Andrew Ng's keynote speech on How AI Agentic Workflow Could Drive More AI Progress
Today, many developers still use LLMs in zero-shot mode, in which you prompt a model to generate the final output token by token without revising its work. This is akin to asking someone to compose an essay from start to finish, typing straight through with no backspacing allowed, and expecting a high-quality result. In comparison, agentic workflows can plan an outline, write a draft, criticize and revise drafts, and call on tools like web search to gather information, using a more iterative process to deliver a superior result. In this presentation, Dr. Andrew Ng, founder and CEO of Landing AI, will describe major agentic workflow design patterns — such as reflection, tool use, planning and multi-agent collaboration — and why they're a powerful tool for developing LLM-based applications. He will also describe Landing AI's work on building a computer vision agent.