Roadmap

Clickable links in observability traces to navigate to the application, variant, version, and environment used in each trace. Jump directly to the configuration that generated a specific trace.

Filter traces by date range in the metrics dashboard. View metrics for the last 6 hours, 24 hours, 7 days, or 30 days.

Track test set changes with versioning. Every edit creates a new version. Evaluations link to specific versions for reliable comparisons. Plus a rebuilt UI that scales to 100K+ rows with inline editing for chat messages and JSON.

Track multi-turn conversations with session grouping. All traces with the same session ID are automatically grouped together, showing complete conversation flows with cost, latency, and token metrics per session.

Attach PDF documents to chat messages in the playground. Upload files, provide URLs, or use file IDs from provider APIs. Works with OpenAI, Gemini, and Claude models. PDFs are supported in evaluations and observability traces.

Use provider built-in tools like web search, code execution, and file search directly in the Playground. Supported providers include OpenAI, Anthropic, and Gemini. Tools are saved with prompts and automatically used via the LLM gateway.

Create projects within organizations to divide work between different AI products. Each project scopes its prompts, traces, and evaluations independently.

We are making it easy to use and navigate in the playground with large testsets.

Create folders and subfolders to organize prompts in the playground. Move prompts between folders and search within specific folders to structure prompt libraries.

Create reusable prompt snippets that can be referenced across multiple prompts. Reference specific versions or always use the latest version to maintain consistency across prompt variants.

Analyze prompts and suggest improvements based on best practices. Identify issues, propose refined versions, and allow users to accept, modify, or reject suggestions.

Add a button in observability to open any chat span directly in the playground. Creates a stateless playground session pre-filled with the exact prompt, configuration, and inputs for immediate iteration.

We are adding the ability to cache prompts in the SDK.

We are adding the ability to tag traces, testsets, evaluations and prompts. This is useful for organizing and filtering your data.