<p>Building production AI systems is hard — especially when you're pioneering entirely new categories. In this episode, Yuval speaks with Guy Becker, Group Product Manager at AI21, to trace the evolution from task-specific models to Agent planning and orchestration systems. Guy shares hard-won lessons from building some of the first RAG-as-a-service offerings when there were literally zero handbooks to follow.</p><p><strong>Key Topics:</strong></p><ol><li><strong>Task-specific models vs. general LLMs</strong>: Why focused, smaller models with pre and post-processing beat general purpose LLMs for business use cases.</li><li><strong>Building RAG before it was cool</strong>: Creating one of the first RAG-as-a-service platforms in early 2023 without any established patterns.</li><li><strong>The one-size-fits-all problem</strong>: Why chunking strategies, embedding models, and retrieval parameters need customization per use case.</li><li><strong>From SaaS to on-prem</strong>: Scaling deployment models for enterprise customers with sensitive data.</li><li><strong>When RAG breaks down</strong>: Multi-hop queries, metadata filtering, and why semantic search isn't always enough.</li><li><strong>Multi-agent orchestration</strong>: How AI21 Maestro uses automated planning to break complex queries into parallelizable subtasks.</li><li><strong>Production lessons</strong>: Evaluation strategies, quality guarantees, and building explainable AI systems for enterprise..</li></ol>