, from basic tasks for end users to more complex tools for system admins.
Seamless Integration
CoPilot was designed to integrate smoothly into SysAid’s existing Spaces product, enhancing workflow without overwhelming users with too many changes.
The admin chatbot in SysAid serves as a powerful tool to automate and enhance routine IT tasks, from resolving tickets to applying solutions and generating guides. Built to integrate seamlessly into the SysAid platform, the chatbot reduces manual workload and improves overall efficiency.
Admins can leverage natural language processing to interact with the system, making tasks such as scanning tickets and applying solutions faster and more intuitive. A prime example of its capabilities is how it assists in resolving service records while minimizing the number of steps needed by the admin.
The design was centered around creating a tool that supports both experienced and new admins in performing complex tasks more efficiently. By conducting A/B testing, we determined that integrating the chatbot as an overlay panel provided the best balance between visibility and non-disruption to ongoing workflows.
The strategy also focused on making AI recommendations and automation features accessible with minimal input, allowing admins to quickly apply solutions, review ticket status, or generate user guides, all through natural language commands. This approach enhances task completion speed while maintaining the complexity needed for advanced workflows.
This Video demonstrates how SysAid’s AI-powered chatbot assists admins in efficiently resolving service records. It shows the chatbot identifying urgent tickets, opening service records, offering resolution suggestions, and generating step-by-step guides for end-users, all within a streamlined workflow that automates manual tasks and improves response
The AI Chatbot for End Users simplifies issue reporting and self-service, allowing employees to bypass IT teams for routine inquiries or service requests. Designed for ease of use, it connects directly to SysAid’s ITSM resources, offering a streamlined way for users to troubleshoot common issues or escalate unresolved problems quickly and independently.
We focused on creating an interface familiar to end users by leveraging popular chatbot patterns, ensuring a minimal learning curve. The AI system was designed to integrate into SysAid’s Self-Service Portal and third-party communication tools, allowing users to resolve their issues or submit service records without leaving their preferred environments.
The AI Usage Dashboard provides a comprehensive overview of system utilization, allowing admins to track both end-user and admin interactions with the AI. Key metrics such as service records touched by AI, categorized interactions, and the impact of internal data are displayed, offering valuable insights that support effective decision-making and AI optimization.
Data Clarity
Ensured all critical metrics are clearly displayed, making the dashboard highly navigable for quick analysis.
Actionable Insights
Focused on creating visual cues that highlight trends and deviations, enabling admins to make informed adjustments quickly.
Customization Flexibility
Integrated flexible filters and views so admins can tailor the dashboard to their specific needs, ensuring a personalized and efficient experience.
Handling big data efficiently is a major challenge for system admins, particularly when ensuring chatbots provide consistent, reliable answers. By fine-tuning data sources, admins can ensure the chatbot becomes a persistent assistant that can reduce the workload on IT and support teams by resolving end-user queries independently.
The fine-tuning interface is designed to minimize effort for admins while maximizing chatbot accuracy. Visual clarity and ease of use were paramount in creating an efficient experience.
The Data Pool consolidates various knowledge sources, such as service records, documents, and knowledge bases, into one central location for each chatbot. This ensures the AI pulls relevant information tailored to specific queries, minimizing reliance on IT staff while maintaining chatbot accuracy.
Color-Coded Chips
Each data source is represented with a unique color and icon, enhancing quick recognition.
Visual Weight System
The weight of each source is visually presented through a 1-5 ball system, making it easy to assess the importance of sources at a glance.
Split-Screen Layout
When a source is selected, a split-screen layout allows admins to view and manage its content effortlessly.
Allows admins to continuously improve the chatbot’s performance by reviewing the quality of its responses. Every question and corresponding answer is displayed in an organized table, providing transparency into how the chatbot functions. Admins can modify, approve, or flag answers for future refinement to ensure the accuracy and reliability of chatbot responses.
Editable Responses
Admins can click on any answer to review and refine it directly within the interface.
Quality Scoring
Each response is assigned a quality score, making it easy to identify areas needing improvement.
Visual Cues
Status indicators like color-coded quality scores help admins instantly assess the chatbot’s performance.
Refined Interaction
Quick actions such as marking an answer as irrelevant, keeping the process efficient and intuitive.
