<p><strong>Aentic workflows</strong> are processes where AI agents dynamically plan, execute, and reflect on steps to achieve a goal, differentiating them from static, predefined workflows. </p><p><br /></p><p><strong>Augmented LLMs</strong>, which serve as a <strong>base building block</strong>, are enhanced with capabilities like tool use and memory, enabling the creation of these more complex <strong>agents</strong>. This episode also distinguish between an <strong>agentic workflow</strong>, the sequence of steps, and the <strong>agentic architecture</strong>, the underlying system allowing multiple workflows to run securely and effectively at scale, highlighting the benefits and challenges of implementing such systems.</p><p><br /></p><p>Sources:</p><p>https://www.anthropic.com/engineering/building-effective-agents</p><p>https://weaviate.io/blog/what-are-agentic-workflows</p><p><br /></p>