W&B Weave
Trace, score and debug LLM-powered apps with tools from Weights & Biases
Launched 2 days agowandb.ai
Do you work on W&B Weave?
This listing is unclaimed. Claim it for free to edit the details, add screenshots and reply to reviews.
About W&B Weave
W&B Weave is the observability and evaluation toolkit from Weights & Biases for applications built on large language models. It records each LLM call automatically, with its inputs, outputs, cost and latency. Evaluation pipelines let teams score model outputs with custom scorers, and a trace explorer shows how an agent reached its answer. It fits into the wider W&B tools for machine learning experiments. A free plan is available. AI engineers use it to test and debug LLM features before and after launch.
Reviews
From people who have used it. One review per person, checked by a human.
No reviews yet. Be the first to say something useful.
