​
Overview

The Competitor Mention Policy helps organisations prevent references to specific competitors in AI interactions. Built with the same flexible configuration structure as the Sensitive Topic Policy, this policy allows users to define a list of named competitors that should be flagged or blocked when mentioned in prompts or generated responses. This feature supports brand protection, internal compliance, and responsible AI use by ensuring that sensitive or strategically inappropriate references to competitors do not appear in user-facing content or internal workflows.

​
What the Policy Does

​
Purpose

The Competitor Mention Policy is designed to protect organisational interests by restricting references to defined competitors during AI interactions. It helps enforce internal communication standards, reduce reputational risk, and maintain compliance with legal or corporate strategy requirements.

Whether the goal is to monitor competitive references or fully block them, the policy allows precise control over how the AI engages with named competitors.

​
Scope

​
Competitor List Control

Organisations can define a custom list of Competitor Names to manage AI behaviour:

  • Names can be added manually based on the organisation’s unique landscape.
  • There is no valid/invalid distinction—only one list of flagged competitor terms is required.

​
Prompt & Response Configuration

The policy can be independently applied to:

  • Prompts: Inputs from users that might mention competitors.
  • Responses: AI-generated content that could reference competitors.

Each direction of interaction can be enabled or disabled separately to match business goals or risk profiles.

​
Operational Modes

  • Log Only: Detects and records mentions of competitors without restricting the conversation.
  • Log and Override: Prevents the AI from processing prompts or generating responses that include listed competitor names.

​
Threshold Sensitivity

Detection strictness can be adjusted using a sensitivity threshold between 0.2 and 0.9:

  • Lower values (e.g., 0.2) are more permissive and reduce false positives.
  • Higher values (e.g., 0.9) apply stricter filtering for enhanced brand control.

​
Key Features

  • Custom Competitor List: Add any number of competitors relevant to your organisation.
  • Prompt & Response Independence: Fine-tune filtering on input and output separately.
  • Flexible Enforcement Options: Choose monitoring only or blocking functionality.
  • Threshold Sensitivity: Tailor detection rigor to your risk appetite.
  • Full Logging Support: Maintain visibility into where and how competitor names appear.

​
Why Use This Policy?

​
Benefits

  • Safeguards brand identity and strategic positioning.
  • Avoids unauthorised promotion or criticism of competitors.
  • Enhances compliance with legal and internal policies.
  • Allows for transparent auditing and internal review.

​
Use Case: Internal Knowledge Assistant for Enterprise SaaS

​
Scenario

A large enterprise SaaS provider uses an LLM-powered assistant internally to generate marketing copy, product comparisons, and training material. The company wants to ensure that content does not reference competitors like Company X, Y, or Z unless authorised.

​
Challenge

Employees might unintentionally prompt the AI to mention competitor names or generate content that includes comparisons or references to rival platforms, breaching brand guidelines or legal constraints.

​
Solution: Implementing the Competitor Mention Policy

  1. Competitor List Configuration

    • The organisation defines a list of specific competitors by name.

  2. Prompt & Response Filtering

    • Prompt Filtering: Ensures employees cannot input prompts that include competitor names.
    • Response Filtering: Prevents the LLM from generating output that contains competitor mentions.

  3. Enforcement Mode & Sensitivity

    • Log and Override mode ensures all references are blocked.
    • Detection sensitivity is set to 0.85, balancing precision and protection.

​
How to Use the Policy

Note: The following steps guide you through configuring the Competitor Mention Policy using the policy workflow interface.

​
Step 1: Navigate to the Policy Workflow

  1. From the Dashboard, open your project to access the Project Overview.
  2. In the Policy section, click Edit Policy to launch the policy configuration workflow.

​
Step 2: Select and Enable the Competitor Mention Policy

  1. In the Configure Policies tab, click on Competitor Mention from the list of available policies.
  2. The configuration panel will appear on the right-hand side of the screen.
  3. Toggle Enable Policy to ON to activate the configuration options.

​
Step 3: Configure Competitor Names

  1. In the Competitor Names input field, type the names of competitors or any known variations (e.g., “OpenAI”, “Open AI”, “OAI”).
  2. Press Enter after each entry to add it to the list.
  3. Each entry will appear as a tag below the input field. You can remove any entry by clicking the X on the tag.

​
Step 4: Set Application Scope

  1. Under Apply Policy To, choose where the policy will be enforced:
    • Prompt – Detect mentions in user input.
    • Response – Detect mentions in AI output.
    • Both – Monitor both directions.

​
Step 5: Configure Enforcement Behaviour

  1. Under Behaviour, choose how the policy should respond:
    • Log Only – Log competitor mentions without interrupting interaction.
    • Log and Override – Block the interaction and return a smart fallback message.

​
Step 6: Adjust Detection Threshold

  1. Use the Threshold Slider to fine-tune sensitivity:
    • A lower threshold (e.g., 0.2) is more permissive and detects broader variations.
    • A higher threshold (e.g., 0.9) applies stricter detection.

​
Step 7: Save, Test, and Apply the Policy

  1. Click Save Changes to store your configuration.
  2. (Optional) Use the Test Policies tab to validate policy enforcement in a sandbox environment.
  3. Return to the Configure Policies tab and click Apply Policies to activate the policy.
  4. A confirmation message will confirm that your policy is live.

The Competitor Mention Policy helps safeguard your brand and strategy by detecting and controlling references to defined competitors across user and AI interactions—ensuring alignment with internal guidelines and competitive positioning.