Autoresearch
Iterative text optimization via LLM eval loop
Provider
Anthropic
OpenAI
API Key
Model
Eval Mode
Score
Compare
Iterations
Text to optimize
Evaluation criteria
Start Optimization
▶
Past Evals
Select a past eval...
Iter
Change
Score
Result
Reasoning
▶
Past Experiment Learnings
Experiment Directions
Analyzing text and generating experiment directions
Start with Selected
Regenerate Plan
Cancel
0 / 0
Stop
Current Best
Iteration History
Optimization Complete
Copy Result