CoolPrompt is a framework for automative prompting creation and optimization.

Practical cases

• Automatic prompt engineering for solving tasks using LLM
• (Semi-)automatic generation of markup for fine-tuning
• Formalization of response quality assessment using LLM
• Prompt tuning for agent systems

Core features

• Optimize prompts with our autoprompting optimizers: HyPE, ReflectivePrompt, DistillPrompt
• LLM-Agnostic Choice: work with your custom llm (from open-sourced to proprietary) using supported Langchain LLMs
• Generate synthetic evaluation data when no input dataset is provided
• Evaluate prompts incorporating multiple metrics for both classification and generation tasks
• Retrieve feedbacks to interpret prompt optimization results
• Automatic task detecting for scenarios without explicit user-defined task specifications

Quick install

• Install with pip:

pip install coolprompt

• Install with git:

git clone https://github.com/CTLab-ITMO/CoolPrompt.git

pip install -r requirements.txt

Quick start

Import and initialize PromptTuner using model qwen3-4b-instruct via HuggingFace

from coolprompt.assistant import PromptTuner

prompt_tuner = PromptTuner()

prompt_tuner.run('Write an essay about autumn')

print(prompt_tuner.final_prompt)

# You are an expert writer and seasonal observer tasked with composing a rich,
# well-structured, and vividly descriptive essay on the theme of autumn...

Examples

See more examples in notebooks to familiarize yourself with our framework

About project

• The framework is developed by Computer Technologies Lab (CT-Lab) of ITMO University.
• API Reference

Contributing

• We welcome and value any contributions and collaborations, so please contact us. For new code check out CONTRIBUTING.md.

Reference

For technical details and full experimental results, please check our papers.

CoolPrompt Publishing

ReflectivePrompt

@misc{zhuravlev2025reflectivepromptreflectiveevolutionautoprompting,
      title={ReflectivePrompt: Reflective evolution in autoprompting algorithms}, 
      author={Viktor N. Zhuravlev and Artur R. Khairullin and Ernest A. Dyagin and Alena N. Sitkina and Nikita I. Kulin},
      year={2025},
      eprint={2508.18870},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2508.18870}, 
}

DistillPrompt

@misc{dyagin2025automaticpromptoptimizationprompt,
      title={Automatic Prompt Optimization with Prompt Distillation}, 
      author={Ernest A. Dyagin and Nikita I. Kulin and Artur R. Khairullin and Viktor N. Zhuravlev and Alena N. Sitkina},
      year={2025},
      eprint={2508.18992},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2508.18992}, 
}