KembaliArsip / superapp-pro / sertifikasi-ibnu
superapp-pro

sertifikasi-ibnu

283 file · 10.6 MB

Buka Sistem Informasi Buka di GitHub
Sistem informasi live — sertifikasi-ibnu.vercel.appBuka di tab baru

README

🎓 Ibnu's Learning Journey v4.0 ULTIMATE EDITION

Professional Certification Dashboard - The most comprehensive, feature-rich certification tracking platform with AI-powered capabilities.

🌐 Live Website: https://sertifikasi-ibnu.vercel.app

Version Status Size Certifications Hours Udemy

🚀 What's New in v4.0

🎓 Udemy Learning Hub

  • Immersive Udemy Course Browser at sertifikasi-ibnu.vercel.app/udemy-hub.html
  • Live progress tracking for 71+ Udemy courses
  • Category filters, search, and beautiful card layouts
  • Course detail modals with syllabus, skills, and projects
  • Direct integration with Udemy personal library

🗺️ Learning Plan: Roadmap ke Gaji 23jt+

  • Comprehensive career roadmap at sertifikasi-ibnu.vercel.app/learning-plan.html
  • AI, Cybersecurity, Management, Live Coding, Infrastructure & Cloud
  • 4-phase learning roadmap with certifications and portfolio projects
  • Interactive curriculum with progress tracking
  • Income progression projection and weekly schedule

✨ Major New Features

  1. 🎊 Confetti Animation System

    • Particle explosions on achievements
    • Configurable colors and physics
    • Non-blocking canvas rendering

  2. 🎤 Voice Search (Web Speech API)

    • Hands-free search capability
    • Natural language commands
    • "Show AI certifications", "Switch theme", etc.

  3. 📱 QR Code Generator

    • Generate shareable QR codes
    • One-click download
    • Direct link copying

  4. 📜 Certificate Generator

    • Create custom certificates
    • Real-time preview
    • PNG export with html2canvas

  5. 🕸️ Interactive Skill Network Graph

    • Animated node visualization
    • Draggable physics simulation
    • Category color coding

  6. 🍞 Advanced Toast Notifications

    • Multiple notification types
    • Action buttons support
    • Auto-dismiss with progress

  7. 🎯 Interactive Tour System

    • Step-by-step guided tour
    • Element highlighting
    • Progress tracking

  8. 🎴 3D Card Tilt Effects

    • Mouse-tracking perspective
    • Smooth CSS transitions
    • Performance optimized

📊 Dashboard Overview

Statistics

  • 15+ Professional Certifications
  • 7 Top-tier Providers (IBM, Google, Microsoft, Stanford, Harvard, Cambridge, Wharton)
  • 2000+ Learning Hours
  • 45+ Projects Built
  • $5,489 Total Investment
  • 11x Estimated ROI

Certification Categories

CategoryCountProviders
🤖 AI & Machine Learning8IBM, Stanford, Harvard, Microsoft, Udemy
🔒 Cybersecurity2Google, Cambridge
📊 Data Analytics1Google
💼 Business2Wharton
👑 Leadership2Harvard, Cambridge

🎮 Keyboard Shortcuts

ShortcutAction
FOpen global search
?Show keyboard shortcuts help
EscClose modals/search
TToggle dark/light theme
CToggle compare mode
BShow bookmarks
VActivate voice search
GOpen certificate generator
↑ / ↓Navigate certifications
EnterOpen selected certification
1-9Jump to sections
Ctrl + PPrint dashboard
Ctrl + EExport to PDF
Ctrl + SSave progress

🎯 Core Features

1. Certification Management

  • 📋 Detailed certification cards
  • 📈 Progress tracking with visual bars
  • 🔖 Bookmark favorite certifications
  • 📊 Side-by-side comparison (up to 3)
  • 🔍 Global search across all fields

2. Analytics Dashboard

  • Learning Hours by Year - Bar chart with 7-year history
  • Category Distribution - Doughnut chart breakdown
  • Provider Breakdown - Pie chart visualization
  • Investment Tracking - Total cost with ROI calculation
  • Skills Gap Analysis - Missing skills priority

3. Skills Radar

  • Technical Competencies - ML, Deep Learning, Python, Cloud, MLOps
  • Business Skills - Strategy, Marketing, Finance, Operations
  • Leadership Skills - Team Management, Communication, Decision Making
  • Combined View - All competencies overlay
  • Gap Recommendations - High/Medium/Low priority skills

4. Study Planner

  • ✅ Goal management with checkboxes
  • 📅 Progress ring visualization
  • 🔥 Learning streak tracker (365 days)
  • 📆 Upcoming events with countdowns
  • 📊 Calendar heatmap

5. Career Alignment

  • 🎯 4 Career paths analyzed
  • 📊 Skill match percentages
  • 💰 Salary range estimates
  • ⚠️ Skills gap identification
  • 🏆 Recommended path highlighting

6. Timeline Journey

  • 📅 Chronological learning history
  • 🎯 Phase indicators (Foundation → Specialization → Advanced → Mastery)
  • ✅ Achievement milestones
  • 🔄 Animated scroll reveal

7. Resources Library

  • 📝 Study notes with tags
  • 🔗 Reference materials
  • 🛠️ Tools collection
  • 🗺️ Learning roadmap
  • 🔖 Bookmarked certifications

🛠️ Technical Stack

Core Technologies

  • HTML5 - Semantic structure, accessibility
  • CSS3 - Custom properties, Grid, Flexbox, animations
  • Vanilla JavaScript - ES6+ modules, no frameworks

Libraries & APIs

  • Chart.js - Data visualizations
  • GSAP 3.12.2 - Advanced animations
  • jsPDF 2.5.1 - PDF generation
  • html2canvas 1.4.1 - Screenshot/PNG export
  • QRCode.js - QR code generation
  • Web Speech API - Voice recognition
  • Intersection Observer - Scroll animations

PWA Features

  • 📱 Installable app
  • 🔌 Offline support
  • 🔄 Background sync
  • 🔔 Push notifications (ready)
  • ⚡ Service worker caching

📱 Responsive Design

Breakpoints

  • Desktop - Full layout with 3D effects
  • Tablet (1024px) - Adjusted grids
  • Mobile (768px) - Single column, hamburger menu
  • Small (480px) - Optimized typography

Mobile Features

  • Touch-friendly interface
  • Swipe gestures support
  • Collapsible sections
  • Bottom sheet modals

🎨 Design System

Color Palette

--color-primary: #6366f1      /* Indigo */
--color-secondary: #22d3ee    /* Cyan */
--color-accent: #f59e0b       /* Amber */
--color-success: #10b981      /* Emerald */
--color-warning: #f59e0b      /* Amber */
--color-error: #ef4444        /* Red */

Typography

  • Primary - Inter (weights: 300-900)
  • Monospace - JetBrains Mono (code, shortcuts)

Shadows & Effects

  • Glass morphism cards
  • Gradient backgrounds
  • Glow effects on hover
  • Smooth transitions (150-500ms)

