Section 1: Linux Fundamentals

Topics Covered:

1. Introduction to Linux – History, distributions, architecture, CLI vs GUI

2. Installing Linux – VM, WSL, cloud instances; post-install setup

3. Command Line Basics – Navigation, file operations, wildcards, history

4. File Permissions & Ownership – chmod, chown, special permissions, sudo

5. Users & Groups – Creating users, group management, best practices

6. Process & System Management – ps, top, jobs, systemctl, logs

7. Package Management – apt, yum/dnf, installing/removing packages

8. File Search, Archiving & Text Processing – find, grep, sed, awk, tar

9. Networking Fundamentals – IP, routing, DNS, ping, ports, traceroute

10. Storage & File Systems – partitions, mounts, file system types, swap

11. Environment & Configuration – variables, aliases, system-wide configs

12. System Security Basics – updates, sudo, firewall basics (ufw)

13. iptables & Firewall Security – rules, policies, persistence, nftables

14. Logging & Monitoring – journalctl, logrotate, CPU/disk/network monitoring

15. Cron Jobs & Scheduling – cron syntax, examples, systemd timers

16. Services & Daemon Management – systemd unit files, custom services

17. Disk Management & LVM – partitions, logical volumes, snapshots

18. SSH & Remote Access – SSH keys, SCP, rsync, securing SSH

Hands-on Practice: Boot Linux, install Ubuntu, manage files and users, configure firewall, schedule cron jobs, manage LVM, and connect via SSH.

Section 2: Docker Fundamentals

Topics Covered:

1. Introduction to Docker – Containerization vs VMs, ecosystem, images, volumes

2. Docker Architecture – CLI, daemon, container lifecycle, registries

3. Docker Images – Base vs custom images, layers, pulling/pushing images

4. Docker Containers – Run, exec, attach, ephemeral vs persistent containers

5. Docker Networking – Bridge, host, overlay networks, port mapping

6. Docker Volumes & Storage – Persistent storage, backup/restore, volume management

7. Dockerfile & Image Building – Instructions, building custom images, tagging

8. Docker Compose – Multi-container orchestration, scaling, logging

9. Best Practices & Optimization – Image size, security, environment variables, cleanup

Hands-on Practice: Install Docker, build images, run containers, create volumes, compose multi-container applications, optimize Dockerfiles.

Section 3: AI Fundamentals

Topics Covered:

1. AI Overview – AI vs ML vs DL vs NN, types of AI (Narrow, General, Super)

2. Machine Learning (ML) Overview – Traditional algorithms, Approximate Nearest Neighbor (ANN), modern NN approaches

3. Neural Networks (NN) Basics – Layers, activation functions, structure

4. Deep Learning (DL) – CNNs, RNNs, LSTM, GRU, Transformers, GANs, Autoencoders, GNNs

5. ML & NN Comparisons – Features, datasets, complexity, speed, accuracy, use cases

6. AI Application Domains – NLP, CV, Multimodal AI, Healthcare, Finance

7. AI Models & Tokenization – Text, voice, image, multimodal models, tokenization

8. Memory in AI – Parametric, non-parametric, session, user session, global memory

9. OpenAI API Parameters – Temperature, max tokens

Hands-on Practice: Compare ML algorithms, train a small neural network, experiment with embeddings, tokenize text.

Section 4: Prompt Engineering for Beginners

Topics Covered:

1. Foundations of Prompt Engineering – Elements, importance, guiding AI outputs

2. Basic Techniques – Zero-shot, few-shot, instruction, role prompts

3. Intermediate Techniques – Chain-of-thought, self-consistency, reflection, meta prompts, delimiters

4. Advanced Techniques – Tree-of-thought, sketch-of-thought, token awareness, robustness, output formatting, hallucination minimization

5. Persona Engineering – System, user, assistant roles, expert/teacher/critic/creative personas

6. Best Practices – Clarity, context, examples, iteration

7. Practice & Iteration – Prompt refinement, reasoning exercises, persona practice, output formatting

Hands-on Practice: Design and test prompts, create personas, control output format, iterate for accuracy.

Section 5: Modern AI Applications – Agentic AI System Cores

Topics Covered:

1. Introduction to Agentic AI – Reasoning, tool usage, retrieval, adaptation

2. Core Components – LLMs, tools, memory (short-term & long-term), vector & graph databases

3. Foundation Blocks – AI agents, RAG, MA-LLM, Graph RAG

4. RAG Pipelines – Indexing, retrieval, generation strategies

Hands-on Practice: Build a mini RAG system with text retrieval and reasoning.

Section 6: AI Agents – Types & Roles

Topics Covered:

1. Agent Types by Decision Logic – Simple reflex, model-based, goal-based, utility-based, learning, multi-agent, hierarchical

2. Agent Types by Functional Role – Customer, employee, creative, data, code, security agents

Hands-on Practice: Identify agent types for real-world use cases, simulate decision logic.

Section 7: Vector Databases – Beginner-Friendly

Topics Covered:

1. What is a Vector & Embedding – Representation of data, dimensionality

2. Vector Databases – Storage, indexing, semantic search, applications

3. Search Types – Traditional, semantic, hybrid

4. Vector Types – Dense, sparse, quantized, applications

5. Indexing & Search Algorithms – Brute force, Approximate Nearest Neighbor (ANN), HNSW, IVF, PQ

6. Similarity Metrics – Cosine, dot product, Euclidean distance

Hands-on Practice: Create a vector database, index embeddings, perform similarity searches.