Yuval speaks with Guy Becker from AI21 about the evolution from task-specific models to Agent planning and orchestration systems, sharing lessons from building early RAG-as-a-service offerings and AI21 Maestro.
Key Topics:
- Task-specific models vs. general LLMs: Why focused, smaller models with pre and post-processing beat general purpose LLMs for business use cases.
- Building RAG before it was cool: Creating one of the first RAG-as-a-service platforms in early 2023 without any established patterns.
- The one-size-fits-all problem: Why chunking strategies, embedding models, and retrieval parameters need customization per use case.
- From SaaS to on-prem: Scaling deployment models for enterprise customers with sensitive data.
- When RAG breaks down: Multi-hop queries, metadata filtering, and why semantic search isn’t always enough.
- Multi-agent orchestration: How AI21 Maestro uses automated planning to break complex queries into parallelizable subtasks.
- Production lessons: Evaluation strategies, quality guarantees, and building explainable AI systems for enterprise.
Speakers
Guy Becker
Director of Product @ AI21
Yuval Belfer
Sr. Developer Advocate @ AI21
