The Tenth annual Nordic Data Science and Machine Learning Summit brings Data Science, Data Engineering, Machine Learning and Artificial Intelligence professionals in the Nordics under one roof for one day of inspiring and insightful presentations, panels, networking sessions.
Date: 23 October
Time: 11:35-12:05
Title: From protocol to production: Building Agentic workflows with MCP + W&B Weave
During this session, we’ll introduce Model Context Protocol (MCP), the open standard for connecting agents to tools and data and show how W&B Weave adds end-to-end observability in just a few lines of code. We’ll go over an agentic workflow, then use Weave’s trace views to debug real issues (duplicate tool calls, failures, latency spikes) and see inputs/outputs, tokens, and cost in context. We’ll close by sharing invaluable best practices for using W&B Weave in both development and production environments. These include constructing meaningful trace trees, tagging traces with structured metadata, managing PII, and more to ensure your AI applications are robust, scalable, and observable.
