Product newsletter: Updates and new features for August 2025

Build smarter RAG systems with Redis + W&B Inference

Run LLM evaluations right in the W&B Weave UI

Evaluating the new Gemini 2.5 Pro Experimental model

Quantization-Aware Training (QAT): A step-by-step guide with PyTorch

Getting Started with MCP using OpenAI Agents

Getting started with the Gemini 2.5 Pro reasoning model API

Agentic RAG: Enhancing retrieval-augmented generation with AI agents

The Model Context Protocol (MCP): A guide for AI integration

Enhancing AI safety, quality, and efficiency: The latest in the Weights & Biases and NVIDIA collaboration

LLMs are machine learning classifiers

Going from demo to production with Google Cloud's Vertex AI Agent Builder

Evaluating Claude 3.7 Sonnet: Performance, reasoning, and cost optimization

W&B being acquired by CoreWeave

Building better evaluations with high-quality data

Fine-tuning Azure OpenAI models with Weights & Biases

Autonomous AI Agents: Capabilities, challenges, and future trends

Tutorial: Building AI agents with CrewAI

Human annotations: Why they matter—and how to get them right

Introducing Weave Guardrails

Training GPT-4o to reason: Fine-tuning vs budget forcing

AI guardrails: Robustness scorers

AI guardrails: Relevance scorers