Completed
Visualizing Agent Execution Graphs
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Build a Language-Learning Agent with OpenAI, LangGraph, Ollama and MCP
Automatically move to the next video in the Classroom when playback concludes
- 1 - Course Intro: What We’ll Build, AI agent tech stack
- 2 - What You’ll Learn: Building an AI Language Learning Agent
- 3 – Who This AI Agent Tutorial Is For Python Prerequisites
- 4 – Instructor Introduction: NLP & Data Science Background
- 5 – Why Use PyCharm for AI Agents & Data Science
- 6 – Installing PyCharm and AI Assistant
- 7 – Creating a Python Project with Virtual Environments
- 8 – Choosing a Multilingual Vocabulary Dataset
- 9 – Best NLP Datasets: Kaggle & UCI Repositories
- 10 – Cloning and Organizing NLP Datasets in PyCharm
- 11 – Installing NLP Libraries: pandas, SpaCy, wordfreq
- 12 – Installing LangChain, LangGraph & MCP Libraries
- 13 – Exploring NLP Data with Jupyter Notebooks
- 14 – Analyzing Vocabulary Size Across Languages
- 15 – Visualizing Word Counts with Pandas Charts
- 16 – Identifying Data Problems in Multilingual Word Lists
- 17 – Introduction to SpaCy for Natural Language Processing
- 18 – Inspecting and Debugging Raw Vocabulary Data
- 19 – Removing Noise: Basic Text Cleaning Techniques
- 20 – Lemmatizing Words with SpaCy Models
- 21 – Using Zipf’s Law Overview to Filter Rare Words
- 22 – Word Frequency Analysis with wordfreq and SpaCy
- 23 - Understand Word Frequencies with wordfreq
- 24 – Building a Complete NLP Cleaning Pipeline
- 25 – Validating Results with a Spanish Dataset
- 26 – Comparing Raw vs Cleaned NLP Data
- 27 – From Clean Data to an AI Agent
- 28 – What Is an AI Agent? Core Concepts
- 29 – Thought-Action-Observation Loop Explained
- 30 – Types of AI Agents
- 31 – How Large Language Models Understand Language
- 32 – Word Embeddings & Word2Vec Explained
- 33 – Why Word Embeddings Fail Without Context
- 34 – Transformers & Self-Attention Explained
- 35 – GPT Models and Decoder-Only Architectures
- 36 – Why Reasoning Models Power AI Agents
- 37 – How Reasoning Models Are Trained Chain-of-Thought
- 38 – When Not to Use Reasoning Models
- 39 How to Build a ReAct Agent with LangGraph
- 40 Agent State, Memory & Tools Explained
- 41 Choosing Between GPT-4 and Open-Source Models
- 42 How to Manage OpenAI API Keys Securely
- 43 How to Build Custom Tools for LangGraph Agents
- 44 Auto-Generating Tool Docstrings with AI
- 45 Improving Agent Reliability with System Prompts
- 46 Building and Connecting a LangGraph Agent Graph
- 47 Running an AI Agent End-to-End
- 48 How to Debug AI Agents in PyCharm
- 49 Visualizing Agent Execution Graphs
- 50 How to Run AI Agents Locally with Ollama
- 51 Choosing the Best Open-Source Reasoning Model
- 52 Installing and Managing Ollama Models
- 53 GPT-4 vs Ollama: Model Comparison for Agents
- 54 Switching LangGraph Agents from OpenAI to Ollama
- 55 Testing a Fully Local AI Agent
- 56 Adding Difficulty-Aware Vocabulary Tools
- 57 Handling Ambiguous User Requests in AI Agents
- 58 Testing AI Agents with Natural Language Prompts
- 59 How to Translate Words Using an LLM Tool
- 60 Building a Translation Tool with Ollama
- 61 Parsing Structured Output from LLMs
- 62 Multi-Step Tool Use in ReAct Agents
- 63 Handling Errors and Non-Determinism in AI Agents
- 64 What Is MCP Model Context Protocol?
- 65 Connecting AI Agents to External Tools with MCP
