Configuring AI Models

Nectir AI allows you to select different AI models for your assistants, each with unique capabilities and performance characteristics.

Selecting an AI Model

  1. Navigate to your Assistant’s settings
  2. Click on Advanced in the settings sidebar
  3. Choose from the available models based on your Group needs:
    • GPT-4o: Latest model with enhanced capabilities and multimodal support. Excels in generating accurate, context-rich responses for healthcare, STEM, and social sciences.
    • Claude 3.5: Advanced model with strong reasoning and instruction following. Shines in humanities, literature, and creative writing with its creativity and conversational flow.

Comparing Model Capabilities

FeatureGPT-4oClaude 3.5
ReasoningExcellent for complex problem-solvingStrong analytical and critical thinking
Content GenerationVersatile across many domainsExcels at nuanced and detailed explanations
Multimodal SupportCan analyze and discuss imagesCan analyze and discuss images
Response StyleMore direct and conciseMore conversational and elaborative
Best ForHealthcare, STEM, Social SciencesHumanities, Literature, Creative Writing
StrengthsAccuracy, precision, problem-solvingCreativity, nuanced thinking, interpretation

What’s Next?

Nectir AI is evaluating additional models to add to the platform:

  • Gemini: With advanced multimodal capabilities, ideal for engineering, architecture, and visual arts
  • DeepSeek: Known for technical accuracy and reasoning, strong in computer science, mathematics, and data analytics

The AI model you select will affect how your Assistant processes information and generates responses. Both models are excellent for educationalapplications, with some subtle differences in response style and strengths. Testing both models with your specific content can help determine which works best for your educational needs.

Model Literacy and Future-Proofing

Introducing multiple AI models helps build AI literacy skills. By engaging with different large language models, students learn how varied models yield diverse results, preparing them for an AI-driven workforce. You may want to encourage students to:

  • Compare model outputs for the same question
  • Analyze different response styles and approaches
  • Understand which model performs better for specific types of tasks

Next Steps