🔐 Accessibility

  • ♿ WCAG 2.1 AA compliant
  • ⌨️ Full keyboard navigation
  • 🔊 Screen reader support
  • 🎯 Focus visible indicators
  • 📖 Semantic HTML structure
  • 🏷️ ARIA labels throughout
  • ⚡ Reduced motion support
  • 🌓 High contrast mode ready

💾 Data Persistence

LocalStorage Keys

bookmarks      // Saved certifications
goals          // Study goals & progress
achievements   // Unlocked achievements
theme          // Dark/light preference
lastSaved      // Last backup timestamp

Backup/Restore

  • 📥 Export to JSON
  • 📤 Import from JSON
  • 🔒 Data validation
  • ⚠️ Error handling

🚀 Performance Optimizations

  • 🖼️ Lazy loading for images
  • 📦 Code splitting (implicit)
  • 🎨 CSS containment
  • 🔄 Debounced search
  • 📊 Canvas rendering for particles
  • ⚡ Passive event listeners
  • 🗜️ Minified assets ready

📊 File Structure

sertifikasi-ibnu/
├── index.html          # Main HTML (81KB)
├── styles.css          # Comprehensive styles (86KB)
├── script.js           # All functionality (86KB)
├── manifest.json       # PWA manifest (3KB)
├── sw.js              # Service worker (6KB)
├── README.md          # Documentation
└── [assets]
    └── sertifikasi-ibnu-final.png

Total Size: ~278KB (excluding images)

🎯 Usage Guide

Getting Started

  1. Open sertifikasi-ibnu.vercel.app in any modern browser
  2. Allow microphone access for voice search
  3. Install as PWA for offline use
  4. Take the tour to learn features

Daily Use

  • Track certification progress
  • Set weekly learning goals
  • Bookmark interesting courses
  • Use voice search for quick finds

Data Management

  • Regular backups recommended
  • Export before major changes
  • Share progress via QR code

🔮 Future Enhancements

  • AI-powered course recommendations
  • Integration with learning platforms API
  • Study session timer with Pomodoro
  • Social sharing & leaderboards
  • Certificate expiry reminders
  • LinkedIn profile integration
  • Mobile app (React Native)

📝 Changelog

v4.0 (2026-03-13)

  • ✨ Confetti animation system
  • 🎤 Voice search with Web Speech API
  • 📱 QR code generator
  • 📜 Certificate generator
  • 🕸️ Skill network visualization
  • 🍞 Toast notification system
  • 🎯 Interactive tour
  • 🎴 3D card effects

v3.0 (Previous)

  • PWA implementation
  • Keyboard shortcuts
  • Achievement system
  • Analytics dashboard
  • Study planner
  • Career alignment

👨‍💻 Author

Subkhan Ibnu Aji

  • 🎓 15+ Professional Certifications
  • 🤖 AI Engineer & Security Professional
  • 📧 Contact via LinkedIn
  • 🌐 Portfolio: GitHub

📄 License

MIT License - Feel free to use and modify for your own learning journey!

<p align="center"> <strong>Made with ❤️ for continuous learning</strong> </p> <p align="center"> 🎓 Never stop learning! 🚀 </p>

📚 Riwayat Pembelajaran

1. Master Class - AIGP Exam Preparation (AI Governance Professional)

Kurikulum:

Section 1: AIGP Certification & Exam Structure (2 lectures • 8m)

  • AIGP Certification & Exam Structure - Video Lecture
  • AIGP Certification & Exam Structure - Notes

Section 2: Domain 1 - Understanding the Foundations of AI Governance (20 lectures • 59m)

  • Understanding Artificial Intelligence - Video Lecture
  • Understanding Artificial Intelligence - Notes
  • Understanding Artificial Intelligence - Practice Questions
  • Machine Learning - Video Lecture
  • Machine Learning - Notes
  • Machine Learning - Practice Questions
  • Narrow AI vis-à-vis General AI - Video Lecture
  • Narrow AI vis-à-vis General AI - Notes
  • Narrow AI vis-à-vis General AI - Practice Tests
  • AI Risks - Video Lecture
  • AI Risks - Notes
  • AI Risks - Practice Questions
  • AI Governance - Video Lecture
  • AI Governance - Notes
  • AI Governance - Practice Questions
  • AI Governance - Roles & Responsibilities - Video Lecture
  • AI Governance - Roles & Responsibilities - Notes
  • AI Governance - Roles & Responsibilities - Practice Questions
  • AI Governance Models - Video Lecture
  • AI Governance Models - Notes
  • AI Governance Models - Practice Questions
  • AI Policies & Procedures - Video Lecture
  • AI Policies & Procedures - Notes
  • AI Policies & Procedures - Practice Questions
  • Steps for AI System Planning - Video Lecture
  • Steps for AI System Planning - Notes
  • Steps for AI System Planning - Practice Questions
  • Principles of Responsible AI - Video Lecture
  • Principles of Responsible AI - Notes
  • Principles of Responsible AI - Practice Questions

Section 3: Domain 2 - Understanding How Laws, Standards and Frameworks Apply to AI (37 lectures • 1h 21m)

  • Privacy Laws and AI - Video Lecture
  • Privacy Laws and AI - Notes
  • Privacy Laws and AI - Practice Questions
  • Differential Privacy - Video Lecture
  • Differential Privacy - Notes
  • Differential Privacy - Practice Questions
  • Federated Privacy - Notes
  • Federated Privacy - Practice Questions
  • Intellectual Property Laws and AI - Video Lecture
  • Intellectual Property Laws and AI - Notes
  • Intellectual Property Laws and AI - Practice Questions
  • Non-Discrimination Laws and AI - Video Lecture
  • Non-Discrimination Laws and AI - Notes
  • Non-Discrimination Laws and AI - Practice Questions
  • Consumer Protection Laws and AI - Video Lecture
  • Consumer Protection Laws and AI - Notes
  • Consumer Protection Laws and AI - Practice Questions
  • EU AI Act - Introduction - Video Lecture
  • EU AI Act - Introduction - Notes
  • EU AI Act - Introduction - Practice Questions
  • EU AI Act - Examples of Prohibited & High Risk AIs - Video Lecture
  • EU AI Act - Examples of Prohibited & High Risk AIs - Notes
  • EU AI Act - Examples of Prohibited & High Risk AIs - Practice Questions
  • EU AI Act - High Risk AI Requirements - Video Lecture
  • EU AI Act - High Risk AI Requirements - Notes
  • EU AI Act - High Risk AI Requirements - Practice Questions
  • EU AI Act - Conformity Assessment - Video Lecture
  • EU AI Act - Conformity Assessment - Notes
  • EU AI Act - Conformity Assessment - Practice Questions
  • EU AI Act - Documentations - Video Lecture
  • EU AI Act - Documentations - Notes
  • EU AI Act - Documentations - Practice Questions
  • EU AI Act - Complaint and Redress Mechanism - Notes
  • EU AI Act - Complaint and Redress Mechanism - Practice Questions
  • EU AI Act - Penalties - Video Lecture
  • EU AI Act - Penalties - Notes
  • EU AI Act - Penalties - Practice Questions
  • OECD Principles - Video Lecture
  • OECD Principles - Notes
  • OECD Principles - Practice Questions
  • NIST AI Risk Management Framework - Video Lecture
  • NIST AI Risk Management Framework - Notes
  • NIST AI Risk Management Framework - Practice Questions
  • NIST ARIA Program - Video Lecture
  • NIST ARIA Program - Notes
  • NIST ARIA Program - Practice Questions
  • ISO/IEC 42001 - AI Management System - Video Lecture
  • ISO/IEC 42001 - AI Management System - Notes
  • ISO/IEC 42001 - AI Management System - Practice Questions
  • ISO/IEC 22989: Terminology and Concepts for AI - Video Lecture
  • ISO/IEC 22989: Terminology and Concepts for AI - Notes
  • ISO/IEC 22989: Terminology and Concepts for AI - Practice Questions
  • Asilomar AI Principles - Notes
  • Asilomar AI Principles - Practice Questions
  • Institute of Electrical and Electronics Engineers (IEEE) - Notes
  • Institute of Electrical and Electronics Engineers (IEEE) - Practice Questions
  • Liability Reforms in AI - Notes
  • Liability Reforms in AI - Practice Questions

