Agenta-AI agenta Discussions
Pinned Discussions
Discussions
-
You must be logged in to vote -
You must be logged in to vote -
You must be logged in to vote -
You must be logged in to vote -
You must be logged in to vote -
You must be logged in to vote -
You must be logged in to vote -
You must be logged in to vote Add JSONPath Support to JSON Field Match Evaluator
enhancementNew feature or request Feature RequestNew feature or request -
You must be logged in to vote Improving Test Set View to Improve Editing Test Cases
Evaluation Feature RequestNew feature or request Planned -
You must be logged in to vote Test Set Versioning
Evaluation Feature RequestNew feature or request Planned -
You must be logged in to vote Add repetition setting to playground for consistency testing
Feature RequestNew feature or request Playground -
You must be logged in to vote Decouple Evaluations from LLM Runs (Post-hoc Evaluation)
Evaluation Feature RequestNew feature or request -
You must be logged in to vote Add Date Range Filter to Metrics Dashboard
Observability Feature RequestNew feature or request -
You must be logged in to vote [Playground] Show model cost (and intelligence?) in the model selector
Feature RequestNew feature or request Playground -
You must be logged in to vote -
You must be logged in to vote Folders for Prompt Organization
Feature RequestNew feature or request Playground -
You must be logged in to vote Chat Session View for Observability
Observability Feature RequestNew feature or request -
You must be logged in to vote -
You must be logged in to vote PDF Support in the Playground
Feature RequestNew feature or request Playground In Progress -
You must be logged in to vote -
You must be logged in to vote Projects and Workspaces
Feature RequestNew feature or request -
You must be logged in to vote Jinja2 Template Support in the Playground
Feature RequestNew feature or request Playground -
You must be logged in to vote -
You must be logged in to vote A simple a way to spin off evaluations for one prompt with multiple models
Evaluation Feature RequestNew feature or request -
You must be logged in to vote
