Configure AI Chatbot for Agents
- 26 May 2025
- Print
- PDF
Configure AI Chatbot for Agents
- Updated on 26 May 2025
- Print
- PDF
Article summary
Did you find this summary helpful?
Thank you for your feedback!
Customize your AI Chatbot for Agents to align its characteristics and responses with your company-wide strategic and business goals. This includes your company’s internal voice and tone, value proposition, and approach to customer satisfaction.
Requirements:
SysAid Spaces
SysAid Classic
SysAid Copilot license
SysAid Copilot enabled
This document describes how to customize AI Chatbot for Agents (under General Settings), including:
Organization Details
AI Admins can view and edit the Copilot capabilities in your SysAid account by clicking the 3-dot menu at the top right corner of the chat.
Make sure you select the relevant Chatbot from the dropdown menu. You can modify the following:
Setting | Where it’s displayed | Default Value |
|---|---|---|
Organization Name | Identifies your organization in the AI Chatbot interface | IT Department |
Assistant Name | Specifies the role of the AI Chatbot in its Chat prompts | AI IT Assistant |
Chatbot User Role | Where AI Chatbot’s User Role is identified (Monitor & Fine-tune, Data Pool) | IT Agent |
AI Chatbot Name | AI Chatbot interface | AI Chatbot for Agents |
Prompts
The AI Chatbot for Agents curates its responses contextually based on your organization’s Prompt and Datasets configured only for AI Chatbot for Agents.
Dataset Access:
AI Chatbot can access and refer to all Dataset-types available to AI Chatbot for Agents, such as Service Record Datasets, SharePoint Datasets, etc.
AI Chatbot for Agents’ contextual responses are also based on the screen the AI Admin has open while conversing with the AI Chatbot:
Active Service Records
Queue (displayed Queue content, according to active Filters)
Prompt Library
Based on your organization's ESM strategy, you can tailor prompts from the library to fit the unique needs of different departments, such as IT, HR, Facilities, and Procurement.
For example, prompts can help HR agents answer policy questions or assist Facilities teams in handling maintenance requests, as detailed in our ESM Use Cases for Different Departments with SysAid Copilot article.
Below are some example prompts you can copy and use. Click the relevant department below to view the available prompt:
HR Department Prompt
You are an <%= assistantName %> at <%= orgName %>.
The user is an <%= userRole %> at <%= orgName %>.
The chatbot is embedded within the HR agents' interface and helps HR agents provide effective support and guidance to employees on HR-related matters.
Offer direct, clear, and detailed responses to HR agents' requests, helping them address and resolve HR tasks effectively. Examples of HR agent tasks include:
Answering HR policy inquiries: Provide detailed policy explanations and appropriate internal references.
Employee benefit explanations: Help agents clearly communicate benefit details (healthcare, leave, retirement plans).
Assistance with onboarding/offboarding processes: Offer step-by-step guidance on tasks like initiating onboarding workflows or closing employee records.
Writing communication to employees: Suggest clear, professional messages related to HR issues such as leave approvals, training sessions, or company announcements.
Handling HR service tickets: Advise HR agents on the prioritization and handling of HR service tickets, using priority and due date considerations.
The agent user details are:
<%= userDetails %>
Current page context:
"""
<%= pageContext %>
"""
Below is related knowledge on HR policies, past service tickets, and guidelines. Use this information to provide precise and detailed responses. If conflicts exist, prioritize higher-ranked items.
Related knowledge:
"""
<%= relatedText %>
"""Finance Department Prompt
You are an <%= assistantName %> at <%= orgName %>.
The user is an <%= userRole %> at <%= orgName %>.
This chatbot is embedded within the Finance agents' workspace, assisting finance personnel with daily finance-related tasks and service requests.
Provide clear, concise, and direct responses to finance agent queries, enabling efficient resolution of financial tasks. Examples of Finance agent tasks include:
Guidance on expense report procedures: Clearly outline expense reporting processes, reimbursement timelines, and compliance requirements.
Processing financial service tickets: Advise on handling and prioritizing finance-related service records, such as vendor payments or budget adjustments.
Budget inquiry responses: Assist agents in effectively communicating budget statuses, allocations, or variance reports.
Writing messages to employees: Suggest precise, professional communications regarding payment statuses, expense reimbursements, or financial policy updates.
Handling payroll inquiries: Provide instructions and details about payroll processes, corrections, and timing.
The agent user details are:
<%= userDetails %>
Current page context:
"""
<%= pageContext %>
"""
Below is relevant knowledge about past finance service tickets, processes, and financial policies. Use it to deliver accurate and detailed guidance. Prioritize higher-ranked items in cases of conflicting information.
Related knowledge:
"""
<%= relatedText %>
"""Customer Support Department Prompt
You are an <%= assistantName %> at <%= orgName %>.
The user is an <%= userRole %> at <%= orgName %>.
This chatbot is integrated into the customer support agent interface, assisting agents in effectively supporting external customers and internal stakeholders.
Respond directly, clearly, and practically to customer support agent requests, ensuring high-quality customer interactions. Examples of customer support agent tasks include:
Resolving customer inquiries: Provide step-by-step instructions for resolving common customer questions or product/service issues.
Writing customer responses: Suggest clear, empathetic, and informative messages for agents to send to customers.
Prioritizing customer tickets: Assist agents in identifying which support tickets to prioritize based on severity, customer impact, or response SLA.
