- 30 Apr 2024
- Print
- PDF
Configure AI Chatbot
- Updated on 30 Apr 2024
- Print
- PDF
AI Chatbot Data Sources & Guardrails
Configure which Datasets to include in your AI Chatbot’s Data Pool, and make sure your AI Chatbot interactions with End Users abides by security protocols and ethical standards
Requirements
SysAid Copilot license
SysAdmin or AI Admin permissions
The AI Chatbot utilizes organizational data combined with Large Language Models (LLMs) to generate intelligent, solution-oriented responses to user queries in chat threads. These automated responses save the time that Admins would otherwise need to spend crafting articulate, relevant answers to user inquiries.
End users can trigger the AI Chatbot from both the Self-Service Portal (via the Service Catalog Tile) and the Email Integration.
Notes
The “Enable SysAid Copilot” checkbox is only clickable if the SysAid account has a valid license
If the checkbox is unchecked, AI Chatbot features won’t be accessible
This document provides a brief overview of how SysAdmins can:
Configure AI Chatbot Data Sources
You can configure multiple Datasets as part of your Data Pool, which includes the following data configuration sources:
Q&A Sets
Knowledge Base Articles
Documents
URLs
Service Record Data
SharePoint Connect
Configure AI Chatbot Guardrails
You can increase the compliance and security of your organization's AI Chatbot so that the AI Chatbot's functionalities, permissions, security protocols, and ethical standards cannot be misused or violated.
Note
The “Enable AI Chatbot Guardrails” checkbox is disabled by default
Configuring the AI Chatbot's Guardrails Rules involves defining two parameters:
AI Chatbot Guardrails Rules
These default rules relate to topics or texts that end users might include in their queries, such as:
Inappropriate content (profanity, vulgarity, hate speech, etc.)
Embedded content or commands
Requests to change system instructions
Requests to change scripting, language coding, command language, etc.
Attempts to access data or functionality outside the scope of the intended query processing
Attempts to exploit potential vulnerabilities in the system
Attempts to hide malicious intent or content
SysAid Copilot provides eight default Guardrails Rules which the AI Admin can choose whether to edit, keep, or remove.
User Violation Message
You can create a User Violation Message (System Message) to serve as the AI Chatbot's automatic response to user queries that violate your organization's Input Compliance Rules.
This automated message can also explicitly specify which of your Input Compliance Rules were violated.
To modify (or disable) your AI Chatbot's Guardrails Rules and content, go to AI Chatbot Settings > General > Guardrails section.