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

Adding observability and tracing to your Bedrock AgentCore Agents

Tutorial: Running inference with Kimi K2 using W&B Inference

Defending against MCP prompt injection attacks

GPT-5 Python quickstart using the OpenAI API

Product newsletter: Updates and new features for July 2025

OpenAI GPT OSS models on W&B Inference

Tutorial: Fine-tuning OpenAI GPT-OSS

Rubric evaluation: A comprehensive framework for generative AI assessment

Amazon Bedrock AgentCore observability guide

What is RLHF? Reinforcement learning from human feedback for AI alignment

Run Qwen3 Coder on W&B Inference

Getting started with the Agent Reinforcement Trainer (ART)

Introducing semantic based coloring for W&B Models

Evaluating Google ADK Agents with W&B Weave for reliable insurance workflows

Run Kimi K2, the latest open-source SOTA model, on W&B Inference

Tutorial: Kimi K2 for code generation with observability

The Google GenAI SDK: A guide with a Python tutorial

Tracing your CrewAI application

Google Agent Development Kit (ADK): A hands-on tutorial

Debugging CrewAI multi-agent applications