Week 8 - AI Agents & Agentic AI on AI Platform Engineering Handbook

Agent Frameworks

Mon, 01 Jan 0001 00:00:00 +0000

1. LangChain

LangChain is one of the earliest and most widely known frameworks in this whole space, and it’s often the first name beginners encounter when they start learning about building with language models. At its core, LangChain provides a large collection of standardized building blocks — a consistent way to connect to many different language models, a consistent way to define and use tools, a consistent way to work with document loading and retrieval (which connects back to the RAG concepts we covered earlier), and pre-built patterns for common agent loops.

AI Agent Fundamentals

Mon, 01 Jan 0001 00:00:00 +0000

1. What is an AI Agent

At its core, an AI agent is an AI system that can autonomously take actions in order to accomplish a goal, rather than just generating a single response to a single question. The word “autonomously” is doing a lot of work here — it means the system itself is making decisions about what to do next, rather than a human explicitly telling it every single step along the way.

Agent Patterns

Mon, 01 Jan 0001 00:00:00 +0000

1. ReAct Pattern

ReAct is one of the most foundational and widely used patterns in the entire agent world, and its name is a combination of two words: “Reasoning” and “Acting.” The core idea is refreshingly simple once you see it: instead of an agent either purely thinking through a problem in its head with no real-world actions, or purely taking actions with no real thinking behind them, ReAct has the agent alternate between the two, over and over, in a tight back-and-forth loop.