Section 4: Domain 3 - Understanding How to Govern AI Development (22 lectures • 51m)

  • Designing & Building AI Model - Notes
  • Designing & Building AI Model - Practice Questions
  • Documentation of AI Systems - Notes
  • Documentation of AI Systems - Practice Questions
  • AI Impact Assessment - Video Lecture
  • AI Impact Assessment - Notes
  • AI Impact Assessment - Practice Questions
  • Risk Management of AI Systems - Notes
  • Risk Management of AI Systems - Practice Questions
  • Cybersecurity of AI Systems - Notes
  • Cybersecurity of AI Systems - Practice Questions
  • Data Lineage and Provenance - Video Lecture
  • Data Lineage and Provenance - Notes
  • Data Lineage and Provenance - Practice Questions
  • AI Model Functions - Video Lecture
  • AI Model Functions - Notes
  • AI Model Functions - Practice Questions
  • Types of Machine Learning - Video Lecture
  • Types of Machine Learning - Notes
  • Types of Machine Learning - Practice Questions
  • Machine Learning Algorithm - Video Lecture
  • Machine Learning Algorithm - Notes
  • Machine Learning Algorithm - Practice Questions
  • Graphical Processing Units - Notes
  • Graphical Processing Units - Practice Questions
  • Release, Monitoring and Maintenance of the AI Model - Notes
  • Release, Monitoring and Maintenance of the AI Model - Practice Questions
  • AI Model Drifting - Video Lecture
  • AI Model Drifting - Notes
  • AI Model Drifting - Practice Questions
  • AI Model Training - Video Lecture
  • AI Model Training - Notes
  • AI Model Training - Practice Questions
  • AI Model Testing - Video Lecture
  • AI Model Testing - Notes
  • AI Model Testing - Practice Questions

Section 5: Domain 4 - Understanding How to Govern AI Deployment and Use (22 lectures • 35m)

  • Deploying the AI Model - Notes
  • Deploying the AI Model - Practice Questions
  • AI System Inventory - Notes
  • AI System Inventory - Practice Questions
  • AI Model Categories - Video Lecture
  • AI Model Categories - Notes
  • AI Model Categories - Practice Questions
  • Proprietary AI vis-a-vis Open Source AI Model - Video Lecture
  • Proprietary AI vis-a-vis Open Source AI Model - Notes
  • Open-Source AI Models - Video Lecture
  • Open-Source AI Models - Notes
  • Open-Source AI Models - Practice Questions
  • Proprietary AI Models - Video Lecture
  • Proprietary AI Models - Notes
  • Proprietary AI Models - Practice Questions
  • Large AI Model vis-a-vis Small AI Model - Video Lecture
  • Large AI Model vis-a-vis Small AI Model - Notes
  • AI Deployment Options - Video Lecture
  • AI Deployment Options - Notes
  • AI Deployment Options - Practice Questions
  • AI Model Card - Video Lecture
  • AI Model Card - Notes
  • AI Model Card - Practice Questions
  • AI Localization Policy - Notes
  • AI Localization Policy - Practice Questions
  • AI Deactivation Policy - Notes
  • AI Deactivation Policy - Practice Questions
  • AI Incident Management Policy - Notes
  • AI Incident Management Policy - Practice Questions
  • AI Communication Policy - Notes
  • AI Communication Policy - Practice Questions
  • AI Assessment Methods - Notes
  • AI Assessment Methods - Practice Questions
  • Deployment and Use of the AI Model - Notes
  • Deployment and Use of the AI Model - Practice Questions

Section 6: Practice Questions

2. LLM Engineering, RAG, & AI Agents Masterclass [2026]

Kurikulum:

Section 1: Welcome to the Bootcamp! (5 lectures • 26m)

  • Instructor Introduction and LLM in Action!
  • Join our Free Community & Connect with Learners worldwide
  • Download the Bootcamp Materials
  • Bootcamp Outline
  • Key Success Tips

Section 2: PART A: CLOSED-SOURCE LLMs, GRADIO, & BENCHMARKING (1 lecture • 1m)

  • Welcome to Part A of the Bootcamp!

Section 3: Day 1 - Develop a Character AI Chatbot Using OpenAI API (12 lectures • 1h)

  • Task 1. Character AI Chatbot Project Introduction & Key Learning Objectives
  • Task 2. Download Anaconda and Configure OpenAI API
  • Task 3. Our First Chat with OpenAI API
  • Practice Opportunity Question: Test OpenAI API for Text Generation
  • Practice Opportunity Solution: Test OpenAI API for Text Generation
  • Task 4. Understand OpenAI API Response Structure & Token Usage
  • Practice Opportunity Question: OpenAI Tokenizer Tool
  • Practice Opportunity Solution: OpenAI Tokenizer Tool
  • Task 5. Giving Our AI Chatbot a Personality Using the System Message!
  • Practice Opportunity Question: Changing AI Personalities
  • Practice Opportunity Solution: Changing AI Personalities
  • Conclusion, Summary, and Thank You!

Section 4: Day 2 - Build an AI Calorie Tracker Using OpenAI API (Vision GPTs) (15 lectures • 1h 5m)

  • Task 1. AI Calorie Tracker Project Introduction & Key Learning Objectives
  • Task 2. Read a Sample Image Using Python's Pillow (PIL) Library
  • Practice Opportunity Question: Read & View Images Using PIL
  • Practice Opportunity Solution: Read & View Images Using PIL
  • Task 3. Understand Prompt Engineering Fundamentals
  • Practice Opportunity Question: Prompt Engineering Fundamentals
  • Practice Opportunity Solution: Prompt Engineering Fundamentals
  • Task 4. Perform Image Recognition Using OpenAI API's Vision GPT Models (Part A)
  • Task 4. Perform Image Recognition Using OpenAI API’s Vision GPT Models (Part B)
  • Practice Opportunity Question: Calling OpenAI API's Vision GPT Models
  • Practice Opportunity Solution: Calling OpenAI API's Vision GPT Models
  • Task 5. Obtain the Calorie Count of Food Images Using Vision GPT Models
  • Practice Opportunity Question: Expand API Payload to include Nutritional Value
  • Practice Opportunity Solution: Expand API Payload to include Nutritional Value
  • Conclusion, Summary, & Thank You Message!

