Product newsletter: Updates and new features for August 2025

Run LLM evaluations right in the W&B Weave UI

Debug RL fine-tuning runs with W&B Weave Traces

Tracking and optimizing agentic workflows using W&B Weave and NVIDIA NeMo Agent Toolkit

The Microsoft Agent Framework

Tutorial: Run inference with Qwen3-Coder using W&B Inference

Tutorial: Run inference with Qwen3 235B A22B-2507 Instruct using W&B Inference

A Guide to W&B Inference powered by CoreWeave

Tutorial: Running inference with OpenAI's GPT OSS 20B using W&B Inference

Tutorial: Running inference with Llama 3.1 8B using W&B Inference

Tutorial: Running inference with Qwen3 235B A22B Thinking-2507 using W&B Inference

Tutorial: Running inference with Zhipu AI's GLM-4.5 using W&B Inference

Tutorial: Running inference with DeepSeek R1-0528 using W&B Inference

Build smarter RAG systems with Redis + W&B Inference

From demos to dependable agents: A practical path

Tutorial: Running inference with Llama 3.3 70B using W&B Inference

How to evaluate the "true" context length of your LLM using RULER

Master sentiment analysis in Python

Tutorial: Running inference with Llama 4 Scout using W&B Inference

Weights & Biases supports BT Group with safe and effective AI deployment

How to build research agents with W&B Weave and Tavily

How to migrate from Humanloop to W&B Weave

Humanloop is Sunsetting. Migrate to Weights & Biases as an alternative

Tutorials: GPT-5 evaluation across multiple tasks