The book is printed!


Embedded AI

Book is Available

The printed copies of Embedded AI: Intelligence at the Deep Edge arrived this week. After a year of early access chapters, revisions, and more hardware letting out the magic smoke than I care to admit, it is a physical book!

Getting a Copy

The book is available direct from No Starch Press. If you buy direct you can get the print edition plus the ebook.

Buying direct helps me. Author royalties on direct sales are roughly double what they are through retail (Amazon, etc.)

What is in the Book

Fourteen chapters across three parts: the foundations of embedded AI, sensors and signal processing on constrained hardware, and end-to-end builds. There are more than 25 projects on Arduino, ESP32, STM32, Raspberry Pi, and the RP2040/RP2350, all with code in the companion repository at github.com/Reefwing-Software/Embedded-AI. The custom PCBs for the audio, MIDI, and battery projects are shared projects on PCBWay, with a reader discount code in the repo README.

I will continue to share free technical articles and bonus content via this newsletter.

Thanks for following along. If you have questions about the content or the projects, please get in touch.

David Such

Reefwing Software

600 1st Ave, Ste 330 PMB 92768, Seattle, WA 98104-2246
​Unsubscribe · Preferences​

Embedded AI

Embedded systems engineer and author of Embedded AI: Intelligence at the Edge published by No Starch Press. 33 hands-on projects deploying machine learning on microcontrollers and edge devices. Subscribe to the Embedded AI newsletter for ongoing bonus content that extends the book, including new projects, hardware add-ons, and updates to the companion code. As a welcome, you will receive free links to a selection of my technical articles on Medium. These include the Chapter 13 Battery Monitor Shield bonus project and a guide to adding a 5-pin MIDI output to the Raspberry Pi Pico keyboard.

Read more from Embedded AI

What happens when you push intelligence straight to the physical edge—running AI models directly inside a sensor or a tiny microcontroller? Traditional programming is deterministic: given the same inputs, you always get the same results. But deploying AI on resource-constrained devices introduces a massive engineering shift. You are dealing with data-driven, probabilistic systems that must operate under strict battery, memory, and latency limitations.In a fascinating new Q&A with ODBMS.org, I...

I recently appeared on the award winning Embedded FM podcast with Elecia and Christopher White. It is called Episode 536: I’ve Seen a Giraffe. In this podcast we talk about the Embedded AI book and explore the boundary between classical signal processing, heuristics, and edge machine learning; IMU processing and sensor fusion; and how to determine what sort of ML fits on your processor. I also share my experience writing for No Starch Press and why future robotic architectures need a digital...

Prototype NFC Business Cards - new "How To" article next week Now that the Embedded AI book has been published, I will send out free links to my technical articles and podcast every couple of weeks or so. If you are not interested in receiving these just unsubscribe from the mailing list - I get it, email is crazy these days. Groupthink — Why AI Agent Groups Fail In 1985, the psychologists Garold Stasser and William Titus ran what became one of the most replicated experiments in group...