Skip to main content

Configure AI Intelligence

Control the underlying technology that powers your Companion. You can select your preferred AI provider and specific model to tailor the quality, speed, and reasoning capabilities of your assistant.

To access these settings, go to User preferences > Intelligence.

Note: These settings are workspace-specific. Changing the AI provider here will not affect your experience in other workspaces.

Select an AI Provider​

Harmony integrates with multiple industry-leading Large Language Model (LLM) providers, giving you the flexibility to choose the "brain" best proves for your needs.

  • OpenAI: The industry standard, offering models like GPT-4o. Best for complex reasoning and high-accuracy tasks.
  • Google: access models like Gemini. Known for strong multimodal capabilities and fast processing.
  • Mistral AI: A leading open-weight provider. accurate and efficient.
  • Cohere: Specialized in enterprise tasks and retrieval-augmented generation (RAG).

Choose a specific Model​

Once you have selected a provider, use the Model dropdown to choose the specific version you want to use.

  • High-Intelligence Models (e.g., GPT-5.1. series, Gemini 3.5 Pro): Choose these for complex analysis, deep reasoning, or drafting detailed documents. They may be slightly slower but offer higher quality.
  • High-Speed Models (e.g., GPT-4o-mini, Gemini Flash): Choose these for quick summaries, simple chat interactions, and instant feedback.

Note: If the Model dropdown is empty, ensure you have selected a Provider card above it first.