Help Center / AI Assistant / Configuration

Configuration

The AI Assistant lets you analyze risk data through natural language. Before using it, you need to configure an AI provider.

Provider setup

MTC Skopos supports three provider types:

ProviderModelsUse Case
AnthropicClaude Sonnet, Claude OpusRecommended default
OpenAI CompatibleGPT-4o, GPT-5, o3, local modelsOpenAI API or compatible endpoints
Azure OpenAIGPT-4o (Azure-hosted)Enterprise deployments with Azure

Setting up

  1. Go to Settings > AI Assistant
  2. Select your Provider Type
  3. Enter your API Key
  4. Choose a Model (defaults to Claude Sonnet for Anthropic)
  5. Optionally set a custom Base URL for self-hosted or proxy endpoints

Azure OpenAI

For Azure deployments, you also need to configure:

  • Base URL: Your Azure OpenAI endpoint
  • API Version: Defaults to 2024-10-21
  • Auth Header: Defaults to api-key

Model settings

SettingDefaultDescription
Temperature0.3Controls response creativity (0.0 = deterministic, 1.0 = creative)
Max Output TokensAuto-detectedMaximum length of AI responses
Response LanguageEnglishLanguage for AI responses
Context Window200,000Total conversation context size

Tool limits

You can control how much data the AI retrieves per query:

SettingDefaultMax
Batch size1025
Search results10100
Entities per risk20100
Overview top N10100

Lower values produce faster, cheaper responses. Increase them when you need more comprehensive analysis.

Updated on: 2026-03-29

« Back to AI Assistant