lets-optimize

What problem does it solve?

This Skill automates the process of running metric-driven iterative optimization loops, enabling users to define a measurable goal, conduct parallel experiments, measure results, and converge on the best solution.

Core Features & Use Cases

• Metric-Driven Optimization: Define a measurable goal and run parallel experiments to optimize against it.
• Experiment Management: Track experiment results, manage experiment states, and persist data for durability.
• Hypothesis Generation: Generate hypotheses based on current learnings and user input.
• Use Case: Imagine you are optimizing a machine learning model's performance. Use this Skill to define a performance metric, run various experiments with different model configurations, measure the results, and converge on the best model.

Quick Start

Use the /lets-optimize command to start an optimization loop for your model. Provide the optimization spec YAML file or describe your optimization goal.