Agentic AI in Python Crash Course

Live Training + Recordings

Author
Trainer: Vishwanath Narayan

What you'll learn :-

This 20 hour crash course teaches how to build agentic AI systems in Python using OpenAI (GPT-4/4o), LangChain, and related tooling. The course is hands-on with notebooks for each module and a multi-agent chatroom capstone implemented both as a console app and a Streamlit web UI.

Training Content


Module 1: Introduction to Agentic AI (2 hours)
  • Concepts, environment setup, first OpenAI API call
  • Hands-on tasks:
    See corresponding Jupyter notebook for step-by-step code and examples.

Module 2: LLM Fundamentals & Prompt Engineering (2 hours)

  • Prompts, templates, few-shot, structured outputs.
  • Hands-on tasks:
    See corresponding Jupyter notebook for step-by-step code and examples.

Module 3: Building Simple Agents (2 hours)

  • Agent loops, LangChain basics
  • Hands-on tasks:
    See corresponding Jupyter notebook for step-by-step code and examples.

Module 4: Tools, Memory & Reasoning (3 hours)

  • Tools, memory stores, ReAct
  • Hands-on tasks:
    See corresponding Jupyter notebook for step-by-step code and examples.

Module 5: Multi-Agent Systems (2 hours)

  • Agent collaboration patterns
  • Hands-on tasks:
    See corresponding Jupyter notebook for step-by-step code and examples.

Module 6: Integrating APIs & External Tools (3 hours)

  • Connect to APIs, file handling
  • Hands-on tasks:
    See corresponding Jupyter notebook for step-by-step code and examples.

Module 7: Custom Agent Workflows & Planning (3 hours)

  • Task decomposition, vector stores
  • Hands-on tasks:
    See corresponding Jupyter notebook for step-by-step code and examples.

Module 8: Capstone — Multi-Agent Chatroom (3 hours)

  • Build multi-agent chatroom (console + Streamlit)
  • Hands-on tasks:
    See corresponding Jupyter notebook for step-by-step code and examples.

Capstone: Multi-Agent Chatroom

  • Two implementations are included:
  1. Console-based: a lightweight terminal app that runs locally.
  2. Streamlit-based: provides a web UI suitable for demos and classrooms.

Both use OpenAI as the LLM backend and LangChain patterns for agents, memory, and tool invocation.

Setup & Requirements

  • Run:
    pip install -r requirements.txt

Set your OpenAI API key in environment variable OPENAI_API_KEY or use a .env file.

Example: export OPENAI_API_KEY='sk-...'

Files in ZIP package

  • 01_intro_agentic_ai.ipynb
  • 02_prompt_engineering.ipynb
  • 03_simple_agents.ipynb
  • 04_tools_memory_reasoning.ipynb
  • 05_multi_agent_systems.ipynb
  • 06_api_integration.ipynb
  • 07_custom_agent_workflows.ipynb
  • 08_capstone_multiagent_chatroom_console.ipynb
  • 08_capstone_multiagent_chatroom_streamlit.ipynb
  • README.md
  • requirements.txt

10 Lessons

03 Hours

World-class training and development programs developed by top teachers

Whats Included

  • World-class training teacher
  • Bench has zero learning curve
  • We handle the rest.