MyNeuralTrainer Lab

Enhanced Metadata

Improve topic tags, cognitive mode, and tone analysis

Gemini analyzes conversations to extract more accurate and detailed metadata, improving the quality of your training data and enabling better model performance.

Cognitive Analysis

Advanced psychological profiling

Perform deep cognitive analysis to understand psychological patterns, communication styles, and reasoning approaches in your conversations.

Alternative Responses

Generate response variations for training diversity

Create multiple alternative responses for each conversation, increasing the diversity of your training data and improving your model's ability to generate varied outputs.

Gemini Pre-processor Test

Test Gemini's pre-processing capabilities on a sample conversation before applying to your dataset

Sample Conversation Unit (JSON)

{
  "id": "sample-123",
  "thread_id": "thread-456",
  "messages": [
    {
      "role": "user",
      "content": "Can you explain how neural networks learn through backpropagation?"
    },
    {
      "role": "assistant",
      "content": "Neural networks learn through backpropagation by calculating the gradient of the loss function with respect to the weights. This process involves:\n\n1. Forward pass: Input data passes through the network to generate predictions\n2. Error calculation: The difference between predictions and actual values is measured\n3. Backward pass: The error is propagated backward through the network\n4. Weight updates: Network parameters are adjusted to minimize the error\n\nThis process is repeated many times across many examples, gradually improving the network's performance."
    }
  ],
  "meta": {
    "timestamp": "2025-05-20T20:57:55.737Z",
    "cognitive_mode": "teacher",
    "tone": {
      "base": "informative",
      "variant": "educational"
    },
    "first_principle_applied": "clarity_through_contrast",
    "structure": {
      "type": "sequential",
      "response_method": "step_by_step"
    },
    "alignment_score": 0.85,
    "topic_tags": ["machine learning", "neural networks"],
    "category": "technical",
    "evolution_phase": "2024_integration"
  }
}

Paste a sample conversation unit in JSON format to test Gemini's pre-processing capabilities

Training Data Generation

Generate enhanced training datasets with Gemini

Use Gemini to pre-process your entire conversation dataset, enhancing metadata, generating alternatives, and performing cognitive analysis at scale. The enhanced data can be exported as JSONL files for model training.

Enhanced metadata extraction

Deep cognitive analysis

Alternative response generation

Truth vector analysis

Data Quality Analysis

Analyze and improve training data quality

Gemini analyzes your training data to identify strengths, gaps, and areas for improvement. Get detailed recommendations to enhance your dataset and improve model performance.

Quality score calculation

Dataset strengths identification

Specific improvement recommendations