Automated Scientist
AI-Powered Experimentation

Accelerate scientific discovery with AI agents that autonomously design, implement, and evaluate experiments – all while you watch in real-time.

Current Demo: Self-Modeling Transformer for MNIST

Watch as our AI agents design, implement, and evaluate a transformer model that can classify MNIST digits while simultaneously modeling its own attention mechanisms.

TransformersSelf-ModelingPyTorchImage Classification

AI Agent Workflow

Our AI workflow orchestrates four specialized agents to automate the scientific experiment process for transformer model development

1

Design Agent

Analyzes experiment requirements and creates detailed specifications based on goal understanding, producing an implementation blueprint for our self-modeling transformer.

2

Implementation Agent

Converts design specifications into executable PyTorch code, implementing transformer architecture with self-modeling capability and establishing a complete experiment pipeline.

3

Validation Agent

Verifies code correctness, checking data loading, model architecture, optimizer configuration, and ensuring technical requirements like GPU compatibility are met.

4

Evaluation Agent

Runs the experiment, monitors training metrics, and produces visualizations of model performance including accuracy comparisons and loss curves.

View Experiment Demo

Watch a replay of AI agents designing, implementing, validating, and evaluating a transformer model with self-modeling capabilities.

This is a pre-recorded demonstration of the Automated Scientist workflow
Demo Experiment Prompt:
Pre-configured

Implement a transformer-based model with self-modeling for MNIST classification

1
Design Agent
2
Implementation Agent
3
Validation Agent
4
Evaluation Agent
automated-scientist-terminaldemo mode

Press "Play Demo Replay" to start