How to build AI agents with MCP and other protocols
Join this webinar to explore how to build reliable agentic systems using protocols such as Model Context Protocol (MCP) and Agent2Agent (A2A) with Weights & Biases.
Evaluating AI agents with SambaNova and W&B Weave
Join this webinar to discover how combining SambaNova’s RDU technology with W&B Weave’s robust tracing, evaluation, and monitoring capabilities enables developers to effectively deploy enterprise-grade agents and agentic workflows.
Agent Evals with CrewAI + W&B Weave
Join this webinar to see a a clear, step-by-step process to evaluate and refine your AI agents—so you can launch with confidence and speed.
Mastering Model Customization: Fine-Tuning Azure OpenAI Service Models with Weights & Biases
Join this webinar to learn how fine-tuning can unlock new AI capabilities for your team.
Evaluating LLM-Powered Applications
In this webinar, we’ll show you how to run rigorous evals on LLM-powered applications—so you can move fast and deploy with confidence.
Building AI agents with confidence
In this on- demand webinar, we will demonstrate how W&B Weave provides the agent ops solution you need to deliver agentic AI with confidence.
Fine-tune Command R/R+ using Cohere and Weights & Biases
In this Webinar, we dive deep into how to use the integration to customize Command R and Command R+ using your own data for specific use cases.
Building production-ready RAG systems
A webinar on building production-ready RAG systems: optimization techniques for performance and scalability
Building a system of record for ML
A webinar on building a system of record for ML -Fine-tuning and moving models to production.
Optimizing CI/CD model management and evaluation workflows
Discover how Weights & Biases enhances CI/CD pipelines, facilitating the deployment of your top production models with effective model management and thorough evaluation procedures.