# Build an AI Agent (From Scratch) (Manning)

**URL:** <https://forum.devtalk.com/t/build-an-ai-agent-from-scratch-manning/218085>\
**Category:** AI Learning Resources\
**Tags:** llms, llm, mcp, ai, rag, ai-agents\
**Created:** [9 October 2025 10:13 UTC](https://forum.devtalk.com/t/build-an-ai-agent-from-scratch-manning/218085 "2025-10-09T10:13:00Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![ManningBooks](https://forum.devtalk.com/user_avatar/forum.devtalk.com/manningbooks/32/1650_2.png) [@ManningBooks](https://forum.devtalk.com/u/ManningBooks)\
**Post date:** [9 October 2025 10:13 UTC](https://forum.devtalk.com/t/build-an-ai-agent-from-scratch-manning/218085/1 "2025-10-09T10:13:00Z")

</div>

_Build an AI Agent (From Scratch)_ is a step-by-step guide to creating a working AI agent, starting with the bare essentials and growing your AI into a full-featured, real-world system.

 ![Song-HI](https://forum.devtalk.com/uploads/default/original/2X/a/a984872ea2f3ec8519d8cc5cd98b7f412745710b.jpeg)

| **Jungjun Hur and Younghee Song** |
| --- |

If you’ve been experimenting with agent frameworks and wondering what’s actually happening _under the hood_, this new book might be up your alley.

_Build an AI Agent (From Scratch)_ by **Younghee Song** and **Jungjun Hur** walks through the full process of implementing an LLM-powered agent—_from first principles_. Instead of relying on opaque libraries or “magic” abstractions, it helps you understand and build every component yourself.

The authors cover core mechanisms like:

- The **ReAct** loop (Thought → Action → Observation)

- Using **MCP** to make tool calls part of the agent’s workflow

- Building **memory modules** for context and long-term goals

- Implementing **Agentic RAG** for more relevant retrieval

- Adding **planning, reflection, and self-correction** capabilities

- Extending to **multi-agent systems** and specialized agents (like code executors)

By the end, you’ll have a fully functional AI agent that can reason, plan, and act — not just call APIs. The examples use open, inspectable code you can adapt for your own frameworks or research setups.

If you’re into building or tuning AI agents for production, research, or experimentation, this one feels like a practical deep dive into the “why” and “how” of agentic systems.

* * *

- Full details: [Build an AI Agent (From Scratch)](https://www.manning.com/books/build-an-ai-agent-from-scratch)

_Don’t forget you can get 45% off with your Devtalk discount! Just use the coupon code “**[devtalk.com](http://devtalk.com)**” at checkout 👍_