Section 5: Day 3 - Build an Adaptive LLM/AI Tutor with Gradio (15 lectures • 1h 6m)

  • Task 1. Introduction & Key Learning Objectives - Adaptive AI Tutor with Gradio
  • Task 2. Learn Gradio 101 & Showcase Capabilities (Maps, Images, & Streaming)
  • Task 3. Build and Test an AI Tutor Function (Without Gradio)
  • Practice Opportunity Question: Test AI Tutor Function with Many Personalities
  • Practice Opportunity Solution: Test AI Tutor Function with Many Personalities
  • Task 4. Build an Interactive Interface Using Gradio (No Streaming)
  • Practice Opportunity Question: Configure Gradio Interface Components
  • Practice Opportunity Solution: Configure Gradio Interface Components
  • Task 5. Add Streaming for an Enhanced Chat Experience in Gradio
  • Practice Opportunity Question: Streaming for an Enhanced Chat Experience
  • Practice Opportunity Solution: Streaming for an Enhanced Chat Experience
  • Task 6. Build a Multi-Level AI Tutor in Gradio with Explanation Level Slider
  • Practice Opportunity Question: Testing AI Tutor Slider Levels & Einstein Model
  • Practice Opportunity Solution: Testing AI Tutor Slider Levels & Einstein Model
  • Conclusion, Summary, & Thank You Message!

Section 6: Day 4 - Build Websites with Claude, Gemini, & OpenAI & LLMs Leaderboards (23 lectures • 1h 28m)

  • Task 1. Introduction & Module Objectives - Build Websites & LLMs Leaderboards
  • Task 2. Setting Up Our Development Environment & Installing Dependencies
  • Practice Opportunity Question: Installation & Environment Setup
  • Practice Opportunity Solution: Installation & Environment Setup
  • Task 3. Build a Multi-LLM Comparison Tool (Claude, Gemini, OpenAI, Llama)
  • Practice Opportunity Question: Multi-LLM Comparison Tool
  • Practice Opportunity Solution: Multi-LLM Comparison Tool
  • Task 4. Create a Dynamic LLM Leaderboard (Based on User Voting)
  • Practice Opportunity Question: Dynamic LLM Leaderboard Logic
  • Practice Opportunity Solution: Dynamic LLM Leaderboard Logic
  • Task 5. Analyze AI Model Trends & User Preference Analytics
  • Practice Opportunity Question: Analyzing LLM Trends & User Preferences
  • Practice Opportunity Solution: Analyzing LLM Trends & User Preferences
  • Task 6. Build a Web App Using Streamlit (Alternative Framework to Gradio)
  • Practice Opportunity Question: Streamlit Web App for LLM Comparison
  • Practice Opportunity Solution: Streamlit Web App for LLM Comparison
  • Task 7. Add Advanced Features: Caching, Session State, & Performance Optimization
  • Practice Opportunity Question: Streamlit Caching & Session State
  • Practice Opportunity Solution: Streamlit Caching & Session State
  • Task 8. Deploy Your Web App Using Streamlit Cloud & Vercel
  • Conclusion and Thank You!

Section 7: PART B: OPEN-SOURCE LLMs, HUGGING FACE, RAG & FINE-TUNING (1 lecture • 2m)

  • Welcome to Part B of the Bootcamp!

Section 8: Day 5 - Hugging Face Open-Source Models (26 lectures • 2h 2m)

  • Task 1. Introduction and Module Objectives - Open-Source LLMs on Hugging Face
  • Task 2. Hugging Face 101: Account Setup, Model Cards, & How to Download Models
  • Practice Opportunity Question: Explore Hugging Face Hub & Model Cards
  • Practice Opportunity Solution: Explore Hugging Face Hub & Model Cards
  • Task 3. Install Necessary Libraries & Download Models Locally
  • Practice Opportunity Question: Download & Load Models Locally
  • Practice Opportunity Solution: Download & Load Models Locally
  • Task 4. Load, Configure, and Compare Open-Source LLMs (Llama, Phi, Gemma, Mistral)
  • Practice Opportunity Question: Loading & Configuring Open-Source LLMs
  • Practice Opportunity Solution: Loading & Configuring Open-Source LLMs
  • Task 5. Quantization 101: Reduce Model Size for Efficient Deployment
  • Practice Opportunity Question: Model Quantization & GGUF Formats
  • Practice Opportunity Solution: Model Quantization & GGUF Formats
  • Task 6. Hugging Face Transformers Library: AutoModelForCasualLM
  • Practice Opportunity Question: Transformers AutoModelForCasualLM
  • Practice Opportunity Solution: Transformers AutoModelForCasualLM
  • Task 7. Read PDF Documents & Extract Content Using PyPDF Library
  • Practice Opportunity Question: PyPDF Library
  • Practice Opportunity Solution: PyPDF Library
  • Task 8. Build the Q&A Logic & Prompt the LLM (Microsoft Phi-4-mini)
  • Practice Opportunity Question: Test the Q&A Pipeline with Open-Source LLM
  • Practice Opportunity Solution: Test the Q&A Pipeline with Open-Source LLM
  • Task 9. Switch LLMs (LLama, Phi, & Gemma) & Build Gradio Interface
  • Practice Opportunity Question: Testing Qwen Open-Source LLM
  • Practice Opportunity Solution: Testing Qwen Open-Source LLM
  • Conclusion & Thank You!

Section 9: Day 6 - Reasoning Open-Source LLMs on Hugging Face & Model Leaderboards (20 lectures • 2h 14m)

  • Task 1. Introduction and Module Objectives - Reasoning LLMs on Hugging Face
  • Task 2. Explore Hugging Face Datasets Library & Install Key Libraries
  • Practice Opportunity Question: Explore Hugging Face Datasets
  • Practice Opportunity Solution: Explore Hugging Face Datasets
  • Task 3. Load Financial News Datasets from Hugging Face
  • Practice Opportunity Question: Explore Financial News Datasets
  • Practice Opportunity Solution: Explore Financial News Datasets
  • Task 4. Load and Test DeepSeek Reasoning Model - Part 1
  • Task 4. Load and Test DeepSeek Reasoning Model - Part 2
  • Practice Opportunity Question: Test Math Capabilities of DeepSeek
  • Practice Opportunity Solution: Test Math Capabilities of DeepSeek
  • Task 5. A Framework for Choosing the Right AI Model for Your Business - Part 1
  • Task 5. A Framework for Choosing the Right AI Model for Your Business - Part 2
  • Task 6. Model Leaderboards and Old/New Model Benchmarks - Part 1
  • Task 6. Model Leaderboards and Old/New Model Benchmarks - Part 2
  • Task 7. Prompting DeepSeek for Reasoning and Classification
  • Practice Opportunity Question: Analyze News Sentiment with DeepSeek
  • Practice Opportunity Solution: Analyze News Sentiment with DeepSeek
  • Task 8. Building Gradio Interface
  • Conclusion and Thank You!

