Best Practices and Lessons Learned in Sourcing
summary
Claims that agentic AI turns ideas into products 1–2 months instead of 6–12, using a master orchestrator and sub-agents that fetch trends, call suppliers, negotiate and finalize orders; cites Zara 30,000 vs Shein 2,000,000 products (≈70×). Describes the Model Context Protocol (MCP) for tool selection, recommends separate toolboxes, memory for past requests, and guardrails. Summarizes nine lessons including the impossible trinity and prefers simple, specialized sub-agents over one big agent.
AI-written summary · about
chapters (4)
- 0:00Introduction to agentic AI
- 3:16Why agentic AI for sourcing
- 7:48Lessons learned in implementation
- 14:30Q&A and closing
related talks
50mAgile Intelligence: Co-Engineering the Future, Not Just Automating It
43mAI Procurement Agents | The Future of Intelligent Procurement
24mPut On Your AI-Colored Glasses
26mBuilding Agentic Workflows: Patterns for Orchestrating Intelligent Systems.
57mWhen AI Agent Teams Work (And When They Just Create More Work)
35mShipping with Confidence in the Age of AI
43mFrom Pilots to Practice: Leading the agentic AI transformation
23mFrom Models to Moments: Why Most AI Products Fail in Week One