# How to AI

👋 This handbook is based on the following resources and my own experience (still new). I encourage you to explore the original sources for deeper insights and broader context.

Primarily:

* AI Engineering by Chip Huyen
* AI Product Manager's Handbook by Irene Bratsis

Others:

* [Building effective agents](https://www.anthropic.com/engineering/building-effective-agents) by Anthropic
* [The 2025 AI Engineer Reading List](https://www.latent.space/p/2025-papers) by Latent Space
* [12-Factor Agents](https://github.com/humanlayer/12-factor-agents) — Reliable LLM app principles by Dex Horthy ([video](https://www.youtube.com/watch?v=8kMaTybvDUw))
* [Zero to One: Learning Agentic Patterns](https://www.philschmid.de/agentic-pattern) by Phil Schmid
* [From Software Engineer to AI Engineer](https://newsletter.pragmaticengineer.com/p/from-software-engineer-to-ai-engineer) by Gergely Orosz
* [AI Engineer](https://youtube.com/@aidotengineer) YouTube channel by World's Fair - tons of real world use cases
* [AI Engineering Anti-patterns](https://youtu.be/tng20xPUpWg) by Chip Huyen

Pre-reading:

* ☕ For super basic concepts, check out [AI Agents Roadmap](https://roadmap.sh/ai-agents) by Roadmap.sh
* 😄 For a non-tech intro to LLMs, check out [Intro to Large Language Models](https://youtu.be/zjkBMFhNj_g?si=d1kKCg4cmzRpDpSe) by Andrej Karpathy
* 😍 For a tech-ish deep dive, check out [Deep Dive into LLMs like ChatGPT](https://youtu.be/7xTGNNLPyMI?si=AUg2P3-1JSZeyLJa) by Andrej Karpathy

This handbook is written with the help of Cursor AI with vibe coding and NotebookLM.

> **Note**: As someone new to AI Engineering myself, this handbook represents my public learning journey - [Jamie Wen](https://justlearning.club/about/)

Before we start, here are two diagrams about cognitive bias and hype cycle. I think they are quite interesting for this journey.

<div><figure><img src="https://3362254923-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F3RA6F4b1kPuyIJpX1t8w%2Fuploads%2Fgit-blob-7b4d3fc56c737db8677fff7298d41e849e622f9d%2Fdunning-kruger-effect-curve.png?alt=media" alt="Dunning-Kruger Effect Curve"><figcaption><p>Dunning-Kruger Effect Curve</p></figcaption></figure> <figure><img src="https://3362254923-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F3RA6F4b1kPuyIJpX1t8w%2Fuploads%2Fgit-blob-728ced92fb56c062b862dfc30d291abdcad36ca9%2Fgartner-hype-cycle.png?alt=media" alt="Gartner Hype Cycle"><figcaption><p>Gartner Hype Cycle</p></figcaption></figure></div>

Gartner Hype Cycle - AI 2025

<figure><img src="https://3362254923-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F3RA6F4b1kPuyIJpX1t8w%2Fuploads%2Fgit-blob-ecbe83e51ae426a7e0192f4396038cc1492a3d4d%2Fgartner-hype-cycle-ai-2025.png?alt=media" alt="Gartner Hype Cycle - AI 2025"><figcaption></figcaption></figure>

🦉, let's get started.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://jamiewen00.gitbook.io/ai-engineering-handbook/readme.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.