Completed
Evaluating Performance – Use “Experiment” for traces, “Scores” for custom evals, and “Evaluations” for metrics like correctness and relevance.
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
How to Improve Quality of Multi-Agent Systems with Agent Bricks
Automatically move to the next video in the Classroom when playback concludes
- 1 Agent Bricks Overview – Build, evaluate, and deploy multi-agent systems on Databricks with natural language.
- 2 Architecture: Vibe-Coding Stack – Overview of the Novel Ideas multi-agent system:
- 3 AI Genie Inventory Space – Uses real-time inventory and sales data for bookstore assistance.
- 4 Knowledge Assistant Bookstock Bot – RAG chatbot for personalized book recommendations.
- 5 Multi-Agent Supervisor Bookworm – Orchestrates Bookstock Bot, Inventory Space, and Tavly MCP for broader queries.
- 6 Improving Quality – Use “Improve Quality” to label sessions, add expectations, and merge expert feedback.
- 7 Wrap-Up & Next Steps
- 8 Using the MCP Server – Routes general questions to Tavly MCP when not in references.
- 9 Evaluating Performance – Use “Experiment” for traces, “Scores” for custom evals, and “Evaluations” for metrics like correctness and relevance.
- 10 Conclusion – Build and evaluate a multi-agent system in minutes with natural language on Databricks.
