Artificial Intelligence Corporate Risk
  • Welcome
  • Getting Started
    • Inviting Users
    • Adding New Large Language Models
      • Azure OpenAI Service
      • OpenAI
      • Mistral
      • Google AI
      • LLaMA AI
      • AWS Bedrock
  • Chat
    • Initiating a Chat
    • Viewing Chat History
  • Dashboards
    • Creating Dashboards
    • Dashboard Elements
      • Top N
      • Charts and Graphs
      • Totals
      • Maps
  • Monitoring
    • Adding a User to the Monitor Role
    • Setting up alerts and issues
    • Editing Issues
  • Compliance
    • Adding a User to the Compliance Role
    • Creating a Search
    • Consuming the Results
  • Admin
    • AI Agents
      • Adding a New Agent
        • General Settings
        • Agent Engine Properties
          • Azure OpenAI
          • OpenAI
          • Mistral
          • Google AI
          • LLaMA AI
          • AWS Bedrock
        • Advanced Settings
          • Usage
            • Max Messages
            • LLM Temperature
          • Scanners
            • AI Scanners
            • General Scanners
          • API Keys
          • Files
      • Editing an Agent
      • Deleting an Agent
      • Adding from a Template
    • Company
      • General Information
      • External Agent Provider Settings
    • Custom APIs
      • OAuth2 API
      • Adding a New API
        • API Information
        • API Headers
        • API Endpoint Parameters
        • API Query Parameters
        • Body Parameters
      • Editing a Custom API
      • Deleting a Custom API
    • Custom Database
    • Users
      • Inviting a New User
      • Deleting a User
      • Roles
        • Accessing User Roles
      • Assigning an Agent
      • Setting a Default Agent
    • Groups
      • Adding a New Group
      • Deleting a Group
      • Assigning a User
      • Removing a User
      • Adding an Agent
      • Removing an Agent
    • Agent Scanner Defaults
      • Toxicity
      • Personal Information
      • Topic Scanner
      • Prompt Injection Detection
      • Regex Scanner
      • Geographic Gating
      • Language Detection
      • Allowed File Types
    • Logs
      • Interpreting Logs
  • Server Admin
    • Upgrade
    • Default Agents
      • Adding a New Agent
    • Data Archive
    • API Access
      • Chat
        • List Agents
        • Create Conversation
        • List of Conversations
        • Get Conversations
        • Ask Agent
        • Chat with Agent
        • Add File to Conversation
        • Add Files to Agent
        • Deleting a File
      • OAuth2
        • OAuth2
        • OAuth2 Token
      • Users
        • List Users
        • Create User
        • Add User to Group
        • Set User Token
        • Delete User
      • How to Launch Our API Example
        • How the Code Works
    • Configure OAuth2
    • Custom Secrets
  • API Overview
    • Authentication
    • Calling the Scanner
    • Consuming the Results
    • 📃Pagination
      • Understanding API Parameters
      • Pagination Helper
      • Example Page
      • Recap
    • AIRisk API OAuth2 Authentication
      • Authorization
      • Authorization Endpoint
        • Example Authorization URL
        • Error Responses
      • Tokens
        • Error Handling
        • Generic vs. User-Specific Tokens
          • Example Usage Flow / Reasons
        • Usage of the Access Token
      • Token Endpoint
        • Example Token Request
        • Error Responses
      • Summary of OAuth2 Authorization Flow
  • Managing Your Account
    • Personal Data
  • Support
    • Onboarding Check List
  • Internal Deployment
    • Outlook Plugin
    • Firewall Rules
    • Infrastructure
    • Graph Connection Requirements
    • Zoom Transcripts
  • Example Python Application
  • Release Notes
    • V4.28
    • V4.12
    • V4.0
    • V3.71
    • V3.0 Beta
    • V2.23
    • V2.22
    • V2.120 HotFix
    • V2.103 June 1
Powered by GitBook
On this page
  1. Admin
  2. AI Agents
  3. Adding a New Agent
  4. Advanced Settings
  5. Scanners

AI Scanners

PreviousScannersNextGeneral Scanners

Last updated 4 months ago

AI Scanners:

    • Description: The Toxicity Scanner identifies and filters out potentially harmful or offensive content from user input or generated responses.

    • Usage: By analyzing the text for indicators of toxicity or inappropriate language, the Toxicity Scanner helps maintain a safe and respectful conversational environment.

    • Description: The PII Scanner detects and masks personally identifiable information to protect user privacy and comply with data protection regulations.

    • Usage: By recognizing sensitive information such as names, addresses, or contact details, the PII Scanner ensures that such data is handled appropriately and securely.

    • Description: The Topic Scanner categorizes user input and facilitates topic-based response generation for improved relevance and coherence.

    • Usage: By analyzing the semantic context and identifying key topics within user messages, the Topic Scanner enables the agent to generate responses that align with the ongoing conversation.

    • Description: Prompt Injection Detection identifies and mitigates attempts to manipulate or inject unauthorized prompts into agent interactions.

    • Usage: By monitoring for anomalies or unexpected changes in conversation dynamics, Prompt Injection Detection helps maintain the integrity and authenticity of interactions.

Toxicity Scanner
PII (Personally Identifiable Information) Scanner
Topic Scanner
Prompt Injection Detection