Section 10: Day 7 - Build RAG Pipelines in LangChain (22 lectures • 1h 25m)

  • Task 1. Introduction & Module Objectives - Build RAG Pipelines in LangChain
  • Task 2. Understand Retrieval Augmented Generation (RAG) & Why Use it
  • Task 3. LangChain 101 & Key Features
  • Task 4. Setup, Gather RAG Tools & Load Datasets
  • Practice Opportunity Question: LangChain Textloader Testing
  • Practice Opportunity Solution: LangChain Textloader Testing
  • Task 5. Splitting (Chunking) Documents Using LangChain Text Splitter
  • Practice Opportunity Question: Configuring RecursiveCharacterTextSplitter
  • Practice Opportunity Solution: Configuring RecursiveCharacterTextSplitter
  • Task 6. Embeddings and Vector Store Creation
  • Practice Opportunity Question: Tensorflow Embeddings Projector
  • Practice Opportunity Solution: Tensorflow Embeddings Projector
  • Task 7. Testing the Retrieval Pipeline
  • Practice Opportunity Question: Retrieval Pipeline Testing
  • Practice Opportunity Solution: Retrieval Pipeline Testing
  • Task 8. Building the Q&A Chain & Testing with LLMs
  • Practice Opportunity Question: Building Q&A Chain with LLMs
  • Practice Opportunity Solution: Building Q&A Chain with LLMs
  • Task 9. Build Gradio Interface for RAG Pipeline
  • Practice Opportunity Question: Build Gradio Interface for RAG
  • Practice Opportunity Solution: Build Gradio Interface for RAG
  • Conclusion and Thank You!

Section 11: Day 8 - Build a Resume & Cover Letter AI Assistant (26 lectures • 2h 4m)

  • Task 1. Introduction & Module Objectives - AI Resume & Cover Letter Assistant
  • Task 2. Understand Prompt Engineering for Structured Output (JSON)
  • Practice Opportunity Question: Prompt Engineering for Structured Outputs
  • Practice Opportunity Solution: Prompt Engineering for Structured Outputs
  • Task 3. Pydantic Basics for Structured Data Models
  • Practice Opportunity Question: Pydantic Data Models
  • Practice Opportunity Solution: Pydantic Data Models
  • Task 4. Integration of Pydantic with OpenAI API for Structured Outputs
  • Practice Opportunity Question: JSON Mode and Structured Outputs
  • Practice Opportunity Solution: JSON Mode and Structured Outputs
  • Task 5. Build Core Functions: Parse User Inputs & OpenAI Integration
  • Practice Opportunity Question: Building Resume Parser Functions
  • Practice Opportunity Solution: Building Resume Parser Functions
  • Task 6. Generate Resume Improvements & Content Suggestions
  • Practice Opportunity Question: Generating Resume Suggestions
  • Practice Opportunity Solution: Generating Resume Suggestions
  • Task 7. Generate Personalized Cover Letters
  • Practice Opportunity Question: Generate Customized Cover Letters
  • Practice Opportunity Solution: Generate Customized Cover Letters
  • Task 8. Handle Edge Cases & Optimize Prompts for Quality Output
  • Practice Opportunity Question: Handling Edge Cases & Validation
  • Practice Opportunity Solution: Handling Edge Cases & Validation
  • Task 9. Build Gradio Interface & Deploy Your App
  • Practice Opportunity Question: Building Gradio Interface for Resume Assistant
  • Practice Opportunity Solution: Building Gradio Interface for Resume Assistant
  • Conclusion & Thank You!

Section 12: Day 9 - Fine-Tuning of LLMs with LORA, SFTTrainer, PEFT, & TRL (20 lectures • 1h 48m)

  • Task 1. Introduction & Module Objectives - Fine-Tuning LLMs
  • Task 2. Understand Fine-Tuning: Why, When, and How to Do It
  • Practice Opportunity Question: Fine-Tuning vs. Prompt Engineering
  • Practice Opportunity Solution: Fine-Tuning vs. Prompt Engineering
  • Task 3. Parameter-Efficient Fine-Tuning (PEFT) & LoRA Overview
  • Practice Opportunity Question: PEFT & LoRA Parameters
  • Practice Opportunity Solution: PEFT & LoRA Parameters
  • Task 4. Setup and Data Preparation for Fine-Tuning
  • Practice Opportunity Question: Data Preparation for Fine-Tuning
  • Practice Opportunity Solution: Data Preparation for Fine-Tuning
  • Task 5. Fine-Tuning with SFTTrainer (Supervised Fine-Tuning)
  • Practice Opportunity Question: SFTTrainer Configuration
  • Practice Opportunity Solution: SFTTrainer Configuration
  • Task 6. Fine-Tuning with LoRA and PEFT
  • Practice Opportunity Question: LoRA Configuration & Parameters
  • Practice Opportunity Solution: LoRA Configuration & Parameters
  • Task 7. Evaluate Fine-Tuned Models & Comparison with Base Models
  • Practice Opportunity Question: Model Evaluation Metrics
  • Practice Opportunity Solution: Model Evaluation Metrics
  • Task 8. Inference with Fine-Tuned Models & Deploy Your Model
  • Conclusion and Thank You!

Section 13: PART C: AI AGENTS WITH LANGGRAPH, AUTOGEN, CREWAI, N8N, & MCP (1 lecture • 2m)

  • Welcome to Part C of the Bootcamp!

Section 14: Day 10 - Build Multi-Model AI Agent Teams Using AutoGen (20 lectures • 1h 16m)

  • Task 1. Introduction & Module Objectives - Build AI Agent Teams with AutoGen
  • Task 2. AutoGen 101: Understanding Agent-Based Systems & Architecture
  • Practice Opportunity Question: AutoGen Architecture & Agent Design
  • Practice Opportunity Solution: AutoGen Architecture & Agent Design
  • Task 3. Setup AutoGen & Create Simple Agents
  • Practice Opportunity Question: Creating Simple AutoGen Agents
  • Practice Opportunity Solution: Creating Simple AutoGen Agents
  • Task 4. Define Multi-Agent Workflows & Agent Communication
  • Practice Opportunity Question: Multi-Agent Communication Patterns
  • Practice Opportunity Solution: Multi-Agent Communication Patterns
  • Task 5. Build Specialized Agents (Researcher, Analyst, Writer)
  • Practice Opportunity Question: Building Specialized Agents
  • Practice Opportunity Solution: Building Specialized Agents
  • Task 6. Implement Tool Use & Code Execution in Agents
  • Practice Opportunity Question: Tool Integration in AutoGen
  • Practice Opportunity Solution: Tool Integration in AutoGen
  • Task 7. Handle Agent Conflicts & Consensus Mechanisms
  • Practice Opportunity Question: Multi-Agent Consensus & Conflict Resolution
  • Practice Opportunity Solution: Multi-Agent Consensus & Conflict Resolution
  • Task 8. Build a Real-World Application: Research & Analysis Team
  • Conclusion and Thank You!

