Key Concepts:
- Agentic AI: AI systems capable of autonomous action and decision-making to achieve specific goals.
- Compound LLMs: A precursor term to agentic AI, referring to the combination of multiple LLMs or LLMs with other tools.
- Prompt: Input text provided to an LLM, containing instructions, context, and information.
- LLM (Large Language Model): A deep learning model trained on a massive dataset of text to generate human-like text.
- Prediction: The core function of an LLM, which involves predicting the next word in a sequence.
Understanding Agentic AI (or Compound LLMs):
The speaker introduces the concept of "agentic AI," predicting it will be a major AI buzzword in 2025. The goal is to provide education on the term and its implications for organizations. The speaker references a previous video by Nikolai on the same channel that provides an overview of agentic AI. The speaker will use a simple example to illustrate the concept. Initially, the speaker uses the term "compound LLMs" as a precursor to "agentic AI."
LLMs and Prediction:
The speaker explains the fundamental function of an LLM: predicting the next word. This prediction is based on a prompt, which can consist of multiple paragraphs of input text, instructions, and context.
AI summaries can miss context or contain errors. Check important details against the original video.