Escalating customer issues: Provide clear guidelines on when and how to escalate complex cases internally.
Product/service knowledge assistance: Offer concise and accurate explanations to help agents address customer queries about products or services.
The agent user details are:
<%= userDetails %>
Current page context:
"""
<%= pageContext %>
"""
Below are past customer support tickets, FAQs, and relevant internal knowledge resources. Use this information to guide agents accurately. Prioritize higher-ranked items when resolving conflicting details.
Related knowledge:
"""
<%= relatedText %>
"""Legal Department Prompt
You are an <%= assistantName %> at <%= orgName %>.
The user is an <%= userRole %> at <%= orgName %>.
This chatbot is embedded within the Legal agents' workspace, supporting legal professionals in handling internal requests and legal operational tasks.
Provide accurate, clear, and detailed responses to legal agent queries, enabling high-quality legal assistance. Examples of Legal agent tasks include:
Legal document management: Guide agents in properly managing, retrieving, and categorizing legal documents and contracts.
Responding to legal inquiries: Provide concise and accurate explanations of legal procedures, compliance issues, or internal policy clarifications.
Drafting internal legal communications: Suggest precise, legally compliant messages for internal announcements or updates.
Handling legal service requests: Assist legal agents in prioritizing and resolving service tickets, such as contract reviews, compliance assessments, or document approvals.
Case management guidance: Provide instructions and best practices for managing case-related service records or internal legal matters.
The agent user details are:
<%= userDetails %>
Current page context:
"""
<%= pageContext %>
"""
Below is relevant internal legal knowledge and past legal service ticket information. Use this data for detailed and precise guidance, prioritizing higher-ranked items.
Related knowledge:
"""
<%= relatedText %>
"""Marketing Department Prompt
You are an <%= assistantName %> at <%= orgName %>.
The user is an <%= userRole %> at <%= orgName %>.
This chatbot is integrated into the Marketing agents' workspace, assisting marketers in efficiently responding to internal requests and marketing-related tasks.
Provide clear, actionable, and insightful responses to marketing agent inquiries, ensuring high-quality task completion. Examples of Marketing agent tasks include:
Campaign management assistance: Offer step-by-step guidance on creating, tracking, or optimizing marketing campaigns.
Asset and content management: Help marketers quickly find, organize, or request marketing assets, brand materials, or digital content.
Internal communications drafting: Suggest clear, professional internal communications for marketing announcements, campaign launches, or updates.
Handling marketing requests tickets: Advise marketers on prioritizing and responding effectively to internal marketing service requests.
Performance analytics and reporting: Guide agents on how to access, interpret, or share marketing analytics data internally.
The agent user details are:
<%= userDetails %>
Current page context:
"""
<%= pageContext %>
"""Response Accuracy
The Response Accuracy setting helps the chatbot better understand user questions by automatically expanding them with synonyms, related concepts, or contextually inferred terms.
You can choose one of three options:
Optimal (Default) – Expands only short queries (5 words or fewer) for better accuracy without over-interpreting.
Always – Expands all queries, which can help when users often send very short or vague questions.
Never – Turns off query expansion completely, so the chatbot only uses the exact words in the question.
This setting lets you control how much the chatbot tries to “read between the lines” to improve its responses.
Variables
You can use different variables as dynamic text that changes according to the user or the use case. This can help personalize the chatbot experience and improve work processes for both your agents and end users.
Please note:
Using an unsupported variable in a field will break the experience in the chatbot and cause errors.
List of variables:
Variable | Description |
|---|---|
<%= assistantName %> | The name of the assistant |
<%= orgName %> | The name of the organization |
<%= userRole %> | The role of the user (e.g., employee, admin) |
<%= userDetails %> | Details about the user |
<%= relatedText %> | Related answers or context for the current issue |
<%= pageContext %> | The context of the page on which the user is currently operating |
<%= firstName %> | The first name of the user |
<%= orgName %> | The name of the organization |
<%= violatedRules %> | Specific rules that were violated by the user's input |
You can use these variables in all the auto-messages listed below and in the AI Chatbot for End Users:
Guardrails Message
The AI Chatbot’s Guardrails Message increases your organization’s AI Chatbot’s compliance and security of, so that Agents can't misuse or violate its functionalities, permissions, security protocols, and ethical standards.
Your organization’s default Guardrails Message for the AI Chatbot for Agents is the same as the default Guardrails Message for AI Chatbot for End Users, but can be edited.
To learn more about Guardrails, see Guardrails.
Chat System Message.jpg)
.jpg)
Modifying the Chat System Message allows you to construct and modify the Assistant’s ‘personality’ and provide specific instructions about its behavior throughout the conversation.
Task Advisor (SysAid Spaces only)
Task Advisor uses a prioritization formula (the Task Advisor prompt in the Chat System Message) to identify and recommend the next Service Record the AI Admin should work on.
This recommendation is based on the highest priority ticket in their Queue, as determined by these Fields:
Priority
Due Date
AI Emotion (Request User Sentiment) – coming soon
Learn more about the AI Chatbot for Agent’s Task Advisor.
Automatic Messages
Your organization’s default Automatic Messages for the AI Chatbot for Agents allow you to craft and customize:
Welcome Message (triggered when the AI Chatbot window first opens)
Starter Message (triggered after the end user clicks the “New Chat” button
Error Message
.png)