Learn AI Engineering! Learn it. Build it. Ship it for others.

★ 79,036⑂ 14,093👁 460⑃ 640● 132▤ 12
PythonMITCreated 2026-03-18aiengineeringfromscratch.com
下载:Edition 2026.11.3: Agent Substrate 101 and Clean Lesson URLsEdition-2026.11.3 ↓2026.11.32026-11-13
+181
日增长
+1,113
周增长
+12,336
月增长
79,036
stars
14,093
forks
460
watchers
640
prs
132
issues
12
releases

README

Implement model internals, retrieval pipelines, and agent runtimes. Test them, inspect failures, and keep the code and evaluation results.

Start learning · Choose a path · Try a lab · Build a project · Browse the curriculum

Free, open source, MIT. Learn on the website, with a coding agent, or by running local code.

 542 lessons. 20 phases. Python, TypeScript, Rust, Julia, Go.

Turn your coding agent into a tutor with one command:

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



  
  
  
  
  



Read in your language


  🇬🇧 English ·
  🇨🇳 简体中文 ·
  🇹🇼 繁體中文(台灣) ·
  🇯🇵 日本語 ·
  🇰🇷 한국어 ·
  🇵🇹 Português ·
  🇧🇷 Português (Brasil) ·
  🇪🇸 Español ·
  🇩🇪 Deutsch ·
  🇫🇷 Français ·
  🇮🇹 Italiano ·
  🇳🇱 Nederlands ·
  🇵🇱 Polski ·
  🇨🇿 Čeština ·
  🇷🇴 Română ·
  🇭🇺 Magyar ·
  🇬🇷 Ελληνικά ·
  🇸🇪 Svenska ·
  🇩🇰 Dansk ·
  🇳🇴 Norsk ·
  🇫🇮 Suomi ·
  🇷🇺 Русский ·
  🇺🇦 Українська ·
  🇹🇷 Türkçe ·
  🇮🇱 עברית ·
  🇸🇦 العربية ·
  🇮🇷 فارسی ·
  🇮🇳 हिन्दी ·
  🇧🇩 বাংলা ·
  🇵🇰 اردو ·
  🇹🇭 ไทย ·
  🇻🇳 Tiếng Việt ·
  🇮🇩 Bahasa Indonesia ·
  🇵🇭 Tagalog




 Sponsors


  



  Your support keeps every lesson free and open source. See all supporters · Become a sponsor


 Why build it from scratch

A framework call hides the part that breaks. When a loss turns into NaN or an agent repeats the same tool call, the person who wrote the small version knows where to look. Most lessons have you write that small version first and run it, then show where production tools do the same work.


  
    
    
    
    
  



Text version

- 01 · THE PROBLEM: An LLM returns text. It cannot act.
- 02 · BUILD IT: A ReAct loop in stdlib Python.
- 03 · USE IT: Where agent SDKs run the same loop.
- 04 · SHIP IT: skill-agent-loop.md, ready for your agent.






 Learning paths

| Route | Starting lesson |
|---|---|
| Model foundations | Setup and tooling |
| LLM systems | Prompt engineering |
| Agents and delivery | The agent loop |

Compare career paths · Prerequisites and study time



 Gradient descent

Twenty starting points follow gradient descent on a quadratic loss. The graph shows their positions and mean loss after each update.


  
    
      
      
      
      
      
      
      
      
    
  


Adjust the learning rate in the lesson · Compare GD, momentum, and Adam in code



 Projects

Three projects with staged starters, reference implementations, and local graders. Run commands from the repository root after setup. Starters fail until you implement the stages.


01 · Retrieval Evaluation Lab · Python · Ranking metrics and regression checks

A candidate improves mean NDCG while one query ranks its most relevant evidence lower. Build a query-by-query comparison that reports the regression and can fail a release check.

Use Python 3.10+. Review RAG and model evaluation. Implement ranking validation, precision and recall, rank-sensitive metrics, then system comparison.

bash
python3 scripts/project_test.py retrieval-evaluation-lab \
  --init learning-artifacts/retrieval-eval

Top issues

Discussions

Latest release

Edition 2026.11.3: Agent Substrate 101 and Clean Lesson URLs v2026.11.3 2026-11-13
Run stateful agents on Kubernetes with numbers you can check. This edition adds Agent Substrate 101, a manual built from 24 recorded experiments, and moves every course lesson to a short, readable URL.

Start learning · Agent Substrate 101 · All manuals

 Agent Substrate 101

A manual for Agent Substrate v1.0.0, with kagent 1.0, agentgateway v1.7.0 and Agent Executor. It goes from the first actor to a cluster that you can size, connect, upgrade, and debug.

| | |
|---|---|
| Sections | 40 in 9 parts, and 10 reference sections |
| Figures | 75, most of them showing each run, not only a median |

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON