AI-Engineering-Playbook

KO | EN

gitlite — search

#http #markdown #anthropic #ai #rust #terminal #openai #machine-learning #codex #chatbot

AI-Engineering-Playbook

(★ 10)

No description available.

File Explorer

ZIP Download

- - cheat_sheet.md
  - interview_questions.md
  - metadata.yaml
  - notebook.ipynb
  - production_notes.md
  - README.md
- - cheat_sheet.md
  - interview_questions.md
  - metadata.yaml
  - notebook.ipynb
  - production_notes.md
  - README.md
- - cheat_sheet.md
  - interview_questions.md
  - metadata.yaml
  - notebook.ipynb
  - production_notes.md
  - README.md
- - cheat_sheet.md
  - interview_questions.md
  - metadata.yaml
  - notebook.ipynb
  - production_notes.md
  - README.md
- - cheat_sheet.md
  - interview_questions.md
  - metadata.yaml
  - notebook.ipynb
  - production_notes.md
  - README.md
- - cheat_sheet.md
  - interview_questions.md
  - metadata.yaml
  - notebook.ipynb
  - production_notes.md
  - README.md
- - cheat_sheet.md
  - interview_questions.md
  - metadata.yaml
  - notebook.ipynb
  - production_notes.md
  - README.md
- - cheat_sheet.md
  - interview_questions.md
  - metadata.yaml
  - notebook.ipynb
  - production_notes.md
  - README.md
- - cheat_sheet.md
  - interview_questions.md
  - metadata.yaml
  - notebook.ipynb
  - production_notes.md
  - README.md
- - cheat_sheet.md
  - interview_questions.md
  - metadata.yaml
  - notebook.ipynb
  - production_notes.md
  - README.md
- - cheat_sheet.md
  - interview_questions.md
  - metadata.yaml
  - notebook.ipynb
  - production_notes.md
  - README.md
- - cheat_sheet.md
  - interview_questions.md
  - metadata.yaml
  - notebook.ipynb
  - production_notes.md
  - README.md
- - cheat_sheet.md
  - interview_questions.md
  - metadata.yaml
  - notebook.ipynb
  - production_notes.md
  - README.md
- - cheat_sheet.md
  - interview_questions.md
  - metadata.yaml
  - notebook.ipynb
  - production_notes.md
  - README.md
- - cheat_sheet.md
  - interview_questions.md
  - metadata.yaml
  - notebook.ipynb
  - production_notes.md
  - README.md
- - cheat_sheet.md
  - interview_questions.md
  - metadata.yaml
  - notebook.ipynb
  - production_notes.md
  - README.md
- README.md
- faq.md
- getting_started.md
- installation.md
- learning_path.md
- prerequisites.md
- CODING_STANDARDS.md
- CONTRIBUTING_GUIDE.md
- - __init__.py
  - constants.py
  - feature_engineering.py
  - metrics.py
  - preprocessing.py
  - splitting.py
  - utilities.py
  - visualization.py
- README.md
- test_dataset_generators.py
- test_episode_structure.py
- test_shared.py
.gitignore
CHANGELOG.md
CODE_OF_CONDUCT.md
CONTRIBUTING.md
HUB.md
LICENSE
README.md
RELEASE_NOTES_v1.0.0.md
requirements.txt
SECURITY.md
SUPPORT.md

# Use via CDN

jsDelivr

jsDelivr serves any public GitHub repository as a CDN with zero setup. Pick a version and a file to get a ready-to-paste link and snippet.

Version

File

Link

Example

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

> **An open-source, engineering-first learning system that teaches professionals how to think, build, evaluate, and productionize AI systems through practical engineering judgment — not just algorithms, frameworks, or tools.**

---

## What This Is

This is NOT another AI course.

This is NOT another collection of notebooks.

This is an engineering-first educational playbook whose purpose is to teach professionals how to think like AI engineers through practical engineering judgment.

We teach:
- **Engineering thinking** — not just algorithms
- **Mental models** — not just frameworks
- **Production reasoning** — not just APIs
- **Practical implementation** — not toy examples
- **Debugging intuition** — not just syntax
- **System design** — not isolated tricks

---

## Who This Is For

**Primary:** Software engineers, data scientists, and ML practitioners who want to move from "knowing AI" to "engineering AI systems."

**Secondary:** Technical leaders evaluating AI talent, interviewers seeking consistent evaluation criteria, and teams building internal AI training.

**Not for:** People seeking passive consumption. Every lesson requires active thinking, building, and decision-making.

---

## The Learning Journey

```
LinkedIn    →  Curiosity
Medium      →  Understanding
GitHub      →  Implementation
Portfolio   →  Professional Capability
Career      →  Impact
```

No platform duplicates another. Every platform has exactly one responsibility.

---

## Module Index

| Module | Topic | Episodes | Status |
|---------|-------|----------|--------|
| 01 | Machine Learning for AI Engineers | 15 + Capstone | Published (v1.0.0) |
| 02 | Deep Learning for AI Engineers | — | Planned |
| 03 | NLP for AI Engineers | — | Planned |
| 04 | Generative AI for AI Engineers | — | Planned |
| 05 | RAG Engineering | — | Planned |
| 06 | AI Agents | — | Planned |
| 07 | Agentic AI | — | Planned |

---

## Start Learning

📋 **Prerequisite Guide:** [docs/prerequisites.md](docs/prerequisites.md)  
📖 **Navigate the Playbook:** [HUB.md](HUB.md)  
🚀 **Getting Started:** [docs/getting_started.md](docs/getting_started.md)  
🛠️ **Installation Guide:** [docs/installation.md](docs/installation.md)  
🎓 **Begin Module 01:** [01-Machine-Learning/](01-Machine-Learning/)

---

## How to Contribute

This playbook is open-source and community-driven. We welcome contributions from learners and community members! Please see our [Contribution Guide](Governance/CONTRIBUTING_GUIDE.md) and [Coding Standards](Governance/CODING_STANDARDS.md) to get started.

---

## Non-Negotiable Principles

- Every episode answers exactly **ONE** engineering question
- Every episode teaches exactly **ONE** mental model
- Every episode contains exactly **ONE** unforgettable insight
- Every episode contains exactly **ONE** hero diagram
- Every episode teaches exactly **ONE** engineering decision
- Every episode satisfies **Knowledge Independence**
- Every episode prefers **timeless mechanisms** over temporary trends
- **Standardize FUNCTION. Never standardize FORMAT.**
- **Ship at 80%. Improve using evidence.**

---

## Success Definition

Success is NOT more articles, notebooks, or stars.

Success is:
- Learners making better engineering decisions
- Learners thinking like AI engineers
- Learners building production-ready systems

Everything we build should move the learner one step closer to becoming a professional AI engineer.

---

## License

MIT License — Free for personal, educational, and commercial use.

---

*Architecture Version 1.0 — Module 01 Released (v1.0.0).*

AI-Engineering-Playbook

Owner Repos

File Explorer

# Use via CDN

Was this content helpful?

Recent Feedback

AI-Engineering-Playbook

Owner Repos

File Explorer

# Use via CDN

Was this content helpful?

Recent Feedback

Download README