Joe Leo and I have officially launched a very special first episode of The Ruby AI Podcast: "Beyond Chat: Phoenix Tests, Ruby Agents & the AI Tipping Point" In the pilot episode, we chat about shipping real AI products in Ruby, how Phoenix got started, and why Ruby syntax actually makes this weird new world fun to build in. Hope you'll come along for the ride. (And send us your favorite AI coding mishaps—we might just feature them in a future episode!) therubyaipodcast.com/

Introducing the Fusion API, the smartest compound model in the market. Fusion achieves Fable-level intelligence at half the price. How it works 👇

Been too busy lately to tweet every nice Ruby perf PR as I spot them. So I went through my notes and dumped all the notable ones into a single roundup. Some of these are insane (like 800000x speedup) - enjoy! 🚀 mensfeld.pl/2026/06/ruby-per… #ruby #performance

Your users are lying to you (politely). Matt Biilmann (@biilmann), co-founder and CEO at Netlify, says users will always tell you your product is "really cool" after you show it to them. That's not the feedback you should pay attention to. Instead, if they don't try to use your tool after you've sat down and walked them through it, you have a problem. In this episode of Dev Propulsion Labs, Matt and @vmelnikova_en cover: - The early-days lessons that led to building Netlify - The four pillars of agent experience - Why DX is no longer enough - How the addressable market for software just went from 17 million developers to 3 billion people Links to the full episode below.

329 BILLION requests in one day. Tell me you project is battle-tested without telling me it’s battle-tested 😂

Link: Spinel: A Different Direction for Ruby Performance – Linking Ruby knowledge from the most remote places in the world. : rubystacknews.com/2026/04/27…

Finally posting my photos from the @ruby_artificial event from February. Love @thecodenamev's jacket. flic.kr/s/aHBqjCRsh1

I build production systems with Claude Code every day. Not demos. Not prototypes. Production. This HN thread has 1100 points saying it's "unusable for complex tasks." I get the frustration. But the problem isn't Claude Code - it's that people treat it like autocomplete. I built a skill system that gives it persistent memory, structured context, and repeatable workflows. The difference between "unusable" and "indispensable" is scaffolding. The tool isn't broken. The workflow is. news.ycombinator.com/item?id…

This is one hell of an edition you're not gonna wont to miss! A huge thank you to @mattsolt for keeping this up (he curates this by hand!). And a feature segment for ups.dev ❣️

"The code that we have is a liability. The system is the asset we're building." @chadfowler, VC at Blue Yard Capital (@blueyard) and former CTO at Wunderlist, sits down with @guypod to discuss the Phoenix Architecture: software designed to be replaced rather than maintained. In this episode: • why was the code written by Chad never longer than a page • how he replaced 70% of a codebase in 3 months and cut costs by 75% • shipping AI code no human ever reviewed, and how to make it safe • the shadow specs your agents are making without you • why your system should work with the worst LLM, not just the best If you're still thinking about your codebase the old way, this one will change that. (0:00) Trailer (1:07) AI DevCon (2:01) Introduction (3:41) Origin story: euthanising legacy systems (5:45) Immutable infrastructure as inspiration (6:48) Disposable software and immutable code (9:00) Cattle versus pets for code (10:03) Making disposable code feasible at Wunderlist (12:31) Phoenix Architecture (15:16) Extreme programming lesson: do hard things constantly (17:04) What level of detail should specs have? (19:15) Pace layers and stable regeneration (22:37) New programming languages versus patterns (29:47) Compiling to system architectures (30:45) Training the programmer versus defining the system (35:03) Personalised and malleable software (37:48) Local first and shared data models (45:08) Evaluations as the real codebase (49:36) Testing the agent versus testing the system (55:38) Path of adoption (01:00:48) Wrap-up

Next week is the one year anniversary edition of the Ruby AI Newsletter, and its already shaping up to be a big one. If you have something you want to announce, let me know!

I made a fork of superpowers and change it to work with Ruby and Ruby on Rails: github.com/lucianghinda/supe… Integrated a bunch of existing skills - I linked them in the Readme if you want to use them directly and added my own for Ruby and Testing.