Weights & Biases has continued to evolve, adding more LLM-focused features since it was last featured in the Radar. They are expanding Traces and introducing Weave, a full-fledged platform that goes beyond tracking LLM-based agentic systems. Weave enables you to create system evaluations, define custom metrics, use LLMs as judges for tasks like summarization and save data sets that capture different behaviors for analysis. This helps optimize LLM components and track performance at both local and global levels. The platform also facilitates iterative development and effective debugging of agentic systems, where errors can be difficult to detect. Additionally, it enables the collection of valuable human feedback, which can later be used for fine-tuning models.
Weights & Biases is a machine learning (ML) platform for building models faster through experiment tracking, data set versioning, visualizing model performance and model management. It can be integrated with existing ML code to get live metrics, terminal logs and system statistics streamed to the dashboard for further analysis. Recently, Weights & Biases has expanded into LLM observability with Traces. Traces visualizes the execution flow of prompt chains as well as intermediate inputs/outputs and provides metadata around chain execution (such as tokens used and start and end time). Our teams find it useful for debugging and getting a greater understanding of the chain architecture.
Weights & Biases is a machine learning (ML) platform for building models faster through experiment tracking, data set versioning, visualizing model performance and model management. You can integrate it with existing ML code and quickly get live metrics, terminal logs and system statistics streamed to the dashboard for further analysis. Our teams have used Weights & Biases, and we like its collaborative approach to model building.
