Traces

Log everything for production monitoring and debugging

Weave automatically logs all inputs, outputs, code, and metadata in your application at a granular level, organizing the data so you can easily visualize traces of your LLM calls. Using these traces, you can debug issues during development and monitor your AI applications when they are deployed in production.

Trace trees

Weave organizes logs from various levels of the call stack into a trace tree, which you can use to quickly detect, analyze, and solve issues. Metrics such as latency and cost are automatically aggregated at every level of the tree, making it easy to pinpoint root causes of problems.

Production monitoring

Monitor live traces from your application in production to identify edge cases missed during evaluation and testing. Continuously improve your application’s quality and performance. Use online evals (preview) to score live, incoming traces for monitoring without impacting the production environment.

Sign up for online evals preview

Multimodality

Weave logs text, datasets, code, images, and audio with support for video and other modalities coming soon.

Built for long text

Weave is built from the ground up for LLM applications. It makes it easy to visualize and examine large strings like documents and code in traces. When you click on a cell, a popout launches where you can change the display format—you can choose text, markdown, or code.

Integrated chat view

When analyzing LLM responses, you can use the chat view to visualize user requests, system prompts, and LLM outputs for a given conversation thread.

Capture user feedback

To thoroughly test AI applications, you need real-world end-user feedback. When you incorporate a feedback mechanism into your application, Weave logs this user feedback as well. This helps you combine calculated scores with user input for a more holistic evaluation of your application’s performance.

Get started with tracing

The Weights & Biases platform helps you streamline your workflow from end to end

Models

Experiments

Track and visualize your ML experiments

Sweeps

Optimize your hyperparameters

Registry

Publish and share your ML models and datasets

Automations

Trigger workflows automatically

Weave

Traces

Explore and debug LLMS

Evaluations

Rigorous evaluations of GenAI applications

Core

Artifacts

Version and manage your ML pipelines

Tables

Visualize and explore your ML data

Reports

Document and share your ML insights

SDK

Log ML experiments and artifacts at scale

The Weights & Biases platform helps you streamline your workflow from end to end

Models

Experiments

Track and visualize your ML experiments

Sweeps

Optimize your hyperparameters

Registry

Publish and share your ML models and datasets

Automations

Trigger workflows automatically

Weave

Traces

Explore and
debug LLMs

Evaluations

Rigorous evaluations of GenAI applications

Core

Artifacts

Version and manage your ML pipelines

Tables

Visualize and explore your ML data

Reports

Document and share your ML insights

SDK

Log ML experiments and artifacts at scale