Swift Security Docs
  • Introduction to Swift Security
  • Onboarding
    • Tenant Setup
    • Product Deployments
      • Browser Extension
      • LLM Guardrails
        • LLM Guardrails API Integration
      • VS Code IDE Extension
    • Directory Sync
      • Configuring Google Directory Sync
      • Configuring Microsoft Directory Sync
    • MDM
      • Extension Deployment Via Google Workspace
      • Extension deployment via google workspace + MDM at device level
      • Extension Deployment Via Microsoft Intune
        • Chromium Browsers in Windows
        • Edge Browsers in Windows
        • Firefox Browsers in Windows
      • Extension Deployment Via Kandji
        • Chromium Browsers in Mac
    • Infrastructure
      • SaaS Model
      • Hybrid deployment (coming soon)
  • Administrative Guide
    • Console Users
      • Role Creation
      • RBAC General Settings for Login Methods (for the Console)
      • User Creation
      • SSO login(okta)
    • Swift Detection Engines
      • Data Identifiers
        • Custom Data Identifiers
      • EDM Dictionaries
        • EDM Rule
        • EDM Profile
        • EDM Extension Policy
      • Data Rules
        • Custom Rules
      • Data Profiles
      • LLM Guardrail Scanners
        • Data Protection Scanner
        • Gibberish Scanner
        • Ban Substrings Scanner
        • Invisible Text Scanner
        • Code Scanner
        • Language Scanner
        • Sentiment Analysis Scanner
        • Jailbreak Scanner
        • Toxicity Scanner
        • Prompt Injection Scanner
        • Token Limit Scanner
        • Reading Time Scanner
        • Language Same Scanner
        • No Refusal Scanner
        • Factual Consistency Scanner
        • Bias Detection Scanner
        • URL Reachability Scanner
        • Nudity Scanner
        • Gender Scanner
        • Celebrity Scanner
        • Face Scanner
        • Race Scanner
        • Performance and Benchmark
    • Browser Extension
      • Extension Installation
      • Granular Policies
        • Control URL access
        • Protect company data
        • Protect against Threats (Coming Soon)
      • Extension Alerts
      • Extension Events
      • Extension Popups
      • Browser Extension Coverage
    • LLM Guardrails
      • LLM Guardrails Policies
      • LLM Guardrails Alert
      • LLM Guardrails Events
    • Regulation Laws
  • Assets
    • Applications
    • Users
    • Extensions
  • Integration
    • Notification
      • Jira
      • ServiceNow
      • Slack
      • Splunk
    • Forensic
    • Feature
      • Rules Glossary
        • United States
        • Canada
        • Latin America
        • European Union
        • Australia
        • APAC (Asia-Pacific)
        • EMEA Countries
        • Others
      • Data identifiers Glossary
        • United States
        • Canada
        • Latin America
        • European Union
        • Australia
        • APAC (Asia-Pacific)
        • EMEA Countries
        • Others
      • Supported MIME Types
      • Supported OCR Format
    • Manage unauthorized access from unmanaged browser
  • Settings
    • Manage Reasons
    • Audit Log
  • Release Notes
    • Version - 1.26
    • Version - 1.25
    • Version - 1.24
    • Version - 1.23
    • Version - 1.16
    • Version - 1.15
    • Version - 1.14
    • Version - 1.13
    • Version - 1.12
    • Version - 1.11
    • Version - 1.10
    • Version - 1.09
    • Version - 1.08
    • Version - 1.07
    • Version - 1.06
    • Version - 1.05
    • Version - 1.04
    • Version - 1.03
    • Version - 1.02
    • Version - 1.01
Powered by GitBook
On this page
  1. Administrative Guide
  2. LLM Guardrails

LLM Guardrails Policies

PreviousLLM GuardrailsNextLLM Guardrails Alert

Last updated 9 months ago

Navigate to the Policies section and select "LLM Guardrails".

Customize the detector to ensure it identifies and manages specific data types accurately before finalizing your policy.

To customize a detector, follow these steps:

  • Navigate to the 'Customize Detectors' section.

  • Select the application you want to configure and click the 'Action' button to edit.

  • A list of all detectors will be displayed. Choose the detector you want to customize.

  • Double-click on the policy action of the chosen detector.

  • From the drop-down menu, choose the policy action (Block, Alert only etc..)

  • click 'Action' and select 'Edit' to choose a profile for the Data Protection Detector.

  • Select the desired profile.

  • Click 'Submit.'

  • Click 'Save.'

  • You will see a confirmation message: 'Input scanner updated successfully.'

  • Repeat these steps to edit all input and output scanners as needed.

To create a policy, follow these steps:

  • Navigate to the 'Policy List' section.

  • Create new policies by clicking on "Add New Policy", fill in the necessary details, and click to "NEXT".

  • Fill the Match Criteria for your chatbot select Application Name from the list of integration.

  • Specify which users or user groups this policy will affect.

  • Check boxes for specific types of detector you need in the input and output respectively.

  • click Next

Notification want as per organization Need(it is optional):

  • Want to Receive Notification on which Channel.

  • Select Frequency(Immediate, Every Hour, Evert Day)

  • Review the policy details and Ensure all details are accurate. Click "CREATE POLICY" to create the new policy.

  • Policy created successfully

After Policy is created Enabled the status

Edit the Policies:

  1. Select the "Edit" option from the action menu.

  2. Update the necessary details in the Policies.

  3. After making the required changes, click the "Save changes" button to apply the updates to the Policies.

Deleting a Policies

Choose the policy to Delete:

  1. Find the policy you wish to delete from the list.

  2. Click on the three vertical dots (action menu) next to the policy you want to remove.

  3. Select the "Delete" option from the action menu.

  4. A confirmation pop-up will appear. Review the details to ensure you are deleting the correct policy.

Confirm the Deletion:

  1. Click the "YES" button in the pop-up to delete the policy.