Section 15: Day 11 - Building AI Agentic Workflows in LangGraph (24 lectures • 1h 46m)

  • Task 1. Introduction & Module Objectives - AI Agentic Workflows in LangGraph
  • Task 2. LangGraph 101: Understanding State Graphs & Agent Workflows
  • Practice Opportunity Question: LangGraph Architecture & Concepts
  • Practice Opportunity Solution: LangGraph Architecture & Concepts
  • Task 3. Setup LangGraph & Create Simple State Graphs
  • Practice Opportunity Question: Creating State Graphs in LangGraph
  • Practice Opportunity Solution: Creating State Graphs in LangGraph
  • Task 4. Build Agent Nodes & Edge Transitions
  • Practice Opportunity Question: Agent Nodes & Conditional Edges
  • Practice Opportunity Solution: Agent Nodes & Conditional Edges
  • Task 5. Implement Tool-Use Patterns in LangGraph Agents
  • Practice Opportunity Question: Tool Integration in LangGraph
  • Practice Opportunity Solution: Tool Integration in LangGraph
  • Task 6. Build Complex Agent Workflows with Multiple Branches
  • Practice Opportunity Question: Complex Workflow Design
  • Practice Opportunity Solution: Complex Workflow Design
  • Task 7. Implement Memory & State Management in Agents
  • Practice Opportunity Question: Agent Memory & State Persistence
  • Practice Opportunity Solution: Agent Memory & State Persistence
  • Task 8. Build a Real-World Application: Document Analysis & Summarization Agent
  • Practice Opportunity Question: Building Document Analysis Agents
  • Practice Opportunity Solution: Building Document Analysis Agents
  • Conclusion and Thank You!

Section 16: Day 12 - Build A Team of Data Science AI Agents Using CrewAI (40 lectures • 3h 24m)

  • Task 1. Introduction & Module Objectives - Data Science Agents with CrewAI
  • Task 2. CrewAI 101: Understanding Agents, Roles, & Team Dynamics
  • Practice Opportunity Question: CrewAI Concepts & Design
  • Practice Opportunity Solution: CrewAI Concepts & Design
  • Task 3. Setup CrewAI & Install Dependencies
  • Practice Opportunity Question: CrewAI Environment Setup
  • Practice Opportunity Solution: CrewAI Environment Setup
  • Task 4. Create Individual Agents with Specific Roles
  • Practice Opportunity Question: Defining Agent Roles & Responsibilities
  • Practice Opportunity Solution: Defining Agent Roles & Responsibilities
  • Task 5. Implement Tools & Task Definitions for Each Agent
  • Practice Opportunity Question: Tool Implementation in CrewAI
  • Practice Opportunity Solution: Tool Implementation in CrewAI
  • Task 6. Design Agent Workflows & Task Dependencies
  • Practice Opportunity Question: Workflow Design & Task Dependencies
  • Practice Opportunity Solution: Workflow Design & Task Dependencies
  • Task 7. Build Data Processing Pipeline with Agents
  • Practice Opportunity Question: Data Processing with AI Agents
  • Practice Opportunity Solution: Data Processing with AI Agents
  • Task 8. Implement Statistical Analysis & Model Evaluation Tasks
  • Practice Opportunity Question: Statistical Analysis with AI Agents
  • Practice Opportunity Solution: Statistical Analysis with AI Agents
  • Task 9. Create Visualization & Reporting Tasks
  • Practice Opportunity Question: Report Generation by AI Agents
  • Practice Opportunity Solution: Report Generation by AI Agents
  • Task 10. Build a Real-World Application: Stock Market Analysis & Forecasting Team
  • Practice Opportunity Question: Building Stock Analysis Agent Team
  • Practice Opportunity Solution: Building Stock Analysis Agent Team
  • Task 11. Extend Team with Additional Agents & Capabilities
  • Practice Opportunity Question: Extending CrewAI Teams
  • Practice Opportunity Solution: Extending CrewAI Teams
  • Conclusion and Thank You!

Section 17: Day 13 - Build Agentic AI Workflows in n8n (14 lectures • 1h 48m)

  • Task 1. Introduction & Module Objectives - n8n Agentic Workflows
  • Task 2. n8n 101: Understanding Workflow Automation & Integration
  • Practice Opportunity Question: n8n Workflow Concepts
  • Practice Opportunity Solution: n8n Workflow Concepts
  • Task 3. Setup n8n & Configure LLM Integration
  • Practice Opportunity Question: n8n Setup & LLM Configuration
  • Practice Opportunity Solution: n8n Setup & LLM Configuration
  • Task 4. Build Simple Agent Workflows with n8n
  • Practice Opportunity Question: Building n8n Agent Workflows
  • Practice Opportunity Solution: Building n8n Agent Workflows
  • Task 5. Implement Tool Integration & API Connections
  • Practice Opportunity Question: API Integration in n8n
  • Practice Opportunity Solution: API Integration in n8n
  • Task 6. Create Complex Multi-Step Agent Workflows
  • Practice Opportunity Question: Complex n8n Workflows
  • Practice Opportunity Solution: Complex n8n Workflows
  • Task 7. Build a Real-World Application: Customer Support Automation Agent
  • Conclusion and Thank You!

Section 18: Day 14 - Build AI Agents with MCP & OpenAI Agents SDK (13 lectures • 1h 8m)

  • Task 1. Introduction & Module Objectives - MCP & OpenAI Agents SDK
  • Task 2. Model Context Protocol (MCP) 101: Understanding Protocol & Architecture
  • Practice Opportunity Question: MCP Fundamentals & Use Cases
  • Practice Opportunity Solution: MCP Fundamentals & Use Cases
  • Task 3. Setup OpenAI Agents SDK & Configure MCP Servers
  • Practice Opportunity Question: OpenAI Agents SDK Setup
  • Practice Opportunity Solution: OpenAI Agents SDK Setup
  • Task 4. Build Agents Using OpenAI Agents SDK
  • Practice Opportunity Question: Building with OpenAI Agents SDK
  • Practice Opportunity Solution: Building with OpenAI Agents SDK
  • Task 5. Implement Custom MCP Servers & Tools
  • Practice Opportunity Question: Custom MCP Server Implementation
  • Practice Opportunity Solution: Custom MCP Server Implementation
  • Task 6. Build a Real-World Application: Integration Agent with Multiple MCP Servers
  • Practice Opportunity Question: Multi-MCP Integration Agents
  • Practice Opportunity Solution: Multi-MCP Integration Agents
  • Conclusion and Thank You!

