Common Sense Guide Structures Algorithms Python

This interview was recorded for the GOTO Book Club. #GOTOcon #GOTObookclub http://gotopia.tech/bookclub Jay Wengrow - Author of “A Common-Sense Guide to AI Engineering” & CEO of Actualize @JayWengrow Kris Jenkins - Lifelong Computer Geek and Podcast Host @krisajenkins RESOURCES Jay https://x.com/jaywengrow https://github.com/jaywengrow https://www.linkedin.com/in/jaywengrow https://www.commonsensedev.com Kris https://bsky.app/profile/krisajenkins.bsky.social https://twitter.com/krisajenkins https://www.linkedin.com/in/krisjenkins https://github.com/krisajenkins http://blog.jenkster.com Links https://youtu.be/p-R7Doigqzc https://youtu.be/R7Dv2h3tYCU https://youtu.be/u1nuS5MUFfc https://youtu.be/fROpZ6EYa54 https://youtu.be/3a0WHZVb1Gg https://youtu.be/SOz66dcsuT8 https://youtu.be/MznD2DzlQCc https://youtu.be/N53Gsz0Gm4c DESCRIPTION In this GOTO Book Club episode, host Kris Jenkins sits down with Jay Wengrow — founder of coding bootcamp Actualize and author of the bestselling Common-Sense Guide to Data Structures and Algorithms — to dig into his latest book, A Common-Sense Guide to AI Engineering. Jay demystifies how AI agents actually work: at heart, they're a clever hack where your code intercepts an LLM's text output, watches for special notation, and triggers real functions when it spots them. From there, the conversation expands into guardrails (regex, judge LLMs, and specialist ML models), multi-agent architectures for complex tasks, and a hands-on example of a 150-line podcast-generating app built entirely from scratch — no framework required. The real throughline is a pragmatic, sceptical take on the current AI tooling landscape. Jay argues that frameworks can lock you into patterns that haven't been proven yet, and that the field is too new to know which abstractions are genuinely worth having. His rule of thumb: reach for a framework only when it will do something meaningfully better than you can — not just faster. The book was deliberately written around fundamentals rather than specific tools, so it ages well even as the ecosystem moves at breakneck speed. The conclusion is refreshingly grounded: understand the LLM's inherent limitations, build the middle layer thoughtfully, and don't outsource your system prompts to anyone — or anything. TIMECODES 00:00 Intro 03:43 How AI agents actually work: The clever hack under the hood 09:56 Multi-agent systems: When one LLM isn't enough 15:40 Frameworks vs building from scratch 23:26 Writing a book for a fast-moving field 25:24 Outro RECOMMENDED BOOKS Jay Wengrow • A Common-Sense Guide to AI Engineering • https://pragprog.com/titles/jwpaieng Jay Wengrow • A Common-Sense Guide to Data Structures and Algorithms • https://amzn.to/4bPiTjd Jay Wengrow • A Common-Sense Guide to Data Structures & Algorithms in Python • https://amzn.to/3PpwtlT Jay Wengrow • A Common-Sense Guide to Data Structures and Algorithms in JavaScript • https://amzn.to/4dDSZBl https://bsky.app/profile/gotocon.com https://twitter.com/GOTOcon https://www.linkedin.com/company/goto- https://www.instagram.com/goto_con https://www.facebook.com/GOTOConferences #AiEngineering #AIAgents #MultiAgentic #CommonSense #AIGuide #TodayInTech #SoftwareEngineering #Programming #JayWengrow #KrisJenkins #BookClub CHANNEL MEMBERSHIP BONUS Join this channel to get early access to videos & other perks: https://www.youtube.com/channel/UCs_tLP3AiwYKwdUHpltJPuA/join Looking for a unique learning experience? Attend the next GOTO conference near you! Get your ticket at https://gotopia.tech Sign up for updates and specials at https://gotopia.tech/newsletter SUBSCRIBE TO OUR CHANNEL - new videos posted almost daily. https://www.youtube.com/user/GotoConferences/?sub_confirmation=1