Self-improving agents are the next frontier in AI, but building them requires robust tooling for debugging, evaluating, and iterating on models and agent harnesses. We’ve rebuilt W&B Weave from the ground up to help you and your coding agents accelerate agent development.
What to expect
Hear about the latest trends, challenges, and tools for building self-improving agents.
Learn about the paradigm shift from offline evaluations to continual learning in production and the latest tools teams need to build self-improving agents.
Explore how coding agents can automate recursive iteration loops.
Share your experiences and perspectives over dinner.
Network with experts working at the frontiers of agentic AI.
Who should attend
AI & ML leaders looking to enhance AI workflows
Researchers, data scientists, and developers interested in state-of-the-art evaluation methods
AI team leads aiming to scale AI adoption in their organizations