

CoreWeave Virtual Workshop: Fine-Tune and Evaluate an AI Agent
December 8, 2026 | 11:30 AM ET / 8:30 AM PT | 90 minutes
The harvest is behind schedule, and the Guild shipment is due. In this hands-on virtual lab, you’ll work through an AI model-improvement loop in CoreWeave Forge: see a base model struggle with a desert logistics task, identify where it fails, then fine-tune a LoRA adapter and track training in Weights & Biases Models. You’ll serve the updated model on CoreWeave Inference, rerun the same shifts, and compare traces and scores to see what changed.
Along the way, you’ll learn when fine-tuning is the right tool for improving an AI agent, and when it isn’t.
What you’ll do
Run the task with CoreWeave Inference
Inspect the base model’s behavior in Agent Lens
Identify failure cases to guide the next iteration
Fine-tune a LoRA adapter and track training in Weights & Biases Models
Rerun the shifts and compare traces and scores
Who should attend
AI researchers, AI engineers, and AI practitioners who want to apply model-improvement techniques to real-world AI systems.
Prizes
Fine-tune your agent, rerun it, and climb the scoreboard. The top three finishers win prizes, and first place takes home Ray-Ban Meta glasses.
Presenter: Travis DePuy, Senior Account Solutions Architect at CoreWeave
Register here: https://utm.io/uuHId