Section 19: Congratulations and Thank You! (2 lectures • 1m)

  • Congratulations and Next Steps
  • Thank You & Community Resources

Section 20: Labs (Beta) (3 lectures • 4m)

  • Labs Overview & How to Use
  • Lab 1: Interactive Coding Environment
  • Lab 2: Challenge Projects

3. Agentic AI - Risk and Cybersecurity Masterclass 2026

Kurikulum:

Section 1: Introduction (3 lectures • 30m)

  • Introduction
  • What Is Agentic AI?
  • Agentic AI vs Generative AI

Section 2: Agentic AI Patterns and Architectures (2 lectures • 25m)

  • Agentic AI Patterns and Architectures
  • AI Agents - Demo

Section 3: Agentic AI In Cybersecurity (2 lectures • 18m)

  • Agentic AI Use Cases in Cybersecurity
  • Agentic AI Use Cases in Cybersecurity - Demo

Section 4: Agentic AI - Existing Risks (4 lectures • 24m)

  • Agentic AI - Existing Risks
  • Bias
  • Transparency
  • AI Model Attacks

Section 5: Agentic AI - New Risks (7 lectures • 40m)

  • Autonomy
  • Accountability
  • Misalignment
  • Disempowerment
  • Misuse
  • Agent Hijacking
  • Agentic Pattern Vulnerabilities

Section 6: Creating An Agentic AI Security Framework (1 lecture • 10m)

  • Creating An Agentic AI Security Framework

Section 7: Threat Modeling Agentic AI (4 lectures • 45m)

  • Threat Modeling Agentic AI - Part 1
  • Threat Modeling Agentic AI - Part 2
  • Threat Modeling Agentic AI - Part 3
  • Threat Modeling - Case Study

Section 8: The Agentic AI Security Scoping Matrix (1 lecture • 12m)

  • Understanding the Agentic AI Security Scoping Matrix

Section 9: Model Context Protocol (3 lectures • 28m)

  • What is Model Context Protocol
  • MCP Risks
  • Reviewing MCP Servers

Section 10: Wrapping Up (1 lecture • 3m)

  • The Way Forward

4. AI Engineer Agentic Track: The Complete Agent & MCP Course

Kurikulum:

Week 1: AI Agents & Frameworks (27 lectures • 4h 6m)

  • Autonomous AI Agent Demo: Using N8n to Control Smart Home Devices
  • AI Agent Frameworks Explained
  • Day 1 - Setting Up Your Environment: Python, VSCode & OpenAI API Keys
  • Day 1 - Building Your First AI Agent: Tools, Chains & Agent Loops
  • Day 1 - Reasoning about Agent Types: Autonomous vs Tool-Using Agents
  • Day 1 - Exploring Weather Tool & Weather Agent: Function Calling Simplified
  • Day 2 - Converting Agents into Tools: Building Hierarchical AI Systems
  • Day 2 - Agent Control Flow: When to Use Handoffs vs Agents as Tools
  • Day 2 - From Function Calls to Agent Autonomy: Sales Automation with OpenAI SDK
  • Day 2 - Agentic AI for Business: Creating Interactive Sales Outreach Tools
  • Day 3 - Multi-Model Integration: Using Gemini, DeepSeek & Groq with OpenAI Agents
  • Day 3 - Implementing Guardrails & Structured Outputs for Robust AI Agent Systems
  • Day 3 - AI Safety in Practice: Implementing Guardrails for LLM Agent Applications
  • Day 4 - Building Deep Research Agents: Implementing OpenAI's Web Search Tool
  • Day 4 - Building a Planner Agent: Using Structured Outputs with Pydantic in AI
  • Day 4 - Building an End-to-End Research Pipeline with GPT-4 Agents & Async Tasks
  • Day 4 - Building a Deep Research Agent: Parallel Searches with AsyncIO
  • Day 5 - Building a Modular AI Research System with Gradio UI Implementation
  • Day 5 - Deep Research App: Gradio to Visualize & Monitor Autonomous AI Agents
  • Day 5 - Deploying Smart Research Agents with Gradio and HuggingFace Spaces
  • Day 2 - Converting Agents into Tools: Building Hierarchical AI Systems
  • Day 2 - Agent Control Flow: When to Use Handoffs vs Agents as Tools
  • Day 2 - From Function Calls to Agent Autonomy: Sales Automation with OpenAI SDK
  • Day 2 - Agentic AI for Business: Creating Interactive Sales Outreach Tools
  • Day 3 - Multi-Model Integration: Using Gemini, DeepSeek & Groq with OpenAI Agents
  • Day 3 - Implementing Guardrails & Structured Outputs for Robust AI Agent Systems
  • Day 3 - AI Safety in Practice: Implementing Guardrails for LLM Agent Applications

Week 2: OpenAI Agents SDK & Advanced Patterns (21 lectures • 2h 26m)

  • Day 1 - Building Your First AI Agent with OpenAI Agents SDK
  • Day 1 - Async Python for AI Agents: Non-Blocking Code for Production
  • Day 1 - Multi-Model Integration with OpenAI Agents SDK
  • Day 1 - Building Research Agents with OpenAI SDK
  • Day 1 - Building AI Agents with OpenAI SDK: Parallel Execution & Complex Workflows
  • Day 2 - Intro to CrewAI: Multi-Agent Collaboration Explained
  • Day 2 - CrewAI Framework: Building Autonomous Agent Teams
  • Day 2 - Building AI Teams with CrewAI: Manager & Role-Based Agents
  • Day 2 - CrewAI Agents for Data Analysis: Building a Research Team
  • Day 2 - CrewAI for Marketing: Building an Autonomous Marketing Agent Team
  • Day 3 - Agents with Long-Term Memory: Building Persistent AI Systems
  • Day 3 - Building AI with Memory: SQLite & LangChain Integration
  • Day 4 - Complex Agent Workflows: Sequential & Hierarchical Execution
  • Day 4 - Building Complex AI Workflows: Autonomous Research & Writing Agents
  • Day 4 - Building Production-Ready AI Systems: Error Handling & Monitoring
  • Day 5 - Building AI Assistants: Langchain & CrewAI Integration
  • Day 5 - Autonomous Agent for Content Generation: Multi-Agent Writing System
  • Day 5 - Advanced CrewAI: Building Domain-Specific Agent Teams
  • Day 5 - CrewAI for E-commerce: Building an Autonomous Sales Agent System
  • Day 5 - CrewAI Hierarchical Agents: Building Complex Multi-Team Systems
  • Day 5 - Advanced CrewAI Techniques: Callbacks, Memory & Custom Tools

Week 3: Crew AI Framework & Advanced Patterns (19 lectures • 2h 32m)

