Teams can use our open-source SDK and playground to:

  • Develop prompts, models, pipelines with experiments

  • Monitor in production, gather custom metrics

  • Use feedback to improve prompts over time

Evaluate systems with multiple approaches

  • Annotate responses with human-in-the-loop

  • Use LLMs for auto-evaluation

  • Run evaluation functions in code

Measure, monitor, and improve your generative AI applications

Hegel AI is building a developer platform for large language model (LLM) applications.

Backed by:

Book a demo to join our private beta and learn more about our platform:

You can use PromptTools in code, notebooks, and a playground.

PromptTools is our open-source platform for building LLM applications.

  • Experiment with prompts, models, and retrieval pipelines

  • Monitor LLM systems in production, evaluate responses online

  • Improve prompts over time with evaluations and customer feedback

We support integrations with almost every LLM, vector database, and framework including:



Vector DBs



We're happy to support LLM use cases across industries and company sizes, with customers and users including:


from prompttools.experiment import OpenAIChatExperiment

messages = [
    [{"role": "user", "content": "Tell me a joke."},],
    [{"role": "user", "content": "Is 17077 a prime number?"},],

models = ["gpt-3.5-turbo", "gpt-3.5-turbo-0613"]
temperatures = [0.0]
openai_experiment = OpenAIChatExperiment(models, messages, temperature=temperatures)