Langtail Roadmap, Feedback and Changelog

Enable integration and support for Anthropic models (specifically Claude) within the application.

Incorporate human evaluation as part of the testing process to ensure accurate and reliable results.

Addidionaly, it would be useful to duplicate prompt to a new project directly

Enable drag and drop functionality to easily rearrange and organize messages within the Playground interface.

There are many APIs available that are compatible with openai standard. Like fireworks.ai , togehter, claude etc. It would be great if we can add them as providers ourselves by changing the URLs

Add the capability to mock responses from OpenAI functions, allowing developers to simulate and test different scenarios without making actual API calls.

Enable the sharing of assertions between prompts and projects, allowing for seamless reuse and consistency in testing and validation.

Enhance the testing functionality to display the cost per test run, providing transparency and cost visibility to users.

Implement the functionality to invite team members by sending email invitations.

Develop a Python client library for Langtail, enabling seamless integration and usage of Langtail functionalities in Python applications.