рџ“ё Introducing OuijaRouter
Originally appeared on justin․searls․co - Digest . Finally figured out a bulletproof system for landing on the best model for the job.
Stories from Searls
Use this page to scan recent stories from Searls, see the themes that keep appearing, and jump into complete story briefs.
Recent curated reads
Traces to Insights: Evaluating LLM Apps
Originally appeared on OmbuLabs.ai . Tracing helps answer an important question: what happened? But knowing what happened isn’t the same as knowing whether it was any good. That’s where evaluation comes in. And if you already have traces running in production, you’re closer to a solid evaluation system than you might t
Rails For Marketing Sites in the AI Era
Originally appeared on Judoscale Dev Blog . A couple of years ago, we rewrote Judoscale’s marketing site from NextJS to Ruby on Rails. I enjoyed the process so much that I made a video sharing how it worked, and Jon wrote a spicy piece arguing that Rails was a perfect fit for mostly-static marketing sites like ours, an
Episode 550: XORuby with Jim Remsik
Originally appeared on The Ruby on Rails Podcast . Jim Remsik, founder of Flagrant and organizer of XORuby, joins David to talk about what he’s learned from taking a Ruby conference on the road. XORuby was designed around a simple premise: traditional conferences are valuable, but travel costs, time away from work, and
On Rails — Eddie Galindo & Kagen Hearn: Rate Limiting For Your Customers
Originally appeared on Ruby on Rails: Compress the complexity of modern web apps . Eddie Galindo is an engineering lead at Ascend and Kagen Hearn is a senior software engineer there, working on a Rails app that helps insurance agencies move and reconcile money. Robby, Eddie, and Kagen get into why Ascend still runs one
10 anti-AI slop moves for frontend projects going faster than humans can review
Originally appeared on Evil Martians . Authors: Yuri Mikhin, Frontend Engineer, and Travis Turner, Tech Editor Topics: DX, AI, Agent Experience, TypeScript, React, Agentic development, LLMs, Continuous Integration Ten checks that catch what AI-written frontend code hides: contract codegen, boundary linting, mutation te
We are all juniors again
Originally appeared on Hi, we're Arkency . We are all juniors again A long, long time ago, when Akinator was the peak of “advanced AI” on the internet, before services became micro, and deployments meant sending a file directly from a local computer via FTP to a server, I was introduced to the Dreyfus Skill Model. As a
Repay Tech Debt with the Strangler Fig Pattern
Originally appeared on The Rails Tech Debt Blog . Replacing a business-critical legacy system does not have to mean committing to a risky, all-at-once rewrite. The strangler fig pattern offers a practical alternative: migrate one capability at a time, run the old and new systems side by side, and gradually retire the l
RubyLLM 2.0: The Agentic Loop, Exposed
Originally appeared on Carmine Paolino . Strip any agent framework down and you find the same loop: call the model, run the tools it asked for, call the model again, stop when it answers without wanting a tool. In RubyLLM 1.x that loop lived inside ask , sealed. In RubyLLM 2.0, you can also make it yours. # Run the age
Agents on Rails: Claude Fable 5.1 and GLM 5.3 Flash (formerly known as ox-alpha)
Originally appeared on Ruby on Rails: Compress the complexity of modern web apps . Claude Fable 5.1 dropped yesterday. See how it handles real Rails tasks, and where it landed on the leaderboard today. We also finally have a name for the stealth model from the last round . Fable 5.1: We have a new best. Fable 5.1 score
Thanking our silver sponsors, and Carolyn Cole
Originally appeared on Hanakai . Welcome to week three of our 2026 sponsorship drive ! Progress from week two We received two one-time individual contributions and one new monthly individual sponsor since our last update, bringing us another $760 closer to our goal for 2026. (I’m basing these estimates on monthly spons
Frequently Played September 2026
Originally appeared on Posts on Kevin Murphy . Frequently Played 🔗 I tend to listen to the same songs or albums on repeat that are evocative of how I’m feeling or what’s going on with me. Here is what I’m currently listening to over, and over, and over, and over, again. Jolene 🔗 Thanks for the name Dolly. And for mod
Read this source in the app
Open the app view when you want faster scanning, saved stories, and source-focused reading in one place.