AI Engineering From Scratch: Learn AI From Zero • blog.dopana

Learn AI the Right Way — From Start to Finish#

84% of students already use AI tools, but only 18% feel prepared to use them professionally. AI Engineering From Scratch closes that gap — 511 lessons, 20 phases, free.

[!TIP] 150,639 readers · 241,669 page views in the last 30 days. This is the largest AI curriculum on GitHub.

What Is AI Engineering From Scratch?#

A complete curriculum where every lesson produces a reusable artifact:

flowchart TB
    P0["Phase 0: Setup & Tooling"] --> P1["Phase 1: Math Foundations"]
    P1 --> P2["Phase 2: ML Fundamentals"]
    P2 --> P3["Phase 3: Deep Learning Core"]
    P3 --> P4["Phase 4: Vision"]
    P3 --> P5["Phase 5: NLP"]
    P3 --> P6["Phase 6: Speech & Audio"]
    P3 --> P9["Phase 9: RL"]
    P5 --> P7["Phase 7: Transformers"]
    P7 --> P8["Phase 8: GenAI"]
    P7 --> P10["Phase 10: LLMs from Scratch"]
    P10 --> P11["Phase 11: LLM Engineering"]
    P10 --> P12["Phase 12: Agents"]
    P12 --> P13["Phase 13: MCP"]
    P12 --> P14["Phase 14: Agent Engineering"]
    P14 --> P15["Phase 15: Agent Skills"]

Stat	Value
Total lessons	511
Phases	20
Estimated time	~329 hours
Languages	Python, TypeScript, Rust, Julia
Artifact per lesson	Prompt, skill, agent, or MCP server

Where to Start?#

flowchart LR
    YOU["You"] --> P0["Phase 0: Setup"]
    YOU --> P1["Phase 1: Math"]
    YOU --> P11["Phase 11: LLM Eng"]
    YOU --> P14["Phase 14: Agent Eng"]
    YOU --> P13["Phase 13: MCP"]
    YOU --> P15["Phase 15: Skills"]

Your Goal	Start Here
Complete foundation	Phase 0: Setup and Tooling
Math + ML foundations	Phase 1: Math Foundations
Production LLM apps	Phase 11: LLM Engineering
Build agents	Phase 14: Agent Engineering
MCP (Model Context Protocol)	Phase 13: MCP route
Agent Skills	Phase 15: Agent Skills

Every Lesson Working Session#

flowchart LR
    R["📖 Read problem"] --> D["📐 Derive math"]
    D --> C["💻 Write code"]
    C --> T["🧪 Run test"]
    T --> A["📦 Keep artifact"]

[!NOTE] Every lesson follows the same loop: read the problem, derive the math, write the code, run the test, keep the artifact. No five-minute videos, no copy-paste, no hand-holding.

Install the AI Tutor#

npx skills add rohitg00/ai-engineering-from-scratch

bash

git clone https://github.com/rohitg00/ai-engineering-from-scratch.git
cd ai-engineering-from-scratch
python3 phases/00-setup-and-tooling/01-dev-environment/code/verify.py --route beginner

bash

Host Invocation#

Host	Start Course	MCP	Agent Skills	Quiz
Codex	`start-learning`	`learn-mcp`	`learn-agent-skills`	`check-understanding 13`
Claude Code	`/start-learning`	`/learn-mcp`	`/learn-agent-skills`	`/check-understanding 13`
Other	Use skill name	Use skill name	Use skill name	Use skill name

Example: First Evidence#

# python3 phases/00-setup-and-tooling/01-dev-environment/code/verify.py --route beginner
# Result: Environment setup check
# If pass → you're ready for Phase 1

python

# python3 phases/01-math-foundations/01-linear-algebra-intuition/code/vectors.py
# Result: matrix × vector = neural network layer operation
# Save terminal output as first evidence

python

Conclusion#

AI Engineering From Scratch doesn’t just teach AI — you build it. End-to-end, by hand. Free, open source, runs on your laptop.

🔗 Repository: github.com/rohitg00/ai-engineering-from-scratch ↗ 🔗 Website: aiengineeringfromscratch.com ↗