Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn to build compound AI systems using Small Language Models (SLMs) and mini-agents to achieve high accuracy in enterprise applications through this 33-minute conference talk. Discover breakthrough techniques including memory RAG, an embedding algorithm that reduces hallucinations by generating contextual embeddings at embed-time to improve indexing and retrieval. Explore memory tuning, a fine-tuning algorithm that leverages a Mixture of Memory Experts (MoME) to specialize models with proprietary data and minimize hallucinations. Examine real-world implementations across text-to-SQL, factual reasoning, function calling, and code analysis applications spanning multiple industries. Master the fundamentals of creating highly accurate mini-agents that can be composed into larger, more sophisticated AI systems, addressing the challenge of steering non-deterministic LLMs toward consistent, high-accuracy performance in production environments.
