Tradeshow
At Weights & Biases, we’re passionate about powering real-world MLOps—not just the theory. That’s why we’re attending the 6th Annual MLOps World | GenAI Summit, October 8–9, 2025, in Austin, Texas. This premier event unites practitioners across 16 tracks and 75 sessions focused on moving AI and agentic systems from concept to production.
Weights & Biases helps teams accelerate ML workflows, simplify production pipelines, and boost transparency. We’re excited to show how our tools unlock efficiency, accountability, and speed. Join us in Austin to connect where the most advanced AI practices are unfolding.
60 minute hands-on virtual workshop: Architecting and orchestrating AI agents
In this session, Anish Shah, one of our brilliant AI engineers will explore how to make LLMs solve real-world business problems with a focus on orchestration, agent frameworks, and building effective AI agents. Attendees will gain insights into the latest agentic AI architectures, engage in hands-on sessions to construct generative AI applications, and learn techniques to enhance agent performance. We’ll cover key design principles like reflection, tool use, planning, and multi-agent collaboration, along with best practices for orchestration and evaluation. This developer-oriented track is ideal for engineers, developers, and technical leaders focused on applying language models in production systems.
30 minute live in person talk: Building and evaluating agents
In this session, Anish Shah, one of our AI engineers, will explore how large language models evolve from single-prompt tools into agentic systems capable of solving real-world business problems. We’ll cover the design principles behind agents — reflection, tool use, planning, and collaboration — and show how these map to modern architectures. The talk then focuses on the challenge of evaluation, highlighting methods like automated judges, process-level metrics, and continuous monitoring to ensure reliability, efficiency, and user trust. Attendees will leave with a clear understanding of how to structure AI agents and how to systematically measure and improve their performance.
