Demystifying AI terms: loop engineering, squads, and harness | S02E02 | The GitHub Podcast

AI terminology is evolving fast, with new terms like loop engineering, harness engineering, and squads popping up constantly. In episode 2 of season 2, Cassidy, Marlene, and GPS break down what these terms actually mean and how they apply to real agentic workflows. They also explore the differences between closed models, open weight models, and true open source AI. Stick around until the end for open source picks including Astro v7, RAE API, and Hugging Face Tao.

Links mentioned in the episode:

Loop Engineering by Addy Osmani - https://addyosmani.com/blog/loop-engineering/
Ralph Wiggum as a "software engineer" - https://ghuntley.com/ralph/
MCP - https://github.com/modelcontextprotocol
LangChain - https://github.com/langchain-ai/langchain
Astro 7 - https://astro.build/blog/astro-7/
RAE API - https://rae-api.com
Tau - https://github.com/huggingface/tau



— CHAPTERS —

00:00 Navigating confusing AI lingo
01:32 What is Loop Engineering?
06:08 Exploring Ralph loops and costs
09:16 Squads: parallel agent collaboration
11:42 Defining Harness Engineering
15:47 Hill Climbing: Improving agent performance
17:32 The Forward deployed engineer role
20:04 Open weight vs. open source models
22:37 Featured Open source projects
24:47 Wrapping up and farewell

#AI #OpenSource #GitHubPodcast

Stay up-to-date on all things GitHub by connecting with us:

YouTube: https://gh.io/subgithub
Blog: https://github.blog
X: https://twitter.com/github
LinkedIn: https://linkedin.com/company/github
Insider newsletter: https://resources.github.com/newsletter/
Instagram: https://www.instagram.com/github
TikTok: https://www.tiktok.com/@github

About GitHub
It’s where over 180 million developers create, share, and ship the best code possible. It’s a place for anyone, from anywhere, to build anything—it’s where the world builds software. https://github.com