  • Day 1 - Crew AI Framework: Creating Collaborative AI Agent Teams
  • Day 1 - Crew AI Framework Explained: Agents, Tasks & Processing Modes Tutorial
  • Day 1 - Crew AI & LightLLM: Flexible Framework for Integrating Multiple LLMs
  • Day 1 - Crew AI Tutorial: Setting Up a Debate Project with GPT-4o mini
  • Day 1 - How to Create an AI Debate System Using Crew AI and Multiple LLMs
  • Day 1 - Building AI Debate Systems with CrewAI: Compare Different LLMs
  • Day 2 - Building Crew AI Projects: Tools, Context & Google Search Integration
  • Day 2 - Building Multi-Agent Financial Research Systems with Crew.ai
  • Day 2 - Enhancing AI Agents with Web Search: Solving the Knowledge Cutoff Problem
  • Day 3 - Building a Crew AI Stock Picker: Multi-Agent System for Investments
  • Day 3 - Implementing Pydantic Outputs in Crew AI: Stock Picker Agent Tutorial
  • Day 3 - Custom Tool Development for Crew AI: JSON Schema & Push Notifications
  • Day 4 - Crew AI Memory: Vector Storage & SQL Implementation for AI Agents
  • Day 4 - Crew AI for Coding Tasks: Agents That Generate & Run Python Code
  • Day 4 - Create a Python-Writing AI Agent: Practical Implementation with Crew AI
  • Day 5 - Building AI Teams: Configure Crew AI for Collaborative Development
  • Day 5 - Collaborative AI Agent Development for a Stock Trading Framework
  • Day 5 - Building a Trading Application Using GPT-4o & Claude
  • Day 5 - From Single Modules to Complete Systems: Advanced CrewAI Techniques

Week 4: LangGraph & Advanced Agent Systems (23 lectures • 2h 59m)

  • Day 1 - LangGraph Explained: Graph-Based Architecture for Robust AI Agents
  • Day 1 - LangGraph Explained: Framework, Studio, and Platform Components Compared
  • Day 1 - LangGraph Theory: Core Components for Building Advanced Agent Systems
  • Day 2 - LangGraph Deep Dive: Managing State in Graph-Based Agent Workflows
  • Day 2 - Mastering LangGraph: How to Define State Objects & Use Reducers
  • Day 2 - LangGraph Fundamentals: Creating Nodes, Edges & Workflows Step-by-Step
  • Day 2 - LangGraph Tutorial: Building an OpenAI Chatbot with Graph Structures
  • Day 3 - LangGraph Advanced Tutorial: Super Steps & Checkpointing Explained
  • Day 3 - Setting Up Langsmith & Creating Custom Tools for LangGraph Applications
  • Day 3 - LangGraph Tool Calling: Working with Conditional Edges & Tool Nodes
  • Day 3 - LangGraph Checkpointing: How to Maintain Memory Between Conversations
  • Day 3 - Building Persistent AI Memory with SQLite: LangGraph State Management
  • Day 4 - Playwright Integration with LangGraph: Creating Web-Browsing AI Agents
  • Day 4 - Create AI Web Assistants: Playwright, LangChain & Gradio Implementation
  • Day 4 - LLM Evaluator Agents: Creating Feedback Loops with Structured Outputs
  • Day 4 - Creating LLM Feedback Loops: Worker-Evaluator Implementation in LangGraph
  • Day 4 - Building an AI Sidekick Using LangGraph, Gradio & Browser Automation
  • Day 5 - Agentic AI: Add Web Search, File System & Python REPL to Your Assistant
  • Day 5 - LangChain Tool Integration: Building a Powerful AI Sidekick from Scratch
  • Day 5 - Creating AI Workflows: Graph Builders & Node Communication Techniques
  • Day 5 - Creating Isolated User Sessions in Gradio Apps Using State Management
  • Day 5 - Inside AI Feedback Loops: Seeing How AI Evaluates & Corrects Errors
  • Day 5 - AI Assistant Upgrades: Memory, Clarifying Questions & Custom Tools

Week 5: AutoGen Framework & Distributed Agents (17 lectures • 2h 10m)

  • Day 1 - Microsoft Autogen 0.5.1: AI Agent Framework Explained for Beginners
  • Day 1 - AutoGen vs Other Agent Frameworks: Features & Components Compared
  • Day 1 - AutoGen Agent Chat Tutorial: Creating Tools and Database Integration
  • Day 1 - Essential AI Components: Models, Messages & Agents Explained
  • Day 2 - Advanced Autogen Agent Chat: Multimodal Features & Structured Outputs
  • Day 2 - Implementing Primary and Evaluator Agents in AutoGen with Langchain
  • Day 2 - Headless Web Scraping Tutorial: MCP Server Fetch Integration in AutoGen
  • Day 3 - AutoGen Core: The Backbone of Distributed Agent Communications
  • Day 3 - Agent Communication in Autogen Core: Message Handlers & Dispatching
  • Day 3 - AutoGenCore Agent Registration and Message Handling: Practical Examples
  • Day 3 - AutoGenCore Standalone Agents: Rock Paper Scissors with GPT-4o & Llama
  • Day 4 - Autogen Core Distributed Runtime: Architecture & Components Explained
  • Day 4 - Implementing Distributed AI Agents with AutoGen Core and gRPC Runtime
  • Day 4 - Building Distributed Agent Systems: AutoGen Cross-Process Communication
  • Day 5 - Creating Autonomous Agents That Write & Deploy Other Agents in AutoGen
  • Day 5 - Implementing Agent-to-Agent Messaging with Autogen Core & Templates
  • Day 5 - Creating Autonomous AI Agents that Collaborate Using Async Python

Week 6: MCP - Model Context Protocol (23 lectures • 2h 50m)

  • Day 1 - Intro to MCP: The USB-C of Agentic AI
  • Day 1 - Understanding MCP Hosts, Clients, and Servers
  • Day 1 - Using MCP Servers with OpenAI Agents SDK
  • Day 1 - Exploring Node-Based MCP Servers & Tool Access
  • Day 1 - Building an Agent That Uses Multiple MCP Servers
  • Day 1 - MCP Marketplaces & Security Considerations
  • Day 2 - Intro to Week 6 Day 2: Building Your Own MCP Server
  • Day 2 - Wiring Business Logic into Your MCP Server
  • Day 2 - Creating Client Code to Use Your MCP Server
  • Day 2 - Wrap-Up: Capabilities of Your Custom MCP Server
  • Day 3 - Exploring Types of MCP Servers and Agent Memory
  • Day 3 - Brave Search API: MCP Server Calling the Web
  • Day 3 - Integrating Polygon API for Stock Market Data
  • Day 3 - Advanced Market Tools Using Paid Polygon Plan
  • Day 4 - What's Next: Launching Our Agent Trading Floor
  • Day 4 - Viewing the User Interface for Trading Activity
  • Day 4 - How Trading Agents Operate and Make Decisions
  • Day 4 - Portfolio Management with Four Autonomous Agents
  • Day 5 - Which Agent Framework Should You Pick?
  • Day 5 - Key Settings and Launching the Trading System
  • Day 5 - Advice for Selecting Agentic Frameworks
  • Day 5 - 10 Essential Lessons for Building Agent Solutions
  • Day 5 - Course Recap and Final Goodbye – Keep Building!

File Utama

  • .gitignore
  • .vercelignore
  • README.md
  • package.json
